diff --git a/1-Introduction/1-intro-to-ML/README.md b/1-Introduction/1-intro-to-ML/README.md deleted file mode 100644 index ce3b13ef..00000000 --- a/1-Introduction/1-intro-to-ML/README.md +++ /dev/null @@ -1,145 +0,0 @@ -# Introduction to machine learning - -## [Pre-lecture quiz](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/1/) - ---- - -[![ML for beginners - Introduction to Machine Learning for Beginners](https://img.youtube.com/vi/6mSx_KJxcHI/0.jpg)](https://youtu.be/6mSx_KJxcHI "ML for beginners - Introduction to Machine Learning for Beginners") - -> đŸŽĨ Click the image above for a short video working through this lesson. - -Welcome to this course on classical machine learning for beginners! Whether you're completely new to this topic, or an experienced ML practitioner looking to brush up on an area, we're happy to have you join us! We want to create a friendly launching spot for your ML study and would be happy to evaluate, respond to, and incorporate your [feedback](https://github.com/microsoft/ML-For-Beginners/discussions). - -[![Introduction to ML](https://img.youtube.com/vi/h0e2HAPTGF4/0.jpg)](https://youtu.be/h0e2HAPTGF4 "Introduction to ML") - -> đŸŽĨ Click the image above for a video: MIT's John Guttag introduces machine learning - ---- -## Getting started with machine learning - -Before starting with this curriculum, you need to have your computer set up and ready to run notebooks locally. - -- **Configure your machine with these videos**. Use the following links to learn [how to install Python](https://youtu.be/CXZYvNRIAKM) in your system and [setup a text editor](https://youtu.be/EU8eayHWoZg) for development. -- **Learn Python**. It's also recommended to have a basic understanding of [Python](https://docs.microsoft.com/learn/paths/python-language/?WT.mc_id=academic-77952-leestott), a programming language useful for data scientists that we use in this course. -- **Learn Node.js and JavaScript**. We also use JavaScript a few times in this course when building web apps, so you will need to have [node](https://nodejs.org) and [npm](https://www.npmjs.com/) installed, as well as [Visual Studio Code](https://code.visualstudio.com/) available for both Python and JavaScript development. -- **Create a GitHub account**. Since you found us here on [GitHub](https://github.com), you might already have an account, but if not, create one and then fork this curriculum to use on your own. (Feel free to give us a star, too 😊) -- **Explore Scikit-learn**. Familiarize yourself with [Scikit-learn](https://scikit-learn.org/stable/user_guide.html), a set of ML libraries that we reference in these lessons. - ---- -## What is machine learning? - -The term 'machine learning' is one of the most popular and frequently used terms of today. There is a nontrivial possibility that you have heard this term at least once if you have some sort of familiarity with technology, no matter what domain you work in. The mechanics of machine learning, however, are a mystery to most people. For a machine learning beginner, the subject can sometimes feel overwhelming. Therefore, it is important to understand what machine learning actually is, and to learn about it step by step, through practical examples. - ---- -## The hype curve - -![ml hype curve](images/hype.png) - -> Google Trends shows the recent 'hype curve' of the term 'machine learning' - ---- -## A mysterious universe - -We live in a universe full of fascinating mysteries. Great scientists such as Stephen Hawking, Albert Einstein, and many more have devoted their lives to searching for meaningful information that uncovers the mysteries of the world around us. This is the human condition of learning: a human child learns new things and uncovers the structure of their world year by year as they grow to adulthood. - ---- -## The child's brain - -A child's brain and senses perceive the facts of their surroundings and gradually learn the hidden patterns of life which help the child to craft logical rules to identify learned patterns. The learning process of the human brain makes humans the most sophisticated living creature of this world. Learning continuously by discovering hidden patterns and then innovating on those patterns enables us to make ourselves better and better throughout our lifetime. This learning capacity and evolving capability is related to a concept called [brain plasticity](https://www.simplypsychology.org/brain-plasticity.html). Superficially, we can draw some motivational similarities between the learning process of the human brain and the concepts of machine learning. - ---- -## The human brain - -The [human brain](https://www.livescience.com/29365-human-brain.html) perceives things from the real world, processes the perceived information, makes rational decisions, and performs certain actions based on circumstances. This is what we called behaving intelligently. When we program a facsimile of the intelligent behavioral process to a machine, it is called artificial intelligence (AI). - ---- -## Some terminology - -Although the terms can be confused, machine learning (ML) is an important subset of artificial intelligence. **ML is concerned with using specialized algorithms to uncover meaningful information and find hidden patterns from perceived data to corroborate the rational decision-making process**. - ---- -## AI, ML, Deep Learning - -![AI, ML, deep learning, data science](images/ai-ml-ds.png) - -> A diagram showing the relationships between AI, ML, deep learning, and data science. Infographic by [Jen Looper](https://twitter.com/jenlooper) inspired by [this graphic](https://softwareengineering.stackexchange.com/questions/366996/distinction-between-ai-ml-neural-networks-deep-learning-and-data-mining) - ---- -## Concepts to cover - -In this curriculum, we are going to cover only the core concepts of machine learning that a beginner must know. We cover what we call 'classical machine learning' primarily using Scikit-learn, an excellent library many students use to learn the basics. To understand broader concepts of artificial intelligence or deep learning, a strong fundamental knowledge of machine learning is indispensable, and so we would like to offer it here. - ---- -## In this course you will learn: - -- core concepts of machine learning -- the history of ML -- ML and fairness -- regression ML techniques -- classification ML techniques -- clustering ML techniques -- natural language processing ML techniques -- time series forecasting ML techniques -- reinforcement learning -- real-world applications for ML - ---- -## What we will not cover - -- deep learning -- neural networks -- AI - -To make for a better learning experience, we will avoid the complexities of neural networks, 'deep learning' - many-layered model-building using neural networks - and AI, which we will discuss in a different curriculum. We also will offer a forthcoming data science curriculum to focus on that aspect of this larger field. - ---- -## Why study machine learning? - -Machine learning, from a systems perspective, is defined as the creation of automated systems that can learn hidden patterns from data to aid in making intelligent decisions. - -This motivation is loosely inspired by how the human brain learns certain things based on the data it perceives from the outside world. - -✅ Think for a minute why a business would want to try to use machine learning strategies vs. creating a hard-coded rules-based engine. - ---- -## Applications of machine learning - -Applications of machine learning are now almost everywhere, and are as ubiquitous as the data that is flowing around our societies, generated by our smart phones, connected devices, and other systems. Considering the immense potential of state-of-the-art machine learning algorithms, researchers have been exploring their capability to solve multi-dimensional and multi-disciplinary real-life problems with great positive outcomes. - ---- -## Examples of applied ML - -**You can use machine learning in many ways**: - -- To predict the likelihood of disease from a patient's medical history or reports. -- To leverage weather data to predict weather events. -- To understand the sentiment of a text. -- To detect fake news to stop the spread of propaganda. - -Finance, economics, earth science, space exploration, biomedical engineering, cognitive science, and even fields in the humanities have adapted machine learning to solve the arduous, data-processing heavy problems of their domain. - ---- -## Conclusion - -Machine learning automates the process of pattern-discovery by finding meaningful insights from real-world or generated data. It has proven itself to be highly valuable in business, health, and financial applications, among others. - -In the near future, understanding the basics of machine learning is going to be a must for people from any domain due to its widespread adoption. - ---- -# 🚀 Challenge - -Sketch, on paper or using an online app like [Excalidraw](https://excalidraw.com/), your understanding of the differences between AI, ML, deep learning, and data science. Add some ideas of problems that each of these techniques are good at solving. - -# [Post-lecture quiz](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/2/) - ---- -# Review & Self Study - -To learn more about how you can work with ML algorithms in the cloud, follow this [Learning Path](https://docs.microsoft.com/learn/paths/create-no-code-predictive-models-azure-machine-learning/?WT.mc_id=academic-77952-leestott). - -Take a [Learning Path](https://docs.microsoft.com/learn/modules/introduction-to-machine-learning/?WT.mc_id=academic-77952-leestott) about the basics of ML. - ---- -# Assignment - -[Get up and running](assignment.md) diff --git a/1-Introduction/1-intro-to-ML/assignment.md b/1-Introduction/1-intro-to-ML/assignment.md deleted file mode 100644 index dbb448c3..00000000 --- a/1-Introduction/1-intro-to-ML/assignment.md +++ /dev/null @@ -1,9 +0,0 @@ -# Get Up and Running - -## Instructions - -In this non-graded assignment, you should brush up on Python and get your environment up and running and able to run notebooks. - -Take this [Python Learning Path](https://docs.microsoft.com/learn/paths/python-language/?WT.mc_id=academic-77952-leestott), and then get your systems setup by going through these introductory videos: - -https://www.youtube.com/playlist?list=PLlrxD0HtieHhS8VzuMCfQD4uJ9yne1mE6 diff --git a/1-Introduction/1-intro-to-ML/images/ai-ml-ds.png b/1-Introduction/1-intro-to-ML/images/ai-ml-ds.png deleted file mode 100644 index 11c9bf37..00000000 Binary files a/1-Introduction/1-intro-to-ML/images/ai-ml-ds.png and /dev/null differ diff --git a/1-Introduction/1-intro-to-ML/images/hype.png b/1-Introduction/1-intro-to-ML/images/hype.png deleted file mode 100644 index 89469139..00000000 Binary files a/1-Introduction/1-intro-to-ML/images/hype.png and /dev/null differ diff --git a/1-Introduction/1-intro-to-ML/lesson-1.pdf b/1-Introduction/1-intro-to-ML/lesson-1.pdf deleted file mode 100644 index c0a6778f..00000000 Binary files a/1-Introduction/1-intro-to-ML/lesson-1.pdf and /dev/null differ diff --git a/1-Introduction/1-intro-to-ML/translations/README.bn.md b/1-Introduction/1-intro-to-ML/translations/README.bn.md deleted file mode 100644 index 5d1ac4dc..00000000 --- a/1-Introduction/1-intro-to-ML/translations/README.bn.md +++ /dev/null @@ -1,151 +0,0 @@ -# āĻŽā§‡āĻļāĻŋāĻ¨ āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚ āĻāĻ° āĻ¸ā§‚āĻšāĻ¨āĻž - - -[![ML, AI, deep learning - What's the difference?](https://img.youtube.com/vi/lTd9RSxS9ZE/0.jpg)](https://youtu.be/lTd9RSxS9ZE "ML, AI, deep learning - What's the difference?") - -> đŸŽĨ āĻŽā§‡āĻļāĻŋāĻ¨ āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚, āĻāĻ†āĻ‡(āĻ†āĻ°ā§āĻŸāĻŋāĻĢāĻŋāĻļāĻŋā§ŸāĻžāĻ˛ āĻ‡āĻ¨ā§āĻŸāĻŋāĻ˛āĻŋāĻœā§‡āĻ¨ā§āĻ¸) āĻāĻŦāĻ‚ āĻĄāĻŋāĻĒ āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚ āĻāĻ° āĻŽāĻ§ā§āĻ¯ā§‡ āĻĒāĻžāĻ°ā§āĻĨāĻ•ā§āĻ¯ āĻāĻ° āĻ†āĻ˛ā§‹āĻšāĻ¨āĻž āĻœāĻžāĻ¨āĻ¤ā§‡ āĻ‰āĻĒāĻ°ā§‡āĻ° āĻ›āĻŦāĻŋāĻŸāĻŋāĻ¤ā§‡ āĻ•ā§āĻ˛āĻŋāĻ• āĻ•āĻ°ā§‡ āĻ­āĻŋāĻĄāĻŋāĻ“āĻŸāĻŋ āĻĻā§‡āĻ–ā§āĻ¨āĨ¤ - -## [āĻĒā§āĻ°āĻŋ-āĻ˛ā§‡āĻ•āĻšāĻžāĻ°-āĻ•ā§āĻ‡āĻœ](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/1/) - ---- -āĻŦāĻŋāĻ—āĻŋāĻ¨āĻžāĻ°āĻĻā§‡āĻ° āĻœāĻ¨ā§āĻ¯ āĻ•ā§āĻ˛āĻžāĻ¸āĻŋāĻ•ā§āĻ¯āĻžāĻ˛ āĻŽā§‡āĻļāĻŋāĻ¨ āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚ āĻ•ā§‡āĻžāĻ°ā§āĻ¸ āĻ āĻ†āĻĒāĻ¨āĻžāĻ•ā§‡ āĻ¸ā§āĻŦāĻžāĻ—āĻ¤āĻŽ!āĻ†āĻĒāĻ¨āĻŋ āĻšā§Ÿ āĻāĻ‡ āĻŦāĻŋāĻˇā§Ÿā§‡ āĻ¸āĻŽā§āĻĒā§‚āĻ°ā§āĻŖ āĻ¨āĻ¤ā§āĻ¨ āĻ…āĻĨāĻŦāĻž āĻŽā§‡āĻļāĻŋāĻ¨ āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚ āĻ āĻ¨āĻŋāĻœā§‡āĻ° āĻ…āĻ¨ā§āĻļā§€āĻ˛āĻ¨āĻ•ā§‡ āĻ†āĻ°āĻ“ āĻ‰āĻ¨ā§āĻ¨āĻ¤ āĻ•āĻ°āĻ¤ā§‡ āĻšāĻžāĻ¨, āĻ†āĻĒāĻ¨āĻŋ āĻ†āĻŽāĻžāĻĻā§‡āĻ° āĻ¸āĻžāĻĨā§‡ āĻ¯ā§‹āĻ—āĻĻāĻžāĻ¨ āĻ•āĻ°āĻ¤ā§‡ āĻĒā§‡āĻ°ā§‡ āĻ†āĻŽāĻ°āĻž āĻ–ā§āĻļāĻŋ! āĻ†āĻŽāĻ°āĻž āĻ†āĻĒāĻ¨āĻžāĻ° ML āĻ…āĻ§ā§āĻ¯āĻ¯āĻŧāĻ¨ā§‡āĻ° āĻœāĻ¨ā§āĻ¯ āĻāĻ•āĻŸāĻŋ āĻŦāĻ¨ā§āĻ§ā§āĻ¤ā§āĻŦāĻĒā§‚āĻ°ā§āĻŖ āĻ˛āĻžā§āĻšāĻŋāĻ‚ āĻ¸ā§āĻĒāĻŸ āĻ¤ā§ˆāĻ°āĻŋ āĻ•āĻ°āĻ¤ā§‡ āĻšāĻžāĻ‡ āĻāĻŦāĻ‚ āĻ†āĻĒāĻ¨āĻžāĻ° āĻŽā§‚āĻ˛ā§āĻ¯āĻžāĻ¯āĻŧāĻ¨, āĻĒā§āĻ°āĻ¤āĻŋāĻ•ā§āĻ°āĻŋāĻ¯āĻŧāĻž,[āĻĢāĻŋāĻĄāĻŦā§āĻ¯āĻžāĻ•](https://github.com/microsoft/ML-For-Beginners/discussions). āĻœāĻžāĻ¨āĻžāĻ¤ā§‡ āĻāĻŦāĻ‚ āĻ…āĻ¨ā§āĻ¤āĻ°ā§āĻ­ā§āĻ•ā§āĻ¤ āĻ•āĻ°āĻ¤ā§‡ āĻĒā§‡āĻ°ā§‡ āĻ–ā§āĻļāĻŋ āĻšāĻŦ āĨ¤ - - -[![Introduction to ML](https://img.youtube.com/vi/h0e2HAPTGF4/0.jpg)](https://youtu.be/h0e2HAPTGF4 "Introduction to ML") - - -> đŸŽĨ āĻ­āĻŋāĻĄāĻŋāĻ“āĻŸāĻŋ āĻĻā§‡āĻ–āĻžāĻ° āĻœāĻ¨ā§āĻ¯ āĻ‰āĻĒāĻ°ā§‡āĻ° āĻ›āĻŦāĻŋāĻ¤ā§‡ āĻ•ā§āĻ˛āĻŋāĻ• āĻ•āĻ°ā§āĻ¨ -MIT āĻāĻ° āĻœāĻ¨ āĻ—āĻžāĻŸā§‡āĻ‚ āĻŽā§‡āĻļāĻŋāĻ¨ āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚ āĻāĻ° āĻĒāĻ°āĻŋāĻšāĻŋāĻ¤āĻŋ āĻ•āĻ°āĻžāĻšā§āĻ›ā§‡āĻ¨āĨ¤ - ---- -## āĻŽā§‡āĻļāĻŋāĻ¨ āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚ āĻāĻ° āĻļā§āĻ°ā§ - -āĻāĻ‡ āĻ•ā§āĻ¯āĻžāĻ°āĻŋāĻ•ā§āĻ˛āĻžāĻŽ āĻļā§āĻ°ā§āĻ° āĻ•āĻ°āĻžāĻ° āĻĒā§‚āĻ°ā§āĻŦā§‡, āĻ¨ā§‹āĻŸāĻŦā§āĻ• āĻ°āĻžāĻ¨ āĻ•āĻ°āĻžāĻ° āĻœāĻ¨ā§āĻ¯ āĻ¨ā§‹āĻŸāĻŦā§āĻ• āĻ¸ā§‡āĻŸāĻ†āĻĒ āĻĨāĻžāĻ•āĻ¤ā§‡ āĻšāĻŦā§‡āĨ¤ - - -- **āĻ†āĻĒāĻ¨āĻžāĻ° āĻŽā§‡āĻļāĻŋāĻ¨ āĻ•ā§‡ āĻ•āĻ¨āĻĢāĻŋāĻ—āĻžāĻ° āĻ•āĻ°ā§āĻ¨ āĻāĻ‡ āĻ­āĻŋāĻĄāĻŋāĻ“ āĻĻā§‡āĻ–ā§‡**. āĻļāĻŋāĻ–āĻžāĻ° āĻœāĻ¨ā§āĻ¯ āĻāĻ‡ āĻ˛āĻŋāĻ‚āĻ•āĻŸāĻŋ āĻŦā§āĻ¯āĻŦāĻšāĻžāĻ° āĻ•āĻ°ā§āĻ¨ [āĻ•āĻŋāĻ­āĻžāĻŦā§‡ āĻĒāĻžāĻ‡āĻĨāĻ¨ āĻ‡āĻ¨ā§āĻ¸āĻŸāĻ˛ āĻ•āĻ°āĻ¤ā§‡ āĻšā§Ÿ](https://youtu.be/CXZYvNRIAKM) āĻāĻŦāĻ‚ [āĻ¸ā§‡āĻŸāĻ†āĻĒ āĻ āĻ‡āĻĄāĻŋāĻŸāĻ°](https://youtu.be/EU8eayHWoZg) . -- **āĻĒāĻžāĻ‡āĻĨāĻ¨ āĻļāĻŋāĻ–ā§āĻ¨**. [āĻĒāĻžāĻ‡āĻĨāĻ¨](https://docs.microsoft.com/learn/paths/python-language/?WT.mc_id=academic-77952-leestott) āĻāĻ° āĻŦā§āĻ¯āĻžāĻ¸āĻŋāĻ• āĻ¨āĻ˛ā§‡āĻœ āĻœāĻžāĻ¨āĻž āĻĨāĻžāĻ•āĻž āĻœāĻ°ā§āĻ°ā§€āĨ¤ āĻāĻ‡ āĻ•ā§‹āĻ°ā§āĻ¸ā§‡āĻ° āĻĒā§āĻ°ā§‹āĻ—ā§āĻ°āĻžāĻŽāĻŋāĻ‚ āĻ˛ā§āĻ¯āĻžāĻ™ā§āĻ—ā§ā§Ÿā§‡āĻœ āĻĄā§‡āĻŸāĻž āĻ¸āĻžāĻ‡āĻ¨ā§āĻ¸āĻŸāĻŋāĻ¸ā§āĻŸ āĻāĻ° āĻœāĻ¨ā§āĻ¯ āĻ–ā§āĻŦāĻ‡ āĻ—ā§āĻ°ā§āĻ¤ā§āĻŦāĻĒā§‚āĻ°ā§āĻŖāĨ¤ -- **Node.js āĻāĻŦāĻ‚ JavaScript āĻļāĻŋāĻ–ā§āĻ¨**.āĻ“ā§Ÿā§‡āĻŦ āĻ…ā§āĻ¯āĻžāĻĒāĻ¸ āĻ¤ā§ˆāĻ°āĻŋāĻ° āĻœāĻ¨ā§āĻ¯ āĻāĻ‡ āĻ•ā§‡āĻžāĻ°ā§āĻ¸ā§‡ āĻ†āĻŽāĻ°āĻž āĻœāĻžāĻŦāĻžāĻ¸ā§āĻ•ā§āĻ°āĻŋāĻĒāĻŸ āĻŦā§āĻ¯āĻžāĻŦāĻšāĻžāĻ° āĻ•āĻ°āĻŦāĨ¤ āĻ¤āĻžāĻ‡, āĻ†āĻĒāĻ¨āĻžāĻ° [āĻ¨ā§‹āĻĄ](https://nodejs.org) āĻāĻŦāĻ‚ [npm](https://www.npmjs.com/) āĻ‡āĻ¨ā§āĻ¸āĻŸāĻ˛ āĻĨāĻžāĻ•āĻ¤ā§‡ āĻšāĻŦā§‡āĨ¤ āĻ…āĻ¨ā§āĻ¯āĻĻāĻŋāĻ•ā§‡, āĻĒāĻžāĻ‡āĻĨāĻ¨ āĻāĻŦāĻ‚ āĻœāĻžāĻ­āĻžāĻ¸ā§āĻ•ā§āĻ°āĻŋāĻĒāĻŸ āĻĄā§‡āĻ­ā§‡āĻ˛āĻžāĻĒāĻŽā§‡āĻ¨ā§āĻŸā§‡āĻ° āĻœāĻ¨ā§āĻ¯ [āĻ­āĻŋāĻœā§ā§ŸāĻžāĻ˛ āĻ¸ā§āĻŸā§āĻĄāĻŋāĻ“](https://code.visualstudio.com/) āĻ•ā§‹āĻĄ āĻ āĻĻā§āĻŸā§āĻ‡ āĻ†āĻ›ā§‡āĨ¤ -- **āĻāĻ•āĻŸāĻŋ āĻ—āĻŋāĻŸāĻšāĻžāĻŦ āĻ…ā§āĻ¯āĻžāĻ•āĻžāĻ‰āĻ¨ā§āĻŸ āĻ¤ā§ˆāĻ°āĻŋ āĻ•āĻ°ā§āĻ¨**. āĻ¯ā§‡āĻšā§‡āĻ¤ā§ āĻ†āĻĒāĻ¨āĻŋ āĻ†āĻŽāĻžāĻĻā§‡āĻ° āĻ•ā§‡ [āĻ—āĻŋāĻŸāĻšāĻžāĻŦ](https://github.com) āĻ āĻĒā§‡ā§Ÿā§‡āĻ›ā§‡āĻ¨, āĻ¤āĻžāĻ°āĻŽāĻžāĻ¨ā§‡ āĻ†āĻĒāĻ¨āĻžāĻ° āĻ‡āĻ¤āĻŋāĻŽāĻ§ā§āĻ¯ā§‡āĻ‡ āĻāĻ•āĻžāĻ‰āĻ¨ā§āĻŸ āĻ†āĻ›ā§‡āĨ¤ āĻ¤āĻŦā§‡ āĻ¯āĻĻāĻŋ āĻ¨āĻž āĻĨāĻžāĻ•ā§‡, āĻāĻ•āĻŸāĻŋ āĻāĻ•āĻžāĻ‰āĻ¨ā§āĻŸ āĻ¤ā§ˆāĻ°āĻŋ āĻ•āĻ°ā§āĻ¨ āĻāĻŦāĻ‚ āĻĒāĻ°ā§‡ āĻĢāĻ°ā§āĻ• āĻ•āĻ°ā§‡ āĻ†āĻĒāĻ¨āĻžāĻ° āĻŦāĻžāĻ¨āĻŋā§Ÿā§‡ āĻ¨āĻŋāĻ¨āĨ¤ (āĻ¸ā§āĻŸāĻžāĻ° āĻĻāĻŋāĻ¤ā§‡ āĻ­ā§āĻ˛ā§‡ āĻ¯āĻžāĻŦā§‡āĻ¨ āĻ¨āĻž,😊 ) -- **āĻ˜ā§āĻ°āĻŋā§Ÿā§‡ āĻ†āĻ¸ā§‡āĻ¨ Scikit-learn**. āĻ¨āĻŋāĻœā§‡āĻ•ā§‡ āĻĒāĻ°āĻŋāĻšāĻŋāĻ¤ āĻ•āĻ°ā§āĻ¨ [Scikit-learn](https://scikit-learn.org/stable/user_guide.html) āĻāĻ° āĻ¸āĻžāĻĨā§‡, āĻŽā§‡āĻļāĻŋāĻ¨ āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚ āĻ˛āĻžāĻ‡āĻŦā§āĻ°ā§‡āĻ°āĻŋ āĻ¸ā§‡āĻŸ āĻ¯āĻž āĻ†āĻŽāĻ°āĻž āĻāĻ‡ āĻ•ā§‹āĻ°ā§āĻ¸ā§‡ āĻ‰āĻ˛ā§āĻ˛ā§‡āĻ– āĻ•āĻ°ā§‡ āĻĨāĻžāĻ•āĻŦ - ---- -## āĻŽā§‡āĻļāĻŋāĻ¨ āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚ āĻ•āĻŋ? -'āĻŽā§‡āĻļāĻŋāĻ¨ āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚' āĻļāĻŦā§āĻĻāĻŸāĻŋ āĻŦāĻ°ā§āĻ¤āĻŽāĻžāĻ¨ āĻ¸āĻŽāĻ¯āĻŧā§‡āĻ° āĻ¸āĻŦāĻšā§‡āĻ¯āĻŧā§‡ āĻœāĻ¨āĻĒā§āĻ°āĻŋāĻ¯āĻŧ āĻāĻŦāĻ‚ āĻĒā§āĻ°āĻžāĻ¯āĻŧāĻ‡ āĻŦā§āĻ¯āĻŦāĻšā§ƒāĻ¤ āĻāĻ•āĻŸāĻŋ āĻļāĻŦā§āĻĻāĨ¤ āĻ†āĻĒāĻ¨āĻŋ āĻ¯ā§‡ āĻĄā§‹āĻŽā§‡āĻ‡āĻ¨ā§‡ āĻ•āĻžāĻœ āĻ•āĻ°ā§‡āĻ¨ āĻ¨āĻž āĻ•ā§‡āĻ¨ āĻĒā§āĻ°āĻ¯ā§āĻ•ā§āĻ¤āĻŋāĻ° āĻ¸āĻžāĻĨā§‡ āĻ†āĻĒāĻ¨āĻžāĻ° āĻĒāĻ°āĻŋāĻšāĻŋāĻ¤āĻŋ āĻĨāĻžāĻ•āĻ˛ā§‡ āĻ…āĻ¨ā§āĻ¤āĻ¤ āĻāĻ•āĻŦāĻžāĻ° āĻāĻ‡ āĻļāĻŦā§āĻĻāĻŸāĻŋ āĻļā§āĻ¨ā§‡āĻ›ā§‡āĻ¨ āĻāĻŽāĻ¨ āĻāĻ•āĻŸāĻŋ āĻ…āĻĒā§āĻ°āĻ¯āĻŧā§‹āĻœāĻ¨ā§€āĻ¯āĻŧ āĻ¸āĻŽā§āĻ­āĻžāĻŦāĻ¨āĻž āĻ°āĻ¯āĻŧā§‡āĻ›ā§‡āĨ¤ āĻŽā§‡āĻļāĻŋāĻ¨ āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚ āĻāĻ° āĻŽā§‡āĻ•āĻžāĻ¨āĻŋāĻ•ā§āĻ¸, āĻ¯āĻžāĻ‡āĻšā§‹āĻ•, āĻŦā§‡āĻļāĻŋāĻ°āĻ­āĻžāĻ— āĻŽāĻžāĻ¨ā§āĻˇā§‡āĻ° āĻ•āĻžāĻ›ā§‡ āĻāĻŸāĻŋ āĻāĻ•āĻŸāĻŋ āĻ°āĻšāĻ¸ā§āĻ¯āĨ¤ āĻāĻ•āĻœāĻ¨ āĻŽā§‡āĻļāĻŋāĻ¨ āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚ āĻ¨āĻ¤ā§āĻ¨āĻĻā§‡āĻ° āĻœāĻ¨ā§āĻ¯, āĻŦāĻŋāĻˇāĻ¯āĻŧāĻŸāĻŋ āĻ•āĻ–āĻ¨āĻ“ āĻ•āĻ–āĻ¨āĻ“ āĻ…āĻĒā§āĻ°āĻ¤āĻŋāĻ°ā§‹āĻ§ā§āĻ¯ āĻŽāĻ¨ā§‡ āĻšāĻ¤ā§‡ āĻĒāĻžāĻ°ā§‡āĨ¤ āĻ…āĻ¤āĻāĻŦ, āĻŽā§‡āĻļāĻŋāĻ¨ āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚ āĻ†āĻ¸āĻ˛ā§‡ āĻ•ā§€ āĻ¤āĻž āĻŦā§‹āĻāĻž āĻ—ā§āĻ°ā§āĻ¤ā§āĻŦāĻĒā§‚āĻ°ā§āĻŖ āĻāĻŦāĻ‚ āĻŦāĻžāĻ¸ā§āĻ¤āĻŦ āĻ‰āĻĻāĻžāĻšāĻ°āĻŖā§‡āĻ° āĻŽāĻžāĻ§ā§āĻ¯āĻŽā§‡ āĻ§āĻžāĻĒā§‡ āĻ§āĻžāĻĒā§‡ āĻāĻŸāĻŋ āĻ¸āĻŽā§āĻĒāĻ°ā§āĻ•ā§‡ āĻļāĻŋāĻ–āĻ¤ā§‡ āĻšāĻŦā§‡āĨ¤ - ---- -## āĻšāĻžāĻ‡āĻĢ āĻ•āĻžāĻ°ā§āĻ­ - -![ml hype curve](../images/hype.png) - -> Google Trends āĻ 'āĻŽā§‡āĻļāĻŋāĻ¨ āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚' āĻļāĻŦā§āĻĻāĻŸāĻŋāĻ° āĻ¸āĻžāĻŽā§āĻĒā§āĻ°āĻ¤āĻŋāĻ• 'āĻšāĻžāĻ‡āĻĒ āĻ•āĻžāĻ°ā§āĻ­'āĨ¤ - ---- -## āĻāĻ• āĻ°āĻšāĻ¸ā§āĻ¯āĻŽāĻ¯āĻŧ āĻŽāĻšāĻžāĻŦāĻŋāĻļā§āĻŦ - -āĻ†āĻŽāĻ°āĻž āĻ°āĻšāĻ¸ā§āĻ¯ā§‡ āĻ­āĻ°āĻĒā§āĻ° āĻāĻ•āĻŸāĻŋ āĻ†āĻ•āĻ°ā§āĻˇāĻ¨ā§€ā§Ÿ āĻŽāĻšāĻžāĻŦāĻŋāĻļā§āĻŦā§‡ āĻŦāĻžāĻ¸ āĻ•āĻ°āĻŋāĨ¤ āĻ¸ā§āĻŸāĻŋāĻĢā§‡āĻ¨ āĻšāĻ•āĻŋāĻ‚, āĻ†āĻ˛āĻŦāĻžāĻ°ā§āĻŸ āĻ†āĻ‡āĻ¨āĻ¸ā§āĻŸāĻžāĻ‡āĻ¨ āĻāĻŦāĻ‚ āĻ†āĻ°āĻ“ āĻ…āĻ¨ā§‡āĻ•ā§‡āĻ° āĻŽāĻ¤ā§‹ āĻŽāĻšāĻžāĻ¨ āĻŦāĻŋāĻœā§āĻžāĻžāĻ¨ā§€āĻ°āĻž āĻ†āĻŽāĻžāĻĻā§‡āĻ° āĻšāĻžāĻ°āĻĒāĻžāĻļā§‡āĻ° āĻŦāĻŋāĻļā§āĻŦā§‡āĻ° āĻ°āĻšāĻ¸ā§āĻ¯ āĻ‰āĻ¨ā§āĻŽā§‹āĻšāĻ¨ āĻ•āĻ°ā§‡ āĻāĻŽāĻ¨ āĻ…āĻ°ā§āĻĨāĻĒā§‚āĻ°ā§āĻŖ āĻ¤āĻĨā§āĻ¯ āĻ…āĻ¨ā§āĻ¸āĻ¨ā§āĻ§āĻžāĻ¨ā§‡ āĻ¤āĻžāĻĻā§‡āĻ° āĻœā§€āĻŦāĻ¨ āĻ‰ā§ŽāĻ¸āĻ°ā§āĻ— āĻ•āĻ°ā§‡āĻ›ā§‡āĻ¨āĨ¤āĻāĻŸāĻŋ āĻŽāĻžāĻ¨ā§āĻˇā§‡āĻ° āĻļā§‡āĻ–āĻžāĻ° āĻāĻ•āĻŸāĻŋ āĻ…āĻŦāĻ¸ā§āĻĨāĻž: āĻāĻ•āĻŸāĻŋ āĻŽāĻžāĻ¨āĻŦ āĻļāĻŋāĻļā§ āĻ¨āĻ¤ā§āĻ¨ āĻœāĻŋāĻ¨āĻŋāĻ¸ āĻļāĻŋāĻ–ā§‡ āĻāĻŦāĻ‚ āĻŦāĻ›āĻ°ā§‡āĻ° āĻĒāĻ° āĻŦāĻ›āĻ° āĻ¤āĻžāĻĻā§‡āĻ° āĻŦāĻŋāĻļā§āĻŦā§‡āĻ° āĻ—āĻ āĻ¨ āĻ‰āĻ¨ā§āĻŽā§‹āĻšāĻ¨ āĻ•āĻ°ā§‡ āĻ¯āĻ–āĻ¨ āĻ¤āĻžāĻ°āĻž āĻĒā§āĻ°āĻžāĻĒā§āĻ¤āĻŦāĻ¯āĻŧāĻ¸ā§āĻ• āĻšāĻ¯āĻŧā§‡ āĻ“āĻ ā§‡āĨ¤ - ---- - -## āĻļāĻŋāĻļā§āĻĻā§‡āĻ° āĻŽāĻ¸ā§āĻ¤āĻŋāĻˇā§āĻ• -āĻāĻ•āĻŸāĻŋ āĻļāĻŋāĻļā§āĻ° āĻŽāĻ¸ā§āĻ¤āĻŋāĻˇā§āĻ• āĻāĻŦāĻ‚ āĻ‡āĻ¨ā§āĻĻā§āĻ°āĻŋāĻ¯āĻŧāĻ—ā§āĻ˛āĻŋ āĻ¤āĻžāĻĻā§‡āĻ° āĻ†āĻļā§‡āĻĒāĻžāĻļā§‡āĻ° āĻ˜āĻŸāĻ¨āĻžāĻ—ā§āĻ˛āĻŋ āĻ‰āĻĒāĻ˛āĻŦā§āĻ§āĻŋ āĻ•āĻ°ā§‡ āĻāĻŦāĻ‚ āĻ§ā§€āĻ°ā§‡ āĻ§ā§€āĻ°ā§‡ āĻœā§€āĻŦāĻ¨ā§‡āĻ° āĻ˛ā§āĻ•āĻžāĻ¨ā§‹ āĻ¨āĻŋāĻĻāĻ°ā§āĻļāĻ¨āĻ—ā§āĻ˛āĻŋ āĻļāĻŋāĻ–ā§‡ āĻ¯āĻž āĻļāĻŋāĻļā§āĻ•ā§‡ āĻļā§‡āĻ–āĻž āĻ¨āĻŋāĻĻāĻ°ā§āĻļāĻ¨āĻ—ā§āĻ˛āĻŋ āĻ¸āĻ¨āĻžāĻ•ā§āĻ¤ āĻ•āĻ°āĻžāĻ° āĻœāĻ¨ā§āĻ¯ āĻ¯ā§ŒāĻ•ā§āĻ¤āĻŋāĻ• āĻ¨āĻŋāĻ¯āĻŧāĻŽ āĻ¤ā§ˆāĻ°āĻŋ āĻ•āĻ°āĻ¤ā§‡ āĻ¸āĻšāĻžāĻ¯āĻŧāĻ¤āĻž āĻ•āĻ°ā§‡āĨ¤ āĻāĻ‡ āĻĒā§āĻ°āĻĨāĻŋāĻŦā§€āĻ¤ā§‡ āĻŽāĻžāĻ¨ā§āĻˇā§‡āĻ° āĻŽāĻ¸ā§āĻ¤āĻŋāĻˇā§āĻ•ā§‡āĻ° āĻļā§‡āĻ–āĻžāĻ° āĻĒā§āĻ°āĻ•ā§āĻ°āĻŋā§ŸāĻž āĻ…āĻ¨ā§āĻ¯āĻžāĻ¨ā§āĻ¯ āĻĒā§āĻ°āĻžāĻŖāĻŋ āĻĨā§‡āĻ•ā§‡ āĻ–ā§āĻŦāĻ‡ āĻ…āĻ¤ā§āĻ¯āĻžāĻ§ā§āĻ¨āĻŋāĻ•āĨ¤ āĻ•ā§āĻ°āĻŽāĻžāĻ—āĻ¤ āĻļā§‡āĻ–āĻž āĻāĻŦāĻ‚ āĻ˛ā§āĻ•āĻžāĻ¨ā§‹ āĻĒā§āĻ¯āĻžāĻŸāĻžāĻ°ā§āĻ¨āĻ—ā§āĻ˛āĻŋ āĻ†āĻŦāĻŋāĻˇā§āĻ•āĻžāĻ° āĻ•āĻ°ā§‡ āĻāĻŦāĻ‚ āĻ¤āĻžāĻ°āĻĒāĻ° āĻ¸ā§‡āĻ‡ āĻĒā§āĻ¯āĻžāĻŸāĻžāĻ°ā§āĻ¨āĻ—ā§āĻ˛āĻŋāĻ¤ā§‡ āĻ‰āĻĻā§āĻ­āĻžāĻŦāĻ¨ āĻ•āĻ°ā§‡ āĻ†āĻŽāĻžāĻĻā§‡āĻ° āĻ¸āĻžāĻ°āĻž āĻœā§€āĻŦāĻ¨ āĻœā§ā§œā§‡ āĻ¨āĻŋāĻœā§‡āĻĻā§‡āĻ° āĻ†āĻ°āĻ“ āĻ­āĻžāĻ˛ā§‹ āĻāĻŦāĻ‚ āĻ‰āĻ¨ā§āĻ¨āĻ¤ āĻ•āĻ°āĻ¤ā§‡ āĻ¸āĻ•ā§āĻˇāĻŽ āĻ•āĻ°ā§‡āĨ¤ āĻāĻ‡ āĻļā§‡āĻ–āĻžāĻ° āĻ•ā§āĻˇāĻŽāĻ¤āĻž āĻ“ āĻŦāĻŋāĻ•āĻļāĻŋāĻ¤ āĻšāĻ“ā§ŸāĻžāĻ° āĻ¸āĻ•ā§āĻˇāĻŽāĻ¤āĻž āĻ•ā§‡ āĻŦāĻ˛ā§‡ [āĻŦā§āĻ°ā§‡āĻ‡āĻ¨ āĻĒā§āĻ˛āĻžāĻ¸ā§āĻŸāĻŋāĻ¸āĻŋāĻŸāĻŋ](https://www.simplypsychology.org/brain-plasticity.html)āĨ¤ āĻŦāĻžāĻšā§āĻ¯āĻŋāĻ•āĻ­āĻžāĻŦā§‡, āĻ†āĻŽāĻ°āĻž āĻŽāĻžāĻ¨āĻŦ āĻŽāĻ¸ā§āĻ¤āĻŋāĻˇā§āĻ•ā§‡āĻ° āĻļā§‡āĻ–āĻžāĻ° āĻĒā§āĻ°āĻ•ā§āĻ°āĻŋāĻ¯āĻŧāĻž āĻāĻŦāĻ‚ āĻŽā§‡āĻļāĻŋāĻ¨ āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚ āĻ§āĻžāĻ°āĻŖāĻžāĻ° āĻŽāĻ§ā§āĻ¯ā§‡ āĻ•āĻŋāĻ›ā§ āĻ…āĻ¨ā§āĻĒā§āĻ°ā§‡āĻ°āĻŖāĻžāĻŽā§‚āĻ˛āĻ• āĻŽāĻŋāĻ˛ āĻ†āĻāĻ•āĻ¤ā§‡ āĻĒāĻžāĻ°āĻŋāĨ¤ - ---- -## āĻŽāĻžāĻ¨ā§āĻˇā§‡āĻ° āĻŽāĻ¸ā§āĻ¤āĻŋāĻˇā§āĻ• - -[āĻŽāĻžāĻ¨ā§āĻˇā§‡āĻ° āĻŽāĻ¸ā§āĻ¤āĻŋāĻˇā§āĻ•]((https://www.livescience.com/29365-human-brain.html)) āĻŦāĻžāĻ¸ā§āĻ¤āĻŦ āĻœāĻ—āĻ¤ āĻĨā§‡āĻ•ā§‡ āĻœāĻŋāĻ¨āĻŋāĻ¸āĻ—ā§āĻ˛āĻŋ āĻ‰āĻĒāĻ˛āĻŦā§āĻ§āĻŋ āĻ•āĻ°ā§‡, āĻ…āĻ¨ā§āĻ­ā§‚āĻ¤ āĻ¤āĻĨā§āĻ¯ āĻĒā§āĻ°āĻ•ā§āĻ°āĻŋāĻ¯āĻŧāĻž āĻ•āĻ°ā§‡, āĻ¯ā§ŒāĻ•ā§āĻ¤āĻŋāĻ• āĻ¸āĻŋāĻĻā§āĻ§āĻžāĻ¨ā§āĻ¤ āĻ¨ā§‡āĻ¯āĻŧ āĻāĻŦāĻ‚ āĻĒāĻ°āĻŋāĻ¸ā§āĻĨāĻŋāĻ¤āĻŋāĻ° āĻ‰āĻĒāĻ° āĻ­āĻŋāĻ¤ā§āĻ¤āĻŋ āĻ•āĻ°ā§‡ āĻ•āĻŋāĻ›ā§ āĻ•ā§āĻ°āĻŋāĻ¯āĻŧāĻž āĻ¸āĻŽā§āĻĒāĻžāĻĻāĻ¨ āĻ•āĻ°ā§‡āĨ¤ āĻāĻŸāĻžāĻ•ā§‡āĻ‡ āĻ†āĻŽāĻ°āĻž āĻŦāĻ˛āĻŋ āĻŦā§āĻĻā§āĻ§āĻŋāĻŽāĻ¤ā§āĻ¤āĻžāĻ° āĻ¸āĻžāĻĨā§‡ āĻ†āĻšāĻ°āĻŖ āĻ•āĻ°āĻžāĨ¤ āĻ¯āĻ–āĻ¨ āĻ†āĻŽāĻ°āĻž āĻāĻ•āĻŸāĻŋ āĻŽā§‡āĻļāĻŋāĻ¨ā§‡ āĻŦā§āĻĻā§āĻ§āĻŋāĻŽāĻžāĻ¨ āĻ†āĻšāĻ°āĻŖāĻ—āĻ¤ āĻĒā§āĻ°āĻ•ā§āĻ°āĻŋāĻ¯āĻŧāĻžāĻ° āĻāĻ•āĻŸāĻŋ āĻĒā§āĻ°āĻ¤āĻŋāĻ•ā§ƒāĻ¤āĻŋ āĻĒā§āĻ°ā§‹āĻ—ā§āĻ°āĻžāĻŽ āĻ•āĻ°āĻŋ, āĻ¤āĻ–āĻ¨ āĻāĻŸāĻŋāĻ•ā§‡ āĻ•ā§ƒāĻ¤ā§āĻ°āĻŋāĻŽ āĻŦā§āĻĻā§āĻ§āĻŋāĻŽāĻ¤ā§āĻ¤āĻž (AI) āĻŦāĻ˛āĻž āĻšāĻ¯āĻŧāĨ¤ - ---- -## āĻ•āĻŋāĻ›ā§ āĻĒāĻ°āĻŋāĻ­āĻžāĻˇāĻž - -āĻ¯āĻĻāĻŋāĻ“ āĻāĻŸāĻž āĻŦāĻŋāĻ­ā§āĻ°āĻžāĻ¨ā§āĻ¤āĻ•āĻ° āĻšāĻ¤ā§‡ āĻĒāĻžāĻ°ā§‡, āĻŽā§‡āĻļāĻŋāĻ¨ āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚ (āĻāĻŽ. āĻāĻ˛) āĻ†āĻ°ā§āĻŸāĻŋāĻĢāĻŋāĻļāĻŋā§ŸāĻžāĻ˛ āĻ‡āĻ¨ā§āĻŸāĻŋāĻ˛āĻŋāĻœā§‡āĻ¨ā§āĻ¸ āĻāĻ° āĻāĻ•āĻŸāĻŋ āĻ…āĻ‚āĻļāĨ¤ **ML āĻ…āĻ°ā§āĻĨāĻĒā§‚āĻ°ā§āĻŖ āĻ¤āĻĨā§āĻ¯ āĻ‰āĻ¨ā§āĻŽā§‹āĻšāĻ¨ āĻ•āĻ°āĻžāĻ° āĻœāĻ¨ā§āĻ¯ āĻŦāĻŋāĻļā§‡āĻˇ āĻ…ā§āĻ¯āĻžāĻ˛āĻ—āĻ°āĻŋāĻĻāĻŽ āĻŦā§āĻ¯āĻŦāĻšāĻžāĻ° āĻ•āĻ°ā§‡ āĻāĻŦāĻ‚ āĻ¯ā§āĻ•ā§āĻ¤āĻŋāĻ¸āĻ™ā§āĻ—āĻ¤ āĻ¸āĻŋāĻĻā§āĻ§āĻžāĻ¨ā§āĻ¤ āĻ—ā§āĻ°āĻšāĻŖā§‡āĻ° āĻĒā§āĻ°āĻ•ā§āĻ°āĻŋāĻ¯āĻŧāĻžāĻŸāĻŋāĻ•ā§‡ āĻ¸āĻŽāĻ°ā§āĻĨāĻ¨ āĻ•āĻ°āĻžāĻ° āĻœāĻ¨ā§āĻ¯ āĻ…āĻ¨ā§āĻ­ā§‚āĻ¤ āĻĄā§‡āĻŸāĻž āĻĨā§‡āĻ•ā§‡ āĻ˛ā§āĻ•āĻžāĻ¨ā§‹ āĻ¨āĻŋāĻĻāĻ°ā§āĻļāĻ¨āĻ—ā§āĻ˛āĻŋ āĻ–ā§āĻāĻœā§‡ āĻŦā§‡āĻ° āĻ•āĻ°āĻžāĻ° āĻ¸āĻžāĻĨā§‡ āĻ¸āĻŽā§āĻĒāĻ°ā§āĻ•āĻŋāĻ¤āĨ¤** - ---- -## āĻ āĻ†āĻ‡, āĻāĻŽ āĻāĻ˛, āĻŽā§‡āĻļāĻŋāĻ¨ āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚ - -![āĻ āĻ†āĻ‡, āĻāĻŽ āĻāĻ˛, āĻŽā§‡āĻļāĻŋāĻ¨ āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚, āĻĄā§‡āĻŸāĻž āĻ¸āĻžāĻ‡āĻ¨ā§āĻ¸](../images/ai-ml-ds.png) - -> āĻĄāĻžā§ŸāĻžāĻ—ā§āĻ°āĻžāĻŽāĻŸāĻŋ āĻāĻ†āĻ‡,āĻāĻŽāĻāĻ˛, āĻĄāĻŋāĻĒ āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚ āĻāĻŦāĻ‚ āĻĄā§‡āĻŸāĻž āĻ¸āĻžāĻ‡āĻ¨ā§āĻ¸ āĻāĻ° āĻŽāĻ§ā§āĻ¯ā§‡ āĻ¸āĻŽā§āĻĒāĻ°ā§āĻ• āĻŦā§āĻāĻžāĻšā§āĻ›ā§‡āĨ¤ āĻ‡āĻ¨āĻĢā§‹āĻ—ā§āĻ°āĻžāĻĢāĻŋāĻ• āĻ•āĻ°ā§‡āĻ›ā§‡āĻ¨ [āĻœā§‡āĻ¨ āĻ˛ā§āĻĒāĻžāĻ°](https://twitter.com/jenlooper) āĻāĻŦāĻ‚ [āĻāĻ‡ āĻ—ā§āĻ°āĻžāĻĢāĻŋāĻ•](https://softwareengineering.stackexchange.com/questions/366996/distinction-between-ai-ml-neural-networks-deep-learning-and-data-mining) āĻĨā§‡āĻ•ā§‡ āĻ…āĻ¨ā§āĻĒā§āĻ°āĻžāĻŖāĻŋāĻ¤ āĻšā§Ÿā§‡āĻ›ā§‡āĻ¨āĨ¤ - ---- -## āĻ•āĻ­āĻžāĻ°-āĻ§āĻžāĻ°āĻŖāĻž - -āĻāĻ‡ āĻ•āĻžāĻ°āĻŋāĻ•ā§āĻ˛āĻžāĻŽā§‡,āĻ†āĻŽāĻ°āĻž āĻļā§āĻ§ā§ āĻŽā§‡āĻļāĻŋāĻ¨ āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚ āĻāĻ° āĻŽā§āĻ˛ āĻ§āĻžāĻ°āĻ¨āĻž āĻ—ā§āĻ˛ā§‹ āĻ†āĻ˛ā§‹āĻšāĻ¨āĻž āĻ•āĻ°āĻŦ āĻ¯āĻž āĻāĻ•āĻœāĻ¨ āĻ¨āĻ¤ā§āĻ¨ āĻļāĻŋāĻ•ā§āĻˇāĻžāĻ°ā§āĻĨā§€āĻ° āĻœāĻžāĻ¨āĻž āĻĒā§āĻ°ā§Ÿā§‹āĻœāĻ¨āĨ¤ āĻ†āĻŽāĻ°āĻž āĻ¯āĻžāĻ•ā§‡ 'āĻ•ā§āĻ˛āĻžāĻ¸āĻŋāĻ•ā§āĻ¯āĻžāĻ˛ āĻŽā§‡āĻļāĻŋāĻ¨ āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚' āĻŦāĻ˛āĻŋ āĻ¤āĻž āĻ†āĻŽāĻ°āĻž āĻĒā§āĻ°āĻžāĻĨāĻŽāĻŋāĻ•āĻ­āĻžāĻŦā§‡ Scikit-learn āĻŦā§āĻ¯āĻŦāĻšāĻžāĻ° āĻ•āĻ°ā§‡ āĻ•āĻ­āĻžāĻ° āĻ•āĻ°āĻŋ, āĻāĻ•āĻŸāĻŋ āĻšāĻŽā§ŽāĻ•āĻžāĻ° āĻ˛āĻžāĻ‡āĻŦā§āĻ°ā§‡āĻ°āĻŋ āĻ¯āĻž āĻ…āĻ¨ā§‡āĻ• āĻļāĻŋāĻ•ā§āĻˇāĻžāĻ°ā§āĻĨā§€ āĻŽā§ŒāĻ˛āĻŋāĻ• āĻŦāĻŋāĻˇāĻ¯āĻŧāĻ—ā§āĻ˛āĻŋ āĻļāĻŋāĻ–āĻ¤ā§‡ āĻŦā§āĻ¯āĻŦāĻšāĻžāĻ° āĻ•āĻ°ā§‡āĨ¤ āĻ•ā§ƒāĻ¤ā§āĻ°āĻŋāĻŽ āĻŦā§āĻĻā§āĻ§āĻŋāĻŽāĻ¤ā§āĻ¤āĻž āĻŦāĻž āĻ—āĻ­ā§€āĻ° āĻļāĻŋāĻ•ā§āĻˇāĻžāĻ° āĻŦāĻŋāĻ¸ā§āĻ¤ā§ƒāĻ¤ āĻ§āĻžāĻ°āĻŖāĻž āĻŦā§‹āĻāĻžāĻ° āĻœāĻ¨ā§āĻ¯, āĻŽā§‡āĻļāĻŋāĻ¨ āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚āĻ¯āĻŧā§‡āĻ° āĻāĻ•āĻŸāĻŋ āĻļāĻ•ā§āĻ¤āĻŋāĻļāĻžāĻ˛ā§€ āĻŽā§ŒāĻ˛āĻŋāĻ• āĻœā§āĻžāĻžāĻ¨ āĻ…āĻĒāĻ°āĻŋāĻšāĻžāĻ°ā§āĻ¯, āĻāĻŦāĻ‚ āĻ¤āĻžāĻ‡ āĻ†āĻŽāĻ°āĻž āĻāĻŸāĻŋ āĻāĻ–āĻžāĻ¨ā§‡ āĻ…āĻĢāĻžāĻ° āĻ•āĻ°āĻ¤ā§‡ āĻšāĻžāĻ‡āĨ¤ - ---- -## āĻāĻ‡ āĻ•ā§‹āĻ°ā§āĻ¸ āĻĨā§‡āĻ•ā§‡ āĻ†āĻĒāĻ¨āĻŋ āĻļāĻŋāĻ–āĻŦā§‡āĻ¨: - -- āĻŽā§‡āĻļāĻŋāĻ¨ āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚ āĻāĻ° āĻŽā§āĻ˛ āĻ§āĻžāĻ°āĻŖāĻž -- āĻŽā§‡āĻļāĻŋāĻ¨ āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚ āĻāĻ° āĻ‡āĻ¤āĻŋāĻšāĻžāĻ¸ -- āĻŽā§‡āĻļāĻŋāĻ¨ āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚ āĻāĻŦāĻ‚ āĻ­ā§Ÿ -- āĻ°āĻŋāĻ—ā§āĻ°ā§‡āĻļāĻ¨ āĻāĻŽ āĻāĻ˛ (āĻŽā§‡āĻļāĻŋāĻ¨ āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚) āĻŸā§‡āĻ•āĻ¨āĻŋāĻ•āĻ¸ -- āĻ•ā§āĻ˛āĻžāĻ¸āĻŋāĻĢāĻŋāĻ•ā§‡āĻļāĻ¨ āĻāĻŽ āĻāĻ˛ (āĻŽā§‡āĻļāĻŋāĻ¨ āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚) āĻŸā§‡āĻ•āĻ¨āĻŋāĻ•āĻ¸ -- āĻ•ā§āĻ˛āĻžāĻ¸ā§āĻŸāĻžāĻ°āĻŋāĻ‚ āĻāĻŽ āĻāĻ˛ (āĻŽā§‡āĻļāĻŋāĻ¨ āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚) āĻŸā§‡āĻ•āĻ¨āĻŋāĻ•āĻ¸ -- āĻ¨ā§āĻ¯āĻžāĻšā§‡āĻ°āĻžāĻ˛ āĻ˛ā§‡āĻ™ā§āĻ—ā§ā§Ÿā§‡āĻœ āĻĒā§āĻ°āĻ¸ā§‡āĻ¸āĻŋāĻ‚ āĻāĻŽ āĻāĻ˛ (āĻŽā§‡āĻļāĻŋāĻ¨ āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚) āĻŸā§‡āĻ•āĻ¨āĻŋāĻ•āĻ¸ -- āĻŸāĻžāĻ‡āĻŽ āĻ¸āĻŋāĻ°āĻŋāĻœ āĻĢāĻ°āĻ•āĻžāĻ¸ā§āĻŸāĻŋāĻ‚ āĻāĻŽ āĻāĻ˛ (āĻŽā§‡āĻļāĻŋāĻ¨ āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚) āĻŸā§‡āĻ•āĻ¨āĻŋāĻ•āĻ¸ -- āĻ°āĻŋāĻāĻ¨āĻĢā§‹āĻ°ā§āĻ¸āĻŽā§‡āĻ¨ā§āĻŸ āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚ -- āĻŽā§‡āĻļāĻŋāĻ¨ āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚ āĻāĻ° āĻœāĻ¨ā§āĻ¯ āĻŦāĻžāĻ¸ā§āĻ¤āĻŦ āĻœāĻ—āĻ¤ā§‡āĻ° āĻ…ā§āĻ¯āĻžāĻĒāĻ˛āĻŋāĻ•ā§‡āĻļāĻ¨āĨ¤ - ---- -## āĻ•āĻŋ āĻļāĻŋāĻ–āĻžāĻ¨ā§‹ āĻšāĻŦā§‡ āĻ¨āĻž: - -- āĻĄāĻŋāĻĒ āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚ -- āĻ¨āĻŋāĻ‰āĻ°āĻžāĻ˛ āĻ¨ā§‡āĻŸāĻ“ā§ŸāĻžāĻ°ā§āĻ•āĻ¸ -- āĻ āĻ†āĻ‡ (āĻ†āĻ°ā§āĻŸāĻŋāĻĢāĻŋāĻļāĻŋā§ŸāĻžāĻ˛ āĻ‡āĻ¨ā§āĻŸāĻŋāĻ˛āĻŋāĻœā§‡āĻ¨ā§āĻ¸) - - -āĻ†āĻ°āĻ“ āĻ­āĻžāĻ˛ā§‹ āĻļāĻŋāĻ–āĻžāĻ° āĻ…āĻ­āĻŋāĻœā§āĻžāĻ¤āĻž āĻ¤ā§ˆāĻ°āĻŋ āĻ•āĻ°āĻžāĻ° āĻœāĻ¨ā§āĻ¯, āĻ†āĻŽāĻ°āĻž āĻ¨āĻŋāĻ‰āĻ°āĻžāĻ˛ āĻ¨ā§‡āĻŸāĻ“āĻ¯āĻŧāĻžāĻ°ā§āĻ• āĻāĻŦāĻ‚ 'āĻĄāĻŋāĻĒ āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚'āĻāĻ° āĻœāĻŸāĻŋāĻ˛āĻ¤āĻžāĻ—ā§āĻ˛āĻŋ āĻāĻĄāĻŧāĻžāĻŦ - āĻ¨āĻŋāĻ‰āĻ°āĻžāĻ˛ āĻ¨ā§‡āĻŸāĻ“āĻ¯āĻŧāĻžāĻ°ā§āĻ• āĻŦā§āĻ¯āĻŦāĻšāĻžāĻ° āĻ•āĻ°ā§‡ āĻŦāĻšā§-āĻ¸ā§āĻ¤āĻ° āĻŦāĻŋāĻļāĻŋāĻˇā§āĻŸ āĻŽāĻĄā§‡āĻ˛-āĻŦāĻŋāĻ˛ā§āĻĄāĻŋāĻ‚ - āĻāĻŦāĻ‚ āĻāĻ†āĻ‡, āĻ¯āĻž āĻ†āĻŽāĻ°āĻž āĻāĻ•āĻŸāĻŋ āĻ­āĻŋāĻ¨ā§āĻ¨ āĻĒāĻžāĻ ā§āĻ¯āĻ•ā§āĻ°āĻŽā§‡ āĻ†āĻ˛ā§‹āĻšāĻ¨āĻž āĻ•āĻ°āĻŦāĨ¤ āĻ†āĻŽāĻ°āĻž āĻāĻ‡ āĻŦā§ƒāĻšāĻ¤ā§āĻ¤āĻ° āĻĒā§āĻ˛āĻžāĻŸāĻĢāĻ°ā§āĻŽāĻŸāĻŋāĻ° āĻĻāĻŋāĻ•ā§‡āĻ° āĻ‰āĻĒāĻ° āĻĢā§‹āĻ•āĻžāĻ¸ āĻ•āĻ°āĻžāĻ° āĻœāĻ¨ā§āĻ¯ āĻāĻ•āĻŸāĻŋ āĻ†āĻ¸āĻ¨ā§āĻ¨ āĻĄā§‡āĻŸāĻž āĻ¸āĻžāĻ¯āĻŧā§‡āĻ¨ā§āĻ¸ āĻĒāĻžāĻ ā§āĻ¯āĻ•ā§āĻ°āĻŽāĻ“ āĻ…āĻĢāĻžāĻ° āĻ•āĻ°āĻŦāĨ¤ - ---- -## āĻ•ā§‡āĻ¨ āĻŽā§‡āĻļāĻŋāĻ¨ āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚? - -āĻŽā§‡āĻļāĻŋāĻ¨ āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚, āĻāĻ•āĻŸāĻŋ āĻ¸āĻŋāĻ¸ā§āĻŸā§‡āĻŽā§‡āĻ° āĻĻā§ƒāĻˇā§āĻŸāĻŋāĻ•ā§‹āĻŖ āĻĨā§‡āĻ•ā§‡, āĻ¸ā§āĻŦāĻ¯āĻŧāĻ‚āĻ•ā§āĻ°āĻŋāĻ¯āĻŧ āĻ¸āĻŋāĻ¸ā§āĻŸā§‡āĻŽā§‡āĻ° āĻ¸ā§ƒāĻˇā§āĻŸāĻŋ āĻšāĻŋāĻ¸āĻžāĻŦā§‡ āĻ¸āĻ‚āĻœā§āĻžāĻžāĻ¯āĻŧāĻŋāĻ¤ āĻ•āĻ°āĻž āĻšāĻ¯āĻŧ āĻ¯āĻž āĻŦā§āĻĻā§āĻ§āĻŋāĻŽāĻžāĻ¨ āĻ¸āĻŋāĻĻā§āĻ§āĻžāĻ¨ā§āĻ¤ āĻ¨āĻŋāĻ¤ā§‡ āĻ¸āĻšāĻžāĻ¯āĻŧāĻ¤āĻž āĻ•āĻ°āĻžāĻ° āĻœāĻ¨ā§āĻ¯ āĻĄā§‡āĻŸāĻž āĻĨā§‡āĻ•ā§‡ āĻ˛ā§āĻ•āĻžāĻ¨ā§‹ āĻĒā§āĻ¯āĻžāĻŸāĻžāĻ°ā§āĻ¨āĻ—ā§āĻ˛āĻŋ āĻļāĻŋāĻ–āĻ¤ā§‡ āĻĒāĻžāĻ°ā§‡āĨ¤ - -āĻāĻ‡ āĻ…āĻ¨ā§āĻĒā§āĻ°ā§‡āĻ°āĻŖāĻžāĻŸāĻŋ āĻĸāĻŋāĻ˛ā§‡āĻĸāĻžāĻ˛āĻžāĻ­āĻžāĻŦā§‡ āĻ…āĻ¨ā§āĻĒā§āĻ°āĻžāĻŖāĻŋāĻ¤ āĻšāĻ¯āĻŧ āĻ•āĻŋāĻ­āĻžāĻŦā§‡ āĻŽāĻžāĻ¨ā§āĻˇā§‡āĻ° āĻŽāĻ¸ā§āĻ¤āĻŋāĻˇā§āĻ• āĻŦāĻžāĻ‡āĻ°ā§‡āĻ° āĻœāĻ—āĻ¤ āĻĨā§‡āĻ•ā§‡ āĻĒā§āĻ°āĻžāĻĒā§āĻ¤ āĻ¤āĻĨā§āĻ¯ā§‡āĻ° āĻ­āĻŋāĻ¤ā§āĻ¤āĻŋāĻ¤ā§‡ āĻ•āĻŋāĻ›ā§ āĻœāĻŋāĻ¨āĻŋāĻ¸ āĻļāĻŋāĻ–ā§‡āĨ¤ - -✅ āĻāĻ• āĻŽāĻŋāĻ¨āĻŋāĻŸā§‡āĻ° āĻœāĻ¨ā§āĻ¯ āĻšāĻŋāĻ¨ā§āĻ¤āĻž āĻ•āĻ°ā§āĻ¨ āĻ•ā§‡āĻ¨ āĻāĻ•āĻŸāĻŋ āĻŦā§āĻ¯āĻŦāĻ¸āĻž ’āĻŽā§‡āĻļāĻŋāĻ¨ āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚’ āĻ•ā§ŒāĻļāĻ˛ āĻŦā§āĻ¯āĻŦāĻšāĻžāĻ° āĻ•āĻ°āĻ¤ā§‡ āĻšāĻžāĻ¯āĻŧ āĻ¯ā§‡āĻ–āĻžāĻ¨ā§‡ āĻāĻ•āĻŸāĻŋ āĻšāĻžāĻ°ā§āĻĄ-āĻ•ā§‹āĻĄā§‡āĻĄ āĻ¨āĻŋāĻ¯āĻŧāĻŽ-āĻ­āĻŋāĻ¤ā§āĻ¤āĻŋāĻ• āĻ‡āĻžā§āĻœāĻŋāĻ¨ āĻ¤ā§ˆāĻ°āĻŋ āĻ•āĻ°āĻž āĻ¯āĻžā§Ÿ āĨ¤ - ---- -## āĻŽā§‡āĻļāĻŋāĻ¨ āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚ āĻāĻ° āĻ…ā§āĻ¯āĻžāĻĒā§āĻ˛āĻŋāĻ•ā§‡āĻļāĻ¨ - -āĻŽā§‡āĻļāĻŋāĻ¨ āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚ āĻāĻ° āĻ…ā§āĻ¯āĻžāĻĒā§āĻ˛āĻŋāĻ•ā§‡āĻļāĻ¨ āĻāĻ–āĻ¨ āĻĒā§āĻ°āĻžā§Ÿ āĻ¸āĻŦāĻ–āĻžāĻ¨ā§‡, āĻāĻŦāĻ‚ āĻ†āĻŽāĻžāĻĻā§‡āĻ° āĻ¸āĻŽāĻžāĻœā§‡āĻ° āĻšāĻžāĻ°āĻĒāĻžāĻļā§‡ āĻĒā§āĻ°āĻšāĻ˛āĻŋāĻ¤ āĻĄā§‡āĻŸāĻžāĻ° āĻŽāĻ¤āĻ‡ āĻ¸āĻ°ā§āĻŦāĻŦā§āĻ¯āĻžāĻĒā§€, āĻ†āĻŽāĻžāĻĻā§‡āĻ° āĻ¸ā§āĻŽāĻžāĻ°ā§āĻŸ āĻĢā§‹āĻ¨, āĻ¸āĻ‚āĻ¯ā§āĻ•ā§āĻ¤ āĻĄāĻŋāĻ­āĻžāĻ‡āĻ¸ āĻāĻŦāĻ‚ āĻ…āĻ¨ā§āĻ¯āĻžāĻ¨ā§āĻ¯ āĻ¸āĻŋāĻ¸ā§āĻŸā§‡āĻŽ āĻĻā§āĻŦāĻžāĻ°āĻž āĻ‰āĻ¤ā§āĻĒāĻ¨ā§āĻ¨āĨ¤ āĻ…āĻ¤ā§āĻ¯āĻžāĻ§ā§āĻ¨āĻŋāĻ• āĻŽā§‡āĻļāĻŋāĻ¨ āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚ āĻ…ā§āĻ¯āĻžāĻ˛āĻ—āĻ°āĻŋāĻĻāĻŽā§‡āĻ° āĻ…āĻĒāĻžāĻ° āĻ¸āĻŽā§āĻ­āĻžāĻŦāĻ¨āĻžāĻ° āĻ•āĻĨāĻž āĻŦāĻŋāĻŦā§‡āĻšāĻ¨āĻž āĻ•āĻ°ā§‡, āĻ—āĻŦā§‡āĻˇāĻ•āĻ°āĻž āĻŦāĻšā§āĻŽāĻžāĻ¤ā§āĻ°āĻŋāĻ• āĻāĻŦāĻ‚ āĻŦāĻšā§-āĻŦāĻŋāĻˇāĻ¯āĻŧāĻ• āĻŦāĻžāĻ¸ā§āĻ¤āĻŦ-āĻœā§€āĻŦāĻ¨ā§‡āĻ° āĻ¸āĻŽāĻ¸ā§āĻ¯āĻžāĻ° āĻ¸āĻŽāĻžāĻ§āĻžāĻ¨ āĻ•āĻ°āĻžāĻ° āĻœāĻ¨ā§āĻ¯ āĻ¤āĻžāĻĻā§‡āĻ° āĻ¸āĻ•ā§āĻˇāĻŽāĻ¤āĻž āĻ…āĻ¨ā§āĻŦā§‡āĻˇāĻŖ āĻ•āĻ°ā§‡ āĻšāĻ˛ā§‡āĻ›ā§‡āĻ¨ āĻ¯āĻžāĻ° āĻŽāĻžāĻ§ā§āĻ¯āĻŽā§‡ āĻŦā§œ āĻ‡āĻ¤āĻŋāĻŦāĻžāĻšāĻ• āĻĢāĻ˛āĻžāĻĢāĻ˛ āĻĒāĻžāĻ“āĻ¯āĻŧāĻž āĻ¯āĻžāĻŦā§‡āĨ¤ - ---- -## āĻŦā§āĻ¯āĻŦāĻšā§ƒāĻ¤ āĻŽā§‡āĻļāĻŋāĻ¨ āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚ āĻāĻ° āĻ‰āĻĻāĻžāĻšāĻ°āĻŖ - -**āĻ†āĻĒāĻ¨āĻŋ āĻŽā§‡āĻļāĻŋāĻ¨ āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚ āĻŦāĻŋāĻ­āĻŋāĻ¨ā§āĻ¨ āĻŽāĻžāĻ§ā§āĻ¯āĻŽā§‡ āĻŦā§āĻ¯āĻŦāĻšāĻžāĻ° āĻ•āĻ°āĻ¤ā§‡ āĻĒāĻžāĻ°āĻŦā§‡āĻ¨**: - -- āĻ°ā§‹āĻ—ā§€āĻ° āĻšāĻŋāĻ•āĻŋā§ŽāĻ¸āĻžāĻ° āĻ°āĻŋāĻĒā§‹āĻ°ā§āĻŸ āĻĨā§‡āĻ•ā§‡ āĻ°ā§‹āĻ—ā§‡āĻ° āĻ¸āĻŽā§āĻ­āĻžāĻŦāĻ¨āĻž āĻ…āĻ¨ā§āĻŽāĻžāĻ¨ āĻ•āĻ°āĻžāĨ¤ -- āĻĻāĻŋāĻ¤ā§‡ āĻ†āĻŦāĻšāĻžāĻ“āĻ¯āĻŧāĻžāĻ° āĻĄā§‡āĻŸāĻž āĻŦā§āĻ¯āĻŦāĻšāĻžāĻ° āĻ•āĻ°ā§‡ āĻ†āĻŦāĻšāĻžāĻ“āĻ¯āĻŧāĻž āĻāĻ° āĻĒā§‚āĻ°ā§āĻŦāĻžāĻ­āĻžāĻ¸ āĻĻā§‡āĻ“ā§ŸāĻž -- āĻāĻ•āĻŸāĻŋ āĻĒāĻžāĻ ā§āĻ¯ā§‡āĻ° āĻ…āĻ¨ā§āĻ­ā§‚āĻ¤āĻŋ āĻŦā§‹āĻāĻžāĻ° āĻœāĻ¨ā§āĻ¯āĨ¤ -- āĻ…āĻĒāĻĒā§āĻ°āĻšāĻžāĻ° āĻŦāĻ¨ā§āĻ§ āĻ•āĻ°āĻ¤ā§‡ āĻ­ā§āĻ¯āĻŧāĻž āĻ–āĻŦāĻ° āĻļāĻ¨āĻžāĻ•ā§āĻ¤ āĻ•āĻ°āĻžāĨ¤ - -āĻ…āĻ°ā§āĻĨ, āĻ…āĻ°ā§āĻĨāĻ¨ā§€āĻ¤āĻŋ, āĻ†āĻ°ā§āĻĨ āĻ¸āĻžāĻ¯āĻŧā§‡āĻ¨ā§āĻ¸, āĻ¸ā§āĻĒā§‡āĻ¸ āĻāĻ•ā§āĻ¸āĻĒā§āĻ˛ā§‹āĻ°ā§‡āĻļāĻ¨, āĻŦāĻžāĻ¯āĻŧā§‹āĻŽā§‡āĻĄāĻŋāĻ•ā§‡āĻ˛ āĻ‡āĻžā§āĻœāĻŋāĻ¨āĻŋāĻ¯āĻŧāĻžāĻ°āĻŋāĻ‚, āĻœā§āĻžāĻžāĻ¨ā§€āĻ¯āĻŧ āĻŦāĻŋāĻœā§āĻžāĻžāĻ¨ āĻāĻŦāĻ‚ āĻāĻŽāĻ¨āĻ•āĻŋ āĻŽāĻžāĻ¨āĻŦāĻŋāĻ• āĻ•ā§āĻˇā§‡āĻ¤ā§āĻ°āĻ—ā§āĻ˛āĻŋ āĻ¤āĻžāĻĻā§‡āĻ° āĻĄā§‹āĻŽā§‡āĻ¨ā§‡āĻ° āĻ•āĻ āĻŋāĻ¨, āĻĄā§‡āĻŸāĻž-āĻĒā§āĻ°āĻ¸ā§‡āĻ¸āĻŋāĻ‚ āĻ­āĻžāĻ°ā§€ āĻ¸āĻŽāĻ¸ā§āĻ¯āĻžāĻ—ā§āĻ˛āĻŋ āĻ¸āĻŽāĻžāĻ§āĻžāĻ¨ āĻ•āĻ°āĻžāĻ° āĻœāĻ¨ā§āĻ¯ āĻŽā§‡āĻļāĻŋāĻ¨ āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚āĻ•ā§‡ āĻŦā§āĻ¯āĻŦāĻšāĻžāĻ° āĻ•āĻ°ā§‡āĻ›ā§‡āĨ¤ - ---- -## āĻ‰āĻĒāĻ¸āĻ‚āĻšāĻžāĻ° - -āĻŽā§‡āĻļāĻŋāĻ¨ āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚ āĻŦāĻžāĻ¸ā§āĻ¤āĻŦ-āĻŦāĻŋāĻļā§āĻŦ āĻŦāĻž āĻ‰ā§ŽāĻĒāĻ¨ā§āĻ¨ āĻĄā§‡āĻŸāĻž āĻĨā§‡āĻ•ā§‡ āĻ…āĻ°ā§āĻĨāĻĒā§‚āĻ°ā§āĻŖ āĻ…āĻ¨ā§āĻ¤āĻ°ā§āĻĻā§ƒāĻˇā§āĻŸāĻŋ āĻ–ā§‹āĻāĻœāĻžāĻ° āĻŽāĻžāĻ§ā§āĻ¯āĻŽā§‡ āĻĒā§āĻ¯āĻžāĻŸāĻžāĻ°ā§āĻ¨-āĻ†āĻŦāĻŋāĻˇā§āĻ•āĻžāĻ°ā§‡āĻ° āĻĒā§āĻ°āĻ•ā§āĻ°āĻŋāĻ¯āĻŧāĻžāĻŸāĻŋāĻ•ā§‡ āĻ¸ā§āĻŦāĻ¯āĻŧāĻ‚āĻ•ā§āĻ°āĻŋāĻ¯āĻŧ āĻ•āĻ°ā§‡āĨ¤ āĻāĻŸāĻŋ āĻ…āĻ¨ā§āĻ¯āĻĻā§‡āĻ° āĻŽāĻ§ā§āĻ¯ā§‡ āĻŦā§āĻ¯āĻŦāĻ¸āĻž, āĻ¸ā§āĻŦāĻžāĻ¸ā§āĻĨā§āĻ¯ āĻāĻŦāĻ‚ āĻ†āĻ°ā§āĻĨāĻŋāĻ• āĻ…ā§āĻ¯āĻžāĻĒā§āĻ˛āĻŋāĻ•ā§‡āĻļāĻ¨āĻ—ā§āĻ˛āĻŋāĻ¤ā§‡ āĻ…āĻ¤ā§āĻ¯āĻ¨ā§āĻ¤ āĻŽā§‚āĻ˛ā§āĻ¯āĻŦāĻžāĻ¨ āĻŦāĻ˛ā§‡ āĻĒā§āĻ°āĻŽāĻžāĻŖāĻŋāĻ¤ āĻšāĻ¯āĻŧā§‡āĻ›ā§‡āĨ¤ - -āĻ…āĻĻā§‚āĻ° āĻ­āĻŦāĻŋāĻˇā§āĻ¯āĻ¤ā§‡, āĻŽā§‡āĻļāĻŋāĻ¨ āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚āĻ¯āĻŧā§‡āĻ° āĻŦā§āĻ¨āĻŋāĻ¯āĻŧāĻžāĻĻāĻŋāĻ—ā§āĻ˛āĻŋ āĻŦā§‹āĻāĻž āĻ¯ā§‡ āĻ•ā§‹āĻ¨āĻ“ āĻĄā§‹āĻŽā§‡āĻ¨ā§‡āĻ° āĻ˛ā§‹āĻ•ā§‡āĻĻā§‡āĻ° āĻœāĻ¨ā§āĻ¯ āĻāĻŸāĻŋāĻ° āĻŦā§āĻ¯āĻžāĻĒāĻ• āĻ—ā§āĻ°āĻšāĻŖā§‡āĻ° āĻ•āĻžāĻ°āĻŖā§‡ āĻ…āĻĒāĻ°āĻŋāĻšāĻžāĻ°ā§āĻ¯ āĻšāĻ¤ā§‡ āĻšāĻ˛ā§‡āĻ›ā§‡āĨ¤ - ---- -# 🚀 Challenge - -āĻ¸ā§āĻ•ā§‡āĻš, āĻ•āĻžāĻ—āĻœā§‡ āĻŦāĻž āĻāĻ•āĻŸāĻŋ āĻ…āĻ¨āĻ˛āĻžāĻ‡āĻ¨ āĻ…ā§āĻ¯āĻžāĻĒ āĻŦā§āĻ¯āĻŦāĻšāĻžāĻ° āĻ•āĻ°ā§‡ [āĻāĻ•ā§āĻ¸āĻžāĻ˛āĻŋāĻĄā§āĻ°](https://excalidraw.com/) AI, ML, āĻĄāĻŋāĻĒ āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚ āĻāĻŦāĻ‚ āĻĄā§‡āĻŸāĻž āĻ¸āĻžāĻ¯āĻŧā§‡āĻ¨ā§āĻ¸ā§‡āĻ° āĻŽāĻ§ā§āĻ¯ā§‡ āĻĒāĻžāĻ°ā§āĻĨāĻ•ā§āĻ¯ āĻ¸āĻŽā§āĻĒāĻ°ā§āĻ•ā§‡āĨ¤ - -# [āĻ˛ā§‡āĻ•āĻšāĻžāĻ°-āĻ•ā§āĻ‡āĻœ](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/2/) - ---- -# āĻĒāĻ°ā§āĻ¯āĻžāĻ˛ā§‹āĻšāĻ¨āĻž āĻ“ āĻ¸ā§‡āĻ˛ā§āĻĢ āĻ¸ā§āĻŸāĻžāĻĄāĻŋ - -āĻ†āĻĒāĻ¨āĻŋ āĻ•āĻŋāĻ­āĻžāĻŦā§‡ āĻ•ā§āĻ˛āĻžāĻ‰āĻĄā§‡ āĻāĻŽāĻāĻ˛ āĻ…ā§āĻ¯āĻžāĻ˛āĻ—āĻ°āĻŋāĻĻāĻŽ āĻĻāĻŋāĻ¯āĻŧā§‡ āĻ•āĻžāĻœ āĻ•āĻ°āĻ¤ā§‡ āĻĒāĻžāĻ°ā§‡āĻ¨ āĻ¸ā§‡ āĻ¸āĻŽā§āĻĒāĻ°ā§āĻ•ā§‡ āĻ†āĻ°āĻ“ āĻœāĻžāĻ¨āĻ¤ā§‡, āĻāĻŸāĻŋ āĻ…āĻ¨ā§āĻ¸āĻ°āĻŖ āĻ•āĻ°ā§āĻ¨ [āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚ āĻĒāĻžāĻĨ](https://docs.microsoft.com/learn/paths/create-no-code-predictive-models-azure-machine-learning/?WT.mc_id=academic-77952-leestott)āĨ¤ - -āĻāĻŽ āĻāĻ˛ āĻŦā§‡āĻ¸āĻŋāĻ• āĻœāĻžāĻ¨ā§āĻ¨ [āĻ˛āĻžāĻ°ā§āĻ¨āĻŋāĻ‚ āĻĒāĻžāĻĨ](https://docs.microsoft.com/learn/modules/introduction-to-machine-learning/?WT.mc_id=academic-77952-leestott) - ---- -# āĻāĻ¸āĻžāĻ‡āĻ¨ā§āĻŸāĻŽā§‡āĻ¨ā§āĻŸ - -[āĻšāĻ˛ā§āĻ¨ āĻļā§āĻ°ā§ āĻ•āĻ°āĻŋ](assignment.md) \ No newline at end of file diff --git a/1-Introduction/1-intro-to-ML/translations/README.es.md b/1-Introduction/1-intro-to-ML/translations/README.es.md deleted file mode 100644 index 024dc814..00000000 --- a/1-Introduction/1-intro-to-ML/translations/README.es.md +++ /dev/null @@ -1,113 +0,0 @@ -# IntroducciÃŗn al machine learning - -[![ML, IA, deep learning - ÂŋCuÃĄl es la diferencia?](https://img.youtube.com/vi/lTd9RSxS9ZE/0.jpg)](https://youtu.be/lTd9RSxS9ZE "ML, IA, deep learning - ÂŋCuÃĄl es la diferencia?") - -> đŸŽĨ Haz clic en la imagen de arriba para ver un video donde se discuten las diferencias entre el machine learning, la inteligencia artificial, y el deep learning. - -## [Cuestionario previo a la conferencia](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/1?loc=es) - -### IntroducciÃŗn - -ÂĄTe damos la bienvenida a este curso acerca del machine learning (ML) clÃĄsico para principiantes! Así se trate de tu primer contacto con este tema, o cuentes con amplia experiencia en el ML y busques refrescar tus conocimientos en un ÃĄrea específica, ÂĄnos alegramos de que te nos unas! Queremos crear un punto de lanzamiento amigable para tus estudios de ML y nos encantaría evaluar, responder, e incorporar tu [retroalimentaciÃŗn](https://github.com/microsoft/ML-For-Beginners/discussions). - -[![IntroducciÃŗn al ML](https://img.youtube.com/vi/h0e2HAPTGF4/0.jpg)](https://youtu.be/h0e2HAPTGF4 "IntroducciÃŗn al ML") - -> Haz clic en la imagen de arriba para ver el video: John Guttag del MIT presenta el machine learning - -### Empezando con el machine learning - -Antes de comenzar con este currículum, debes tener tu computadora configurada y lista para ejecutar los notebooks localmente. - -- **Configura tu equipo con estos videos**. Aprende mÃĄs acerca de como configurar tu equipo con [estos videos](https://www.youtube.com/playlist?list=PLlrxD0HtieHhS8VzuMCfQD4uJ9yne1mE6). -- **Aprende Python**. TambiÊn se recomienda que tengas un entendimiento bÃĄsico de [Python](https://docs.microsoft.com/learn/paths/python-language/?WT.mc_id=academic-77952-leestott), un lenguaje de programaciÃŗn Ãētil para practicantes de la ciencia de datos, y que se utiliza en este curso. -- **Aprende Node.js y JavaScript**. TambiÊn usamos JavaScript unas cuantas veces en este curso cuando creamos aplicaciones web, así que necesitarÃĄs tener [node](https://nodejs.org) y [npm](https://www.npmjs.com/) instalados, así como [Visual Studio Code](https://code.visualstudio.com/) listo para el desarrollo con Python y JavaScript. -- **Crea una cuenta de GitHub**. Como nos encontraste aquí en [GitHub](https://github.com), puede que ya tengas una cuenta, pero si no, crÊate una y despuÊs haz un fork de este curriculum para usarlo en tu computadora personal. (SiÊntete libre de darnos una estrella 😊) -- **Explora Scikit-learn**. Familiarízate con [Scikit-learn](https://scikit-learn.org/stable/user_guide.html), un conjunto de bibliotecas de ML que referenciamos en estas lecciones. - -### ÂŋQuÊ es el machine learning? - -El tÊrmino "machine learning" es uno de los tÊrminos mÃĄs frecuentemente usados y populares hoy en día. Es muy probable que hayas escuchado este tÊrmino al menos una vez si tienes algÃēn tipo de familiaridad con la tecnología, no importa el sector en que trabajes. AÃēn así, las mecÃĄnicas del machine learning son un misterio para la mayoría de la gente. Para un principiante en machine learning, el tema puede parecer intimidante. Es por esto que es importante entender lo que realmente es el machine learning y aprender sobre el tema poco a poco, a travÊs de ejemplos prÃĄcticos. - -![curva de interÊs en ml](../images/hype.png) - -> Google Trends nos muestra la "curva de interÊs" mÃĄs reciente para el tÊrmino "machine learning" - -Vivimos en un universo lleno de misterios fascinantes. Grandes científicos como Stephen Hawking, Albert Einstein, y muchos mÃĄs han dedicado sus vidas a la bÃēsqueda de informaciÃŗn significativa que revela los misterios del mundo a nuestro alrededor. Esta es la condiciÃŗn humana del aprendizaje: un niÃąo humano aprende cosas nuevas y descubre la estructura de su mundo aÃąo tras aÃąo a medida que se convierten en adultos. - -El cerebro y los sentidos de un niÃąo perciben sus alrededores y van aprendiendo gradualmente los patrones escondidos de la vida, lo que le ayuda al niÃąo a crear reglas lÃŗgicas para identificar los patrones aprendidos. El proceso de aprendizaje del cerebro humano nos hace las criaturas mÃĄs sofisticadas del planeta. Aprender de forma continua al descubrir patrones ocultos e innovar sobre esos patrones nos permite seguir mejorando a lo largo de nuestras vidas. Esta capacidad de aprendizaje y la capacidad de evoluciÃŗn estÃĄn relacionadas a un concepto llamado [plasticidad cerebral o neuroplasticidad](https://www.simplypsychology.org/brain-plasticity.html). Podemos trazar algunas similitudes superficiales en cuanto a la motivaciÃŗn entre el proceso de aprendizaje del cerebro humano y los conceptos de machine learning. - -El [cerebro humano](https://www.livescience.com/29365-human-brain.html) percibe cosas del mundo real, procesa la informaciÃŗn percibida, toma decisiones racionales, y realiza ciertas acciones basadas en las circunstancias. Esto es a lo que se le conoce como el comportamiento inteligente. Cuando programamos un facsímil (copia) del proceso del comportamiento inteligente, se le llama inteligencia artificial (IA). - -Aunque los tÊrminos se suelen confundir, machine learning (ML) es una parte importante de la inteligencia artificial. **El objetivo del ML es utilizar algoritmos especializados para descubrir informaciÃŗn significativa y encontrar patrones ocultos de los datos percibidos para corroborar el proceso relacional de la toma de decisiones**. - -![IA, ML, deep learning, ciencia de los datos](../images/ai-ml-ds.png) - -> El diagrama muestra la relaciÃŗn entre IA, ML, deep learning y la ciencia de los datos. Infografía hecha por [Jen Looper](https://twitter.com/jenlooper) inspirada en [esta grÃĄfica](https://softwareengineering.stackexchange.com/questions/366996/distinction-between-ai-ml-neural-networks-deep-learning-and-data-mining). - -## Lo que aprenderÃĄs en el curso - -En este currículum, vamos a cubrir solo los conceptos clave de machine learning que un principiante debería conocer. Cubrimos algo a lo que le llamamos "machine learning clÃĄsico" usando principalmente Scikit-learn, una biblioteca excelente que muchos estudiantes utilizan para aprender las bases. Para entender conceptos mÃĄs amplios de la inteligencia artificial o deep learning, es indispensable tener un fuerte conocimiento de los fundamentos, y eso es lo que nos gustaría ofrecerte aquí. - -En este curso aprenderÃĄs: - -- conceptos clave del machine learning -- la historia del ML -- la justicia y el ML -- tÊcnicas de regresiÃŗn en ML -- tÊcnicas de clasificaciÃŗn en ML -- tÊcnicas de agrupamiento en ML -- tÊcnicas de procesamiento del lenguaje natural en ML -- tÊcnicas de previsiÃŗn de series temporales en ML -- reforzamiento del aprendizaje -- ML aplicada al mundo real - -## Lo que no cubriremos - -- deep learning -- redes neuronales -- inteligencia artificial (IA) - -Para tener una mejor experiencia de aprendizaje, vamos a evitar las complejidades de las redes neuronales, "deep learning" (construcciÃŗn de modelos de muchas capas utilizando las redes neuronales) e inteligencia artificial, que se discutirÃĄ en un currículum diferente. En un futuro tambiÊn ofreceremos un currículum acerca de la ciencia de datos para enfocarnos en ese aspecto de ese campo. - -## ÂŋPor quÊ estudiar machine learning? - -El Machine learning, desde una perspectiva de los sistemas, se define como la creaciÃŗn de sistemas automÃĄticos que pueden aprender patrones ocultos a partir de datos para ayudar en tomar decisiones inteligentes. - -Esta motivaciÃŗn estÃĄ algo inspirada por como el cerebro humano aprende ciertas cosas basadas en los datos que percibe en el mundo real. - -✅ Piensa por un minuto en porquÊ querría un negocio intentar implementar estrategias de machine learning en lugar de programar un motor basado en reglas programadas de forma rígida. - -### Aplicaciones del machine learning - -Las aplicaciones del machine learning hoy en día estÃĄn casi en todas partes, y son tan ubicuas como los datos que fluyen alrededor de nuestras sociedades, generados por nuestros telÊfonos inteligentes, dispositivos conectados a internet, y otros sistemas. Considerando el inmenso potencial de los algoritmos punteros de machine learning, los investigadores han estado explorando su capacidad de resolver problemas multidimensionales y multidisciplinarios de la vida real con resultados muy positivos. - -**TÃē puedes utilizar machine learning de muchas formas**: - -- Para predecir la probabilidad de enfermedad a partir del historial mÊdico o reportes de un paciente. -- Para aprovechar datos del clima y predecir eventos climatolÃŗgicos. -- Para entender la intenciÃŗn de un texto. -- Para detectar noticias falsas y evitar la propagaciÃŗn de propaganda. - -Finanzas, economía, ciencias de la Tierra, exploraciÃŗn espacial, ingeniería biomÊdica, ciencia cognitiva, e incluso campos en las humanidades han adaptado machine learning para solucionar algunos de los problemas mÃĄs arduos y pesados en cuanto al procesamiento de datos de cada una de estas ramas. - -Machine learning automatiza el proceso del descubrimiento de patrones al encontrar perspectivas significativas de datos provenientes del mundo real o generados. Machine learning ha demostrado ser muy valioso en las aplicaciones del sector de la salud, de negocios y finanzas, entre otros. - -En el futuro prÃŗximo, entender las bases de machine learning va a ser una necesidad para la gente en cualquier sector debido a su adopciÃŗn tan extendida. - ---- - -## 🚀 Desafío - -Dibuja, en papel o usando una aplicaciÃŗn como [Excalidraw](https://excalidraw.com/), cÃŗmo entiendes las diferencias entre inteligencia artificial, ML, deep learning, y la ciencia de datos. Agrega algunas ideas de problemas que cada una de estas tÊcnicas son buenas en resolver. - -## [Cuestionario despuÊs de la lecciÃŗn](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/2?loc=es) - -## RevisiÃŗn y autoestudio - -Para aprender mÃĄs sobre como puedes trabajar con algoritmos de ML en la nube, sigue esta [Ruta de Aprendizaje](https://docs.microsoft.com/learn/paths/create-no-code-predictive-models-azure-machine-learning/?WT.mc_id=academic-77952-leestott). - -Toma esta [Ruta de Aprendizaje](https://docs.microsoft.com/learn/modules/introduction-to-machine-learning/?WT.mc_id=academic-77952-leestott) sobre las bases de ML. - -## Tarea - -[Ponte en marcha](assignment.md) diff --git a/1-Introduction/1-intro-to-ML/translations/README.fr.md b/1-Introduction/1-intro-to-ML/translations/README.fr.md deleted file mode 100644 index b9c7fb31..00000000 --- a/1-Introduction/1-intro-to-ML/translations/README.fr.md +++ /dev/null @@ -1,109 +0,0 @@ -# Introduction au machine learning - -[![ML, AI, deep learning - Quelle est la diffÊrence ?](https://img.youtube.com/vi/lTd9RSxS9ZE/0.jpg)](https://youtu.be/lTd9RSxS9ZE "ML, AI, deep learning - What's the difference?") - -> đŸŽĨ Cliquer sur l'image ci-dessus afin de regarder une vidÊo expliquant la diffÊrence entre machine learning, AI et deep learning. - -## [Quiz prÊalable](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/1?loc=fr) - -### Introduction - -Bienvenue à ce cours sur le machine learning classique pour dÊbutant ! Que vous soyez complètement nouveau sur ce sujet ou que vous soyez un professionnel du ML expÊrimentÊ cherchant à peaufiner vos connaissances, nous sommes heureux de vous avoir avec nous ! Nous voulons crÊer un tremplin chaleureux pour vos Êtudes en ML et serions ravis d'Êvaluer, de rÊpondre et d'apprendre de vos retours d'[expÊriences](https://github.com/microsoft/ML-For-Beginners/discussions). - -[![Introduction au ML](https://img.youtube.com/vi/h0e2HAPTGF4/0.jpg)](https://youtu.be/h0e2HAPTGF4 "Introduction to ML") - -> đŸŽĨ Cliquer sur l'image ci-dessus afin de regarder une vidÊo: John Guttag du MIT introduit le machine learning -### DÊbuter avec le machine learning - -Avant de commencer avec ce cours, vous aurez besoin d'un ordinateur configurÊ et prÃĒt à faire tourner des notebooks (jupyter) localement. - -- **Configurer votre ordinateur avec ces vidÊos**. Apprendre comment configurer votre ordinateur avec cette [sÊrie de vidÊos](https://www.youtube.com/playlist?list=PLlrxD0HtieHhS8VzuMCfQD4uJ9yne1mE6). -- **Apprendre Python**. Il est aussi recommandÊ d'avoir une connaissance basique de [Python](https://docs.microsoft.com/learn/paths/python-language/?WT.mc_id=academic-77952-leestott), un langage de programmaton utile pour les data scientist que nous utilisons tout au long de ce cours. -- **Apprendre Node.js et Javascript**. Nous utilisons aussi Javascript par moment dans ce cours afin de construire des applications WEB, vous aurez donc besoin de [node](https://nodejs.org) et [npm](https://www.npmjs.com/) installÊ, ainsi que de [Visual Studio Code](https://code.visualstudio.com/) pour dÊvelopper en Python et Javascript. -- **CrÊer un compte GitHub**. Comme vous nous avez trouvÊ sur [GitHub](https://github.com), vous y avez sÃģrement un compte, mais si non, crÊez en un et rÊpliquez ce cours afin de l'utiliser à votre grÊs. (N'oublier pas de nous donner une Êtoile aussi 😊) -- **Explorer Scikit-learn**. Familiariser vous avec [Scikit-learn](https://scikit-learn.org/stable/user_guide.html), un ensemble de librairies ML que nous mentionnons dans nos leçons. - -### Qu'est-ce que le machine learning - -Le terme `machine learning` est un des mots les plus populaire et le plus utilisÊ ces derniers temps. Il y a une probabilitÊ accrue que vous l'ayez entendu au moins une fois si vous avez une appÊtence pour la technologie indÊpendamment du domaine dans lequel vous travaillez. Le fonctionnement du machine learning, cependant, reste un mystère pour la plupart des personnes. Pour un dÊbutant en machine learning, le sujet peut nous submerger. Ainsi, il est important de comprendre ce qu'est le machine learning et de l'apprendre petit à petit au travers d'exemples pratiques. - -![ml hype curve](../images/hype.png) - -> Google Trends montre la rÊcente 'courbe de popularitÊ' pour le mot 'machine learning' - -Nous vivons dans un univers rempli de mystères fascinants. De grands scientifiques comme Stephen Hawking, Albert Einstein et pleins d'autres ont dÊvouÊs leur vie à la recherche d'informations utiles afin de dÊvoiler les mystères qui nous entourent. C'est la condition humaine pour apprendre : un enfant apprend de nouvelles choses et dÊcouvre la structure du monde annÊe après annÊe jusqu'à qu'ils deviennent adultes. - -Le cerveau d'un enfant et ses sens perçoivent l'environnement qui les entourent et apprennent graduellement des schÊmas non observÊs de la vie qui vont l'aider à fabriquer des règles logiques afin d'identifier les schÊmas appris. Le processus d'apprentissage du cerveau humain est ce que rend les hommes comme la crÊature la plus sophistiquÊe du monde vivant. Apprendre continuellement par la dÊcouverte de schÊmas non observÊs et ensuite innover sur ces schÊmas nous permet de nous amÊliorer tout au long de notre vie. Cette capacitÊ d'apprendre et d'Êvoluer est liÊe au concept de [plasticitÊ neuronale](https://www.simplypsychology.org/brain-plasticity.html), nous pouvons tirer quelques motivations similaires entre le processus d'apprentissage du cerveau humain et le concept de machine learning. - -Le [cerveau humain](https://www.livescience.com/29365-human-brain.html) perçoit des choses du monde rÊel, assimile les informations perçues, fait des dÊcisions rationnelles et entreprend certaines actions selon le contexte. C'est ce que l'on appelle se comporter intelligemment. Lorsque nous programmons une reproduction du processus de ce comportement à une machine, c'est ce que l'on appelle intelligence artificielle (IA). - -Bien que le terme peut ÃĒtre confu, machine learning (ML) est un important sous-ensemble de l'intelligence artificielle. **ML se rÊfère à l'utilisation d'algorithmes spÊcialisÊs afin de dÊcouvrir des informations utiles et de trouver des schÊmas non observÊs depuis des donnÊes perçues pour corroborer un processus de dÊcision rationnel**. - -![AI, ML, deep learning, data science](../images/ai-ml-ds.png) - -> Un diagramme montrant les relations entre AI, ML, deep learning et data science. Infographie par [Jen Looper](https://twitter.com/jenlooper) et inspirÊ par [ce graphique](https://softwareengineering.stackexchange.com/questions/366996/distinction-between-ai-ml-neural-networks-deep-learning-and-data-mining) - -## Ce que vous allez apprendre dans ce cours - -Dans ce cours, nous allons nous concentrer sur les concepts clÊs du machine learning qu'un dÊbutant se doit de connaÃŽtre. Nous parlerons de ce que l'on appelle le 'machine learning classique' en utilisant principalement Scikit-learn, une excellente librairie que beaucoup d'Êtudiants utilisent afin d'apprendre les bases. Afin de comprendre les concepts plus larges de l'intelligence artificielle ou du deep learning, une profonde connaissance en machine learning est indispensable, et c'est ce que nous aimerions fournir ici. - -Dans ce cours, vous allez apprendre : - -- Les concepts clÊs du machine learning -- L'histoire du ML -- ML et ÊquitÊ (fairness) -- Les techniques de rÊgression ML -- Les techniques de classification ML -- Les techniques de regroupement (clustering) ML -- Les techniques du traitement automatique des langues (NLP) ML -- Les techniques de prÊdictions à partir de sÊries chronologiques ML -- Apprentissage renforcÊ -- D'applications rÊels du ML - -## Ce que nous ne couvrirons pas - -- Deep learning -- Neural networks -- IA - -Afin d'avoir la meilleur expÊrience d'apprentissage, nous Êviterons les complexitÊs des rÊseaux neuronaux, du 'deep learning' (construire un modèle utilisant plusieurs couches de rÊseaux neuronaux) et IA, dont nous parlerons dans un cours diffÊrent. Nous offirons aussi un cours à venir sur la data science pour concentrer sur cet aspect de champs très large. - -## Pourquoi etudier le machine learning ? - -Le machine learning, depuis une perspective systÊmique, est dÊfini comme la crÊation de systèmes automatiques pouvant apprendre des schÊmas non observÊs depuis des donnÊes afin d'aider à prendre des dÊcisions intelligentes. - -Ce but est faiblement inspirÊ de la manière dont le cerveau humain apprend certaines choses depuis les donnÊes qu'il perçoit du monde extÊrieur. - -✅ Penser une minute aux raisons qu'une entreprise aurait d'essayer d'utiliser des stratÊgies de machine learning au lieu de crÊer des règles codÊs en dur. - -### Les applications du machine learning - -Les applications du machine learning sont maintenant pratiquement partout, et sont aussi omniprÊsentes que les donnÊes qui circulent autour de notre sociÊtÊ (gÊnÊrÊs par nos smartphones, appareils connectÊs ou autres systèmes). En prenant en considÊration l'immense potentiel des algorithmes dernier cri de machine learning, les chercheurs ont pu exploitÊs leurs capacitÊs afin de rÊsoudre des problèmes multidimensionnels et interdisciplinaires de la vie avec d'important retours positifs - -**Vous pouvez utiliser le machine learning de plusieurs manières** : - -- Afin de prÊdire la possibilitÊ d'avoir une maladie à partir des donnÊes mÊdicales d'un patient. -- Pour tirer parti des donnÊes mÊtÊorologiques afin de prÊdire les ÊvÊnements mÊtÊorologiques. -- Afin de comprendre le sentiment d'un texte. -- Afin de dÊtecter les fake news pour stopper la propagation de la propagande. - -La finance, l'Êconomie, les sciences de la terre, l'exploration spatiale, le gÊnie biomÊdical, les sciences cognitives et mÃĒme les domaines des sciences humaines ont adaptÊ le machine learning pour rÊsoudre les problèmes ardus et lourds de traitement des donnÊes dans leur domaine respectif. - -Le machine learning automatise le processus de dÊcouverte de modèles en trouvant des informations significatives à partir de donnÊes rÊelles ou gÊnÊrÊes. Il s'est avÊrÊ très utile dans les applications commerciales, de santÊ et financières, entre autres. - -Dans un avenir proche, comprendre les bases du machine learning sera indispensable pour les personnes de tous les domaines en raison de son adoption gÊnÊralisÊe. - ---- -## 🚀 Challenge - -Esquisser, sur papier ou à l'aide d'une application en ligne comme [Excalidraw](https://excalidraw.com/), votre comprÊhension des diffÊrences entre l'IA, le ML, le deep learning et la data science. Ajouter quelques idÊes de problèmes que chacune de ces techniques est bonne à rÊsoudre. - -## [Quiz de validation des connaissances](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/2?loc=fr) - -## RÊvision et auto-apprentissage - -Pour en savoir plus sur la façon dont vous pouvez utiliser les algorithmes de ML dans le cloud, suivez ce [Parcours d'apprentissage](https://docs.microsoft.com/learn/paths/create-no-code-predictive-models-azure-machine-learning/?WT.mc_id=academic-77952-leestott). - -## Devoir - -[Être opÊrationnel](assignment.fr.md) diff --git a/1-Introduction/1-intro-to-ML/translations/README.id.md b/1-Introduction/1-intro-to-ML/translations/README.id.md deleted file mode 100644 index 230bddfb..00000000 --- a/1-Introduction/1-intro-to-ML/translations/README.id.md +++ /dev/null @@ -1,107 +0,0 @@ -# Pengantar Machine Learning - -[![ML, AI, deep learning - Apa perbedaannya?](https://img.youtube.com/vi/lTd9RSxS9ZE/0.jpg)](https://youtu.be/lTd9RSxS9ZE "ML, AI, deep learning - Apa perbedaannya?") - -> đŸŽĨ Klik gambar diatas untuk menonton video yang mendiskusikan perbedaan antara Machine Learning, AI, dan Deep Learning. - -## [Quiz Pra-Pelajaran](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/1/) - -### Pengantar - -Selamat datang di pelajaran Machine Learning klasik untuk pemula! Baik kamu yang masih benar-benar baru, atau seorang praktisi ML berpengalaman yang ingin meningkatkan kemampuan kamu, kami senang kamu ikut bersama kami! Kami ingin membuat sebuah titik mulai yang ramah untuk pembelajaran ML kamu dan akan sangat senang untuk mengevaluasi, merespon, dan memasukkan [umpan balik](https://github.com/microsoft/ML-For-Beginners/discussions) kamu. - -[![Pengantar Machine Learning](https://img.youtube.com/vi/h0e2HAPTGF4/0.jpg)](https://youtu.be/h0e2HAPTGF4 "Pengantar Machine Learning") - -> đŸŽĨ Klik gambar diatas untuk menonton video: John Guttag dari MIT yang memberikan pengantar Machine Learning. -### Memulai Machine Learning - -Sebelum memulai kurikulum ini, kamu perlu memastikan komputer kamu sudah dipersiapkan untuk menjalankan *notebook* secara lokal. - -- **Konfigurasi komputer kamu dengan video ini**. Pelajari bagaimana menyiapkan komputer kamu dalam [video-video](https://www.youtube.com/playlist?list=PLlrxD0HtieHhS8VzuMCfQD4uJ9yne1mE6) ini. -- **Belajar Python**. Disarankan juga untuk memiliki pemahaman dasar dari [Python](https://docs.microsoft.com/learn/paths/python-language/?WT.mc_id=academic-77952-leestott), sebuah bahasa pemrograman yang digunakan oleh data scientist yang juga akan kita gunakan dalam pelajaran ini. -- **Belajar Node.js dan JavaScript**. Kita juga menggunakan JavaScript beberapa kali dalam pelajaran ini ketika membangun aplikasi web, jadi kamu perlu menginstal [node](https://nodejs.org) dan [npm](https://www.npmjs.com/), serta [Visual Studio Code](https://code.visualstudio.com/) yang tersedia untuk pengembangan Python dan JavaScript. -- **Buat akun GitHub**. Karena kamu menemukan kami di [GitHub](https://github.com), kamu mungkin sudah punya akun, tapi jika belum, silakan buat akun baru kemudian *fork* kurikulum ini untuk kamu pergunakan sendiri. (Jangan ragu untuk memberikan kami bintang juga 😊) -- **Jelajahi Scikit-learn**. Buat diri kamu familiar dengan [Scikit-learn]([https://scikit-learn.org/stable/user_guide.html), seperangkat *library* ML yang kita acu dalam pelajaran-pelajaran ini. - -### Apa itu Machine Learning? - -Istilah 'Machine Learning' merupakan salah satu istilah yang paling populer dan paling sering digunakan saat ini. Ada kemungkinan kamu pernah mendengar istilah ini paling tidak sekali jika kamu familiar dengan teknologi. Tetapi untuk mekanisme Machine Learning sendiri, merupakan sebuah misteri bagi sebagian besar orang. Karena itu, penting untuk memahami sebenarnya apa itu Machine Learning, dan mempelajarinya langkah demi langkah melalui contoh praktis. - -![kurva tren ml](../images/hype.png) - -> Google Trends memperlihatkan 'kurva tren' dari istilah 'Machine Learning' belakangan ini. - -Kita hidup di sebuah alam semesta yang penuh dengan misteri yang menarik. Ilmuwan-ilmuwan besar seperti Stephen Hawking, Albert Einstein, dan banyak lagi telah mengabdikan hidup mereka untuk mencari informasi yang berarti yang mengungkap misteri dari dunia disekitar kita. Ini adalah kondisi belajar manusia: seorang anak manusia belajar hal-hal baru dan mengungkap struktur dari dunianya tahun demi tahun saat mereka tumbuh dewasa. - -Otak dan indera seorang anak memahami fakta-fakta di sekitarnya dan secara bertahap mempelajari pola-pola kehidupan yang tersembunyi yang membantu anak untuk menyusun aturan-aturan logis untuk mengidentifikasi pola-pola yang dipelajari. Proses pembelajaran otak manusia ini menjadikan manusia sebagai makhluk hidup paling canggih di dunia ini. Belajar terus menerus dengan menemukan pola-pola tersembunyi dan kemudian berinovasi pada pola-pola itu memungkinkan kita untuk terus menjadikan diri kita lebih baik sepanjang hidup. Kapasitas belajar dan kemampuan berkembang ini terkait dengan konsep yang disebut dengan *[brain plasticity](https://www.simplypsychology.org/brain-plasticity.html)*. Secara sempit, kita dapat menarik beberapa kesamaan motivasi antara proses pembelajaran otak manusia dan konsep Machine Learning. - -[Otak manusia](https://www.livescience.com/29365-human-brain.html) menerima banyak hal dari dunia nyata, memproses informasi yang diterima, membuat keputusan rasional, dan melakukan aksi-aksi tertentu berdasarkan keadaan. Inilah yang kita sebut dengan berperilaku cerdas. Ketika kita memprogram sebuah salinan dari proses perilaku cerdas ke sebuah mesin, ini dinamakan kecerdasan buatan atau Artificial Intelligence (AI). - -Meskipun istilah-stilahnya bisa membingungkan, Machine Learning (ML) adalah bagian penting dari Artificial Intelligence. **ML berkaitan dengan menggunakan algoritma-algoritma terspesialisasi untuk mengungkap informasi yang berarti dan mencari pola-pola tersembunyi dari data yang diterima untuk mendukung proses pembuatan keputusan rasional**. - -![AI, ML, deep learning, data science](../images/ai-ml-ds.png) - -> Sebuah diagram yang memperlihatkan hubungan antara AI, ML, Deep Learning, dan Data Science. Infografis oleh [Jen Looper](https://twitter.com/jenlooper) terinspirasi dari [infografis ini](https://softwareengineering.stackexchange.com/questions/366996/distinction-between-ai-ml-neural-networks-deep-learning-and-data-mining) - -## Apa yang akan kamu pelajari - -Dalam kurikulum ini, kita hanya akan membahas konsep inti dari Machine Learning yang harus diketahui oleh seorang pemula. Kita membahas apa yang kami sebut sebagai 'Machine Learning klasik' utamanya menggunakan Scikit-learn, sebuah *library* luar biasa yang banyak digunakan para siswa untuk belajar dasarnya. Untuk memahami konsep Artificial Intelligence atau Deep Learning yang lebih luas, pengetahuan dasar yang kuat tentang Machine Learning sangat diperlukan, itulah yang ingin kami tawarkan di sini. - -Kamu akan belajar: - -- Konsep inti ML -- Sejarah dari ML -- Keadilan dan ML -- Teknik regresi ML -- Teknik klasifikasi ML -- Teknik *clustering* ML -- Teknik *natural language processing* ML -- Teknik *time series forecasting* ML -- *Reinforcement learning* -- Penerapan nyata dari ML -## Yang tidak akan kita bahas - -- *deep learning* -- *neural networks* -- AI - -Untuk membuat pengalaman belajar yang lebih baik, kita akan menghindari kerumitan dari *neural network*, *deep learning* - membangun *many-layered model* menggunakan *neural network* - dan AI, yang mana akan kita bahas dalam kurikulum yang berbeda. Kami juga akan menawarkan kurikulum *data science* yang berfokus pada aspek bidang tersebut. -## Kenapa belajar Machine Learning? - -Machine Learning, dari perspektif sistem, didefinisikan sebagai pembuatan sistem otomatis yang dapat mempelajari pola-pola tersembunyi dari data untuk membantu membuat keputusan cerdas. - -Motivasi ini secara bebas terinspirasi dari bagaimana otak manusia mempelajari hal-hal tertentu berdasarkan data yang diterimanya dari dunia luar. - -✅ Pikirkan sejenak mengapa sebuah bisnis ingin mencoba menggunakan strategi Machine Learning dibandingkan membuat sebuah mesin berbasis aturan yang tertanam (*hard-coded*). - -### Penerapan Machine Learning - -Penerapan Machine Learning saat ini hampir ada di mana-mana, seperti data yang mengalir di sekitar kita, yang dihasilkan oleh ponsel pintar, perangkat yang terhubung, dan sistem lainnya. Mempertimbangkan potensi besar dari algoritma Machine Learning terkini, para peneliti telah mengeksplorasi kemampuan Machine Learning untuk memecahkan masalah kehidupan nyata multi-dimensi dan multi-disiplin dengan hasil positif yang luar biasa. - -**Kamu bisa menggunakan Machine Learning dalam banyak hal**: - -- Untuk memprediksi kemungkinan penyakit berdasarkan riwayat atau laporan medis pasien. -- Untuk memanfaatkan data cuaca untuk memprediksi peristiwa cuaca. -- Untuk memahami sentimen sebuah teks. -- Untuk mendeteksi berita palsu untuk menghentikan penyebaran propaganda. - -Keuangan, ekonomi, geosains, eksplorasi ruang angkasa, teknik biomedis, ilmu kognitif, dan bahkan bidang humaniora telah mengadaptasi Machine Learning untuk memecahkan masalah sulit pemrosesan data di bidang mereka. - -Machine Learning mengotomatiskan proses penemuan pola dengan menemukan wawasan yang berarti dari dunia nyata atau dari data yang dihasilkan. Machine Learning terbukti sangat berharga dalam penerapannya di berbagai bidang, diantaranya adalah bidang bisnis, kesehatan, dan keuangan. - -Dalam waktu dekat, memahami dasar-dasar Machine Learning akan menjadi suatu keharusan bagi orang-orang dari bidang apa pun karena adopsinya yang luas. - ---- -## 🚀 Tantangan - -Buat sketsa di atas kertas atau menggunakan aplikasi seperti [Excalidraw](https://excalidraw.com/), mengenai pemahaman kamu tentang perbedaan antara AI, ML, Deep Learning, dan Data Science. Tambahkan beberapa ide masalah yang cocok diselesaikan masing-masing teknik. - -## [Quiz Pasca-Pelajaran](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/2/) - -## Ulasan & Belajar Mandiri - -Untuk mempelajari lebih lanjut tentang bagaimana kamu dapat menggunakan algoritma ML di cloud, ikuti [Jalur Belajar](https://docs.microsoft.com/learn/paths/create-no-code-predictive-models-azure-machine-learning/?WT.mc_id=academic-77952-leestott) ini. - -## Tugas - -[Persiapan](assignment.id.md) diff --git a/1-Introduction/1-intro-to-ML/translations/README.it.md b/1-Introduction/1-intro-to-ML/translations/README.it.md deleted file mode 100644 index 37b23a0a..00000000 --- a/1-Introduction/1-intro-to-ML/translations/README.it.md +++ /dev/null @@ -1,108 +0,0 @@ -# Introduzione a machine learning - -[![ML, AI, deep learning: qual è la differenza?](https://img.youtube.com/vi/lTd9RSxS9ZE/0.jpg)](https://youtu.be/lTd9RSxS9ZE "ML, AI, deep learning: qual è la differenza?") - -> đŸŽĨ Fare clic sull'immagine sopra per un video che illustra la differenza tra machine learning, intelligenza artificiale (AI) e deep learning. - -## [Quiz pre-lezione](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/1/?loc=it) - -### Introduzione - -Benvenuti in questo corso su machine learning classico per principianti! Che si sia completamente nuovo su questo argomento, o un professionista esperto di ML che cerca di rispolverare un'area, è un piacere avervi con noi! Si vuole creare un punto di partenza amichevole per lo studio di ML e saremo lieti di valutare, rispondere e incorporare il vostro [feedback](https://github.com/microsoft/ML-For-Beginners/discussions). - -[![Introduzione a ML](https://img.youtube.com/vi/h0e2HAPTGF4/0.jpg)](https://youtu.be/h0e2HAPTGF4 " Introduzione a ML") - -> đŸŽĨ Fare clic sull'immagine sopra per un video: John Guttag del MIT introduce machine learning - -### Iniziare con machine learning - -Prima di iniziare con questo programma di studi, è necessario che il computer sia configurato e pronto per eseguire i notebook in locale. - -- **Si configuri la propria macchina con l'aiuto di questi video**. Si scopra di piÚ su come configurare la propria macchina in questa [serie di video](https://www.youtube.com/playlist?list=PLlrxD0HtieHhS8VzuMCfQD4uJ9yne1mE6). -- **Imparare Python**. Si consiglia inoltre di avere una conoscenza di base di [Python](https://docs.microsoft.com/learn/paths/python-language/?WT.mc_id=academic-77952-leestott), un linguaggio di programmazione utile per i data scientist che si utilizzerà in questo corso. -- **Imparare Node.js e JavaScript**. Talvolta in questo corso si usa anche JavaScript durante la creazione di app web, quindi sarà necessario disporre di [node](https://nodejs.org) e [npm](https://www.npmjs.com/) installati, oltre a [Visual Studio Code](https://code.visualstudio.com/) disponibile sia per lo sviluppo Python che JavaScript. -- **Creare un account GitHub**. E' probabile che si [](https://github.com)disponga già di un account GitHub, ma in caso contrario occorre crearne uno e poi eseguire il fork di questo programma di studi per utilizzarlo autonomamente. (Sentitevi liberi di darci anche una stella 😊) -- **Esplorare Scikit-learn**. Familiarizzare con Scikit-learn,[]([https://scikit-learn.org/stable/user_guide.html) un insieme di librerie ML a cui si farà riferimento in queste lezioni. - -### Che cos'è machine learning? - -Il termine "machine learning" è uno dei termini piÚ popolari e usati di oggi. C'è una buona possibilità che si abbia sentito questo termine almeno una volta se si ha una sorta di familiarità con la tecnologia, indipendentemente dal campo in cui si lavora. I meccanismi di machine learning, tuttavia, sono un mistero per la maggior parte delle persone. Per un principiante di machine learning l'argomento a volte puÃ˛ sembrare soffocante. Pertanto, è importante capire cos'è effettivamente machine learning e impararlo passo dopo passo, attraverso esempi pratici. - -![ml curva di hype](../images/hype.png) - -> Google Trends mostra la recente "curva di hype" del termine "machine learning" - -Si vive in un universo pieno di misteri affascinanti. Grandi scienziati come Stephen Hawking, Albert Einstein e molti altri hanno dedicato la loro vita alla ricerca di informazioni significative che svelino i misteri del mondo circostante. Questa è la condizione umana dell'apprendimento: un bambino impara cose nuove e scopre la struttura del suo mondo anno dopo anno mentre cresce fino all'età adulta. - -Il cervello e i sensi di un bambino percepiscono i fatti dell'ambiente circostante e apprendono gradualmente i modelli di vita nascosti che aiutano il bambino a creare regole logiche per identificare i modelli appresi. Il processo di apprendimento del cervello umano rende l'essere umano la creatura vivente piÚ sofisticata di questo mondo. Imparare continuamente scoprendo schemi nascosti e poi innovare su questi schemi ci consente di migliorarsi sempre di piÚ per tutta la vita. Questa capacità di apprendimento e capacità di evoluzione è correlata a un concetto chiamato [plasticità cerebrale](https://www.simplypsychology.org/brain-plasticity.html). Superficialmente, si possono tracciare alcune somiglianze motivazionali tra il processo di apprendimento del cervello umano e i concetti di machine learning. - -Il [cervello umano](https://www.livescience.com/29365-human-brain.html) percepisce le cose dal mondo reale, elabora le informazioni percepite, prende decisioni razionali ed esegue determinate azioni in base alle circostanze. Questo è ciÃ˛ che viene chiamato comportarsi in modo intelligente. Quando si programma un facsimile del processo comportamentale intelligente su una macchina, si parla di intelligenza artificiale (AI). - -Sebbene i termini possano essere confusi, machine learning (ML) è un importante sottoinsieme dell'intelligenza artificiale. **Machine learning si occupa di utilizzare algoritmi specializzati per scoprire informazioni significative e trovare modelli nascosti dai dati percepiti per corroborare il processo decisionale razionale**. - -![AI, machine learning, deep learning, data science](../images/ai-ml-ds.png) - -> Un diagramma che mostra le relazioni tra intelligenza artificiale (AI), machine learning, deep learning e data science. Infografica di [Jen Looper](https://twitter.com/jenlooper) ispirata a [questa grafica](https://softwareengineering.stackexchange.com/questions/366996/distinction-between-ai-ml-neural-networks-deep-learning-and-data-mining) - -## Ecco cosa si imparerà in questo corso - -In questo programma di studi, saranno tratteti solo i concetti fondamentali di machine learning che un principiante deve conoscere. Si tratterà di ciÃ˛ che viene chiamato "machine learning classico" principalmente utilizzando Scikit-learn, una eccellente libreria che molti studenti usano per apprendere le basi. Per comprendere concetti piÚ ampi di intelligenza artificiale o deep learning, è indispensabile una forte conoscenza fondamentale di machine learning, e quindi la si vorrebbe offrire qui. - -In questo corso si imparerà: - -- concetti fondamentali di machine learning -- la storia di ML -- ML e correttezza -- tecniche di regressione ML -- tecniche di classificazione ML -- tecniche di clustering ML -- tecniche di elaborazione del linguaggio naturale ML -- tecniche ML di previsione delle serie temporali -- reinforcement learning -- applicazioni del mondo reale per ML -## Cosa non verrà trattato - -- deep learning -- reti neurali -- AI (intelligenza artificiale) - -Per rendere l'esperienza di apprendimento migliore, si eviteranno le complessità delle reti neurali, del "deep learning" (costruzione di modelli a piÚ livelli utilizzando le reti neurali) e dell'AI, di cui si tratterà in un altro programma di studi. Si offrirà anche un prossimo programma di studi di data science per concentrarsi su quell'aspetto di questo campo piÚ ampio. -## PerchÊ studiare machine learning? - -Machine learning, dal punto di vista dei sistemi, è definito come la creazione di sistemi automatizzati in grado di apprendere modelli nascosti dai dati per aiutare a prendere decisioni intelligenti. - -Questa motivazione è vagamente ispirata dal modo in cui il cervello umano apprende determinate cose in base ai dati che percepisce dal mondo esterno. - -✅ Si pensi per un minuto al motivo per cui un'azienda dovrebbe provare a utilizzare strategie di machine learning rispetto alla creazione di un motore cablato a codice basato su regole codificate. - -### Applicazioni di machine learning - -Le applicazioni di machine learning sono ormai quasi ovunque e sono onnipresenti come i dati che circolano nelle società, generati dagli smartphone, dispositivi connessi e altri sistemi. Considerando l'immenso potenziale degli algoritmi di machine learning all'avanguardia, i ricercatori hanno esplorato la loro capacità di risolvere problemi multidimensionali e multidisciplinari della vita reale con grandi risultati positivi. - -**Si puÃ˛ utilizzare machine learning in molti modi**: - -- Per prevedere la probabilità di malattia dall'anamnesi o dai rapporti di un paziente. -- Per sfruttare i dati meteorologici per prevedere gli eventi meteorologici. -- Per comprendere il sentimento di un testo. -- Per rilevare notizie false per fermare la diffusione della propaganda. - -La finanza, l'economia, le scienze della terra, l'esplorazione spaziale, l'ingegneria biomedica, le scienze cognitive e persino i campi delle scienze umanistiche hanno adattato machine learning per risolvere gli ardui problemi di elaborazione dati del proprio campo. - -Machine learning automatizza il processo di individuazione dei modelli trovando approfondimenti significativi dal mondo reale o dai dati generati. Si è dimostrato di grande valore in applicazioni aziendali, sanitarie e finanziarie, tra le altre. - -Nel prossimo futuro, comprendere le basi di machine learning sarà un must per le persone in qualsiasi campo a causa della sua adozione diffusa. - ---- -## 🚀 Sfida - -Disegnare, su carta o utilizzando un'app online come [Excalidraw](https://excalidraw.com/), la propria comprensione delle differenze tra AI, ML, deep learning e data science. Aggiungere alcune idee sui problemi che ciascuna di queste tecniche è in grado di risolvere. - -## [Quiz post-lezione](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/2/?loc=it) - -## Revisione e Auto Apprendimento - -Per saperne di piÚ su come si puÃ˛ lavorare con gli algoritmi ML nel cloud, si segua questo [percorso di apprendimento](https://docs.microsoft.com/learn/paths/create-no-code-predictive-models-azure-machine-learning/?WT.mc_id=academic-77952-leestott). - -## Compito - -[Tempi di apprendimento brevi](assignment.it.md) diff --git a/1-Introduction/1-intro-to-ML/translations/README.ja.md b/1-Introduction/1-intro-to-ML/translations/README.ja.md deleted file mode 100644 index db0ed50d..00000000 --- a/1-Introduction/1-intro-to-ML/translations/README.ja.md +++ /dev/null @@ -1,105 +0,0 @@ -# 抟æĸ°å­Ļįŋ’へぎ導å…Ĩ - -[![ML, AI, deep learning - 違いはäŊ•ã‹īŧŸ](https://img.youtube.com/vi/lTd9RSxS9ZE/0.jpg)](https://youtu.be/lTd9RSxS9ZE "ML, AI, deep learning - 違いはäŊ•ã‹īŧŸ") - -> đŸŽĨ 上ぎį”ģ像をクãƒĒックすると、抟æĸ°å­Ļįŋ’、AIã€æˇąåą¤å­Ļįŋ’ぎ違いãĢついãĻčĒŦ明した動į”ģãŒčĄ¨į¤ēされぞす。 - -## [Pre-lecture quiz](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/1?loc=ja) - -### イãƒŗãƒˆãƒ­ãƒ€ã‚¯ã‚ˇãƒ§ãƒŗ - -初åŋƒč€…ぎためぎ古典įš„ãĒ抟æĸ°å­Ļįŋ’ぎã‚ŗãƒŧ゚へようこそ! こぎテãƒŧマãĢ全くč§ĻれたことぎãĒã„æ–šã‚‚ã€ã“ãŽåˆ†é‡Žã‚’ãƒ–ãƒŠãƒƒã‚ˇãƒĨã‚ĸップしたいįĩŒé¨“čąŠå¯ŒãĒæ–šã‚‚ã€ãœã˛ã”å‚åŠ ãã ã•ã„ã€‚į§ãŸãĄã¯ã€ã‚ãĒたぎMLぎå­Ļįŋ’ãĢついãĻぎčĻĒしãŋやすい゚ã‚ŋãƒŧト地į‚šã‚’äŊœã‚ŠãŸã„ã¨č€ƒãˆãĻいぞす。あãĒたぎ[フã‚Ŗãƒŧドバック](https://github.com/microsoft/ML-For-Beginners/discussions)ã‚’čŠ•äžĄã—ã€å¯žåŋœã—、取りå…Ĩれることができれば嚸いです。 -[![抟æĸ°å­Ļįŋ’へぎ導å…Ĩ](https://img.youtube.com/vi/h0e2HAPTGF4/0.jpg)](https://youtu.be/h0e2HAPTGF4 "抟æĸ°å­Ļįŋ’へぎ導å…Ĩ") - -> đŸŽĨ 上ぎį”ģ像をクãƒĒックすると、MITぎJohn Guttagが抟æĸ°å­Ļįŋ’ã‚’į´šäģ‹ã™ã‚‹å‹•į”ģãŒčĄ¨į¤ēされぞす。 -### 抟æĸ°å­Ļįŋ’を始めるãĢあたãŖãĻ - -こぎã‚ĢãƒĒキãƒĨナムを始める前ãĢ、ã‚ŗãƒŗピãƒĨãƒŧã‚ŋã‚’č¨­åŽšã—ã€ãƒŽãƒŧトブックをロãƒŧã‚ĢãƒĢã§åŽŸčĄŒã§ãã‚‹ã‚ˆã†ãĢするåŋ…čĻãŒã‚りぞす。 - -- **ã“ãĄã‚‰ãŽãƒ“ãƒ‡ã‚Ēã§ãƒžã‚ˇãƒŗãŽč¨­åŽšã‚’čĄŒãŖãĻください。** ãƒžã‚ˇãƒŗãŽč¨­åŽšæ–šæŗ•ãĢついãĻは、[これらぎビデã‚Ē](https://www.youtube.com/playlist?list=PLlrxD0HtieHhS8VzuMCfQD4uJ9yne1mE6)をごčĻ§ãã ã•ã„。 -- **Pythonをå­Ļįŋ’する。** æœŦčŦ›åē§ã§äŊŋį”¨ã™ã‚‹ã€ãƒ‡ãƒŧã‚ŋã‚ĩイエãƒŗテã‚Ŗ゚トãĢ有į”¨ãĒプログナミãƒŗã‚°č¨€čĒžã§ã‚ã‚‹[Python](https://docs.microsoft.com/learn/paths/python-language/?WT.mc_id=academic-77952-leestott)ぎåŸēæœŦįš„ãĒį†č§Ŗがあることが望ぞしいです。 -- **Node.jsとJavaScriptをå­Ļįŋ’する。** こぎã‚ŗãƒŧ゚ではã‚Ļェブã‚ĸプãƒĒを構į¯‰ã™ã‚‹éš›ãĢJavaScriptもäŊ•åēĻかäŊŋį”¨ã—ぞすぎで、[node](https://nodejs.org)と[npm](https://www.npmjs.com/)がイãƒŗ゚トãƒŧãƒĢされãĻいること、PythonとJavaScriptãŽä¸Ąæ–šãŽé–‹į™ēãĢåŋ…čĻãĒ[Visual Studio Code](https://code.visualstudio.com/)が刊į”¨å¯čƒŊであることがåŋ…čĻã§ã™ã€‚ -- **GitHubぎã‚ĸã‚Ģã‚ĻãƒŗトをäŊœæˆã™ã‚‹ã€‚** [GitHub](https://github.com)でį§ãŸãĄã‚’čĻ‹ã¤ã‘たぎですから、すでãĢã‚ĸã‚Ģã‚Ļãƒŗãƒˆã‚’ãŠæŒãĄã‹ã‚‚ã—ã‚Œãžã›ã‚“ãŒã€ã‚‚ã—ãŠæŒãĄã§ãĒければ、ã‚ĸã‚Ģã‚ĻãƒŗトをäŊœæˆã—ãĻ、こぎã‚ĢãƒĒキãƒĨナムをフりãƒŧクしãĻごč‡Ē分でおäŊŋいください。(ã‚šã‚ŋãƒŧをつけることもおåŋ˜ã‚ŒãĒãđŸ˜Š) -- **Scikit-learnをæŽĸį´ĸする。** こぎãƒŦッ゚ãƒŗで参į…§ã™ã‚‹MLナイブナãƒĒぎã‚ģットである[Scikit-learn]([https://scikit-learn.org/stable/user_guide.html)ãĢæ…ŖれčĻĒしんでください。 - -### 抟æĸ°å­Ļįŋ’とはäŊ•ã‹īŧŸ - -"抟æĸ°å­Ļįŋ’(Machine Learning)"ã¨ã„ã†č¨€č‘‰ã¯ã€įžåœ¨æœ€ã‚‚äēē気があり、é ģįšãĢäŊŋį”¨ã•ã‚ŒãĻã„ã‚‹č¨€č‘‰ãŽä¸€ã¤ã§ã™ã€‚ãŠã‚“ãĒåˆ†é‡ŽãŽæŠ€čĄ“č€…ã§ã‚ãŖãĻも、多少ãĒã‚Šã¨ã‚‚æŠ€čĄ“ãĢį˛žé€šã—ãĻいれば、一åēĻã¯ã“ãŽč¨€č‘‰ã‚’č€ŗãĢしたことがある可čƒŊ性は少ãĒくありぞせん。しかし、抟æĸ°å­Ļįŋ’ぎäģ•įĩ„ãŋは、ãģとんおぎäēēãĢとãŖãĻčŦŽãĢ包ぞれãĻおり、抟æĸ°å­Ļįŋ’ぎ初åŋƒč€…ãĢとãŖãĻ、こぎテãƒŧマは時ãĢ圧倒されるようãĢ感じられぞす。そぎため、抟æĸ°å­Ļįŋ’とはäŊ•ã‹ã‚’原際ãĢį†č§Ŗし、原čˇĩįš„ãĒ䞋を通しãĻæŽĩ階įš„ãĢå­Ļんでいくことが重čĻã§ã™ã€‚ - -![抟æĸ°å­Ļįŋ’ぎäēē気をį¤ēすグナフ](../images/hype.png) - -> Google TrendsãĢよる、「抟æĸ°å­Ļįŋ’ã€ã¨ã„ã†č¨€č‘‰ãŽæœ€čŋ‘ぎį››ã‚Šä¸ŠãŒã‚Šã‚’į¤ēすグナフ。 - -į§ãŸãĄã¯ã€é­…力įš„ãĒčŦŽãĢæē€ãĄãŸåŽ‡åŽ™ãĢäŊã‚“でいぞす。ホãƒŧキãƒŗグ博åŖĢやã‚ĸイãƒŗã‚ˇãƒĨã‚ŋイãƒŗ博åŖĢをはじめとする偉大ãĒį§‘å­Ļč€…ãŸãĄã¯ã€į§ãŸãĄã‚’取りåˇģく世į•ŒãŽčŦŽã‚’č§Ŗき明かす意å‘ŗãŽã‚ã‚‹æƒ…å ąã‚’æŽĸすことãĢäēēį”Ÿã‚’捧げãĻきぞした。äēē間ぎ子䞛は、大äēēãĢãĒるぞでぎ間ãĢ、嚴々新しいことをå­Ļãŗ、č‡Ē分ぎ世į•ŒãŽæ§‹é€ ã‚’明らかãĢしãĻいきぞす。 - -子䞛ぎč„ŗと感čĻšã¯ã€å‘¨å›˛ãŽäē‹åŽŸã‚’čĒč­˜ã—、垐々ãĢäēēį”ŸãŽéš ã‚ŒãŸãƒ‘ã‚ŋãƒŧãƒŗをå­Ļãŗ、å­Ļįŋ’したパã‚ŋãƒŧãƒŗã‚’č­˜åˆĨするためぎčĢ–į†įš„ãĒãƒĢãƒŧãƒĢをäŊœã‚‹ãŽãĢåŊšįĢ‹ãĄãžã™ã€‚こういãŖたå­Ļįŋ’プロã‚ģ゚は、äēē間をこぎ世で最も洗įˇ´ã•ã‚ŒãŸį”Ÿį‰ŠãĢしãĻいぞす。隠れたパã‚ŋãƒŧãƒŗをį™ēčĻ‹ã™ã‚‹ã“とでįļ™įļšįš„ãĢå­Ļįŋ’し、そぎパã‚ŋãƒŧãƒŗãĢåŸēãĨいãĻéŠæ–°ã‚’čĄŒã†ã“ã¨ã§ã€į§ãŸãĄã¯į”Ÿæļ¯ã‚’通じãĻč‡Ē分č‡ĒčēĢã‚’ã‚ˆã‚Šč‰¯ãã—ãĻいくことができぞす。こぎå­Ļįŋ’čƒŊåŠ›ã¨é€˛åŒ–čƒŊ力は、[「č„ŗãŽå¯åĄ‘æ€§ã€](https://www.simplypsychology.org/brain-plasticity.html)とå‘ŧばれるæĻ‚åŋĩãĢé–ĸé€ŖしãĻã„ãžã™ã€‚čĄ¨éĸįš„ãĢは、äēē間ぎč„ŗぎå­Ļįŋ’プロã‚ģ゚と抟æĸ°å­Ļįŋ’ぎã‚ŗãƒŗã‚ģプトãĢは、ãƒĸチベãƒŧã‚ˇãƒ§ãƒŗぎéĸã§ã„ãã¤ã‹ãŽå…ąé€šį‚šãŒã‚りぞす。 - -[äēē間ぎč„ŗ](https://www.livescience.com/29365-human-brain.html)は、įžåŽŸä¸–į•ŒãŽį‰Šäē‹ã‚’įŸĨčĻšã—、įŸĨčĻšã—ãŸæƒ…å ąã‚’å‡Ļį†ã—、合į†įš„ãĒ判断を下し、įŠļæŗãĢåŋœã˜ãĻã‚ã‚‹čĄŒå‹•ã‚’ã—ãžã™ã€‚ã“ã‚Œã¯įŸĨįš„čĄŒå‹•ã¨å‘ŧばれぞす。こぎįŸĨįš„čĄŒå‹•ãŽãƒ—ãƒ­ã‚ģ゚を抟æĸ°ãĢプログナムすることをäēēåˇĨįŸĨčƒŊīŧˆAIīŧ‰ã¨ã„いぞす。 - -ã“ãŽč¨€č‘‰ã¯æˇˇåŒã•ã‚Œã‚‹ã“ã¨ãŒã‚ã‚Šãžã™ãŒã€æŠŸæĸ°å­Ļįŋ’īŧˆMLīŧ‰ã¯äēēåˇĨįŸĨčƒŊぎ重čĻãĒã‚ĩブã‚ģットです。**MLは、į‰šæŽŠãĒã‚ĸãƒĢゴãƒĒã‚ēムをäŊŋį”¨ã—ãĻ、意å‘ŗãŽã‚ã‚‹æƒ…å ąã‚’į™ēčĻ‹ã—、įŸĨčĻšã•ã‚ŒãŸãƒ‡ãƒŧã‚ŋから隠れたパã‚ŋãƒŧãƒŗをčĻ‹ã¤ã‘ãĻ、合į†įš„ãĒ意思æąē厚プロã‚ģã‚šã‚’čŖäģ˜ã‘ることãĢé–ĸäŋ‚しãĻいぞす。** - -![AI, ML, デã‚Ŗãƒŧプナãƒŧニãƒŗグ、デãƒŧã‚ŋã‚ĩイエãƒŗã‚š](../images/ai-ml-ds.png) - - ->[こぎグナフ](https://softwareengineering.stackexchange.com/questions/366996/distinction-between-ai-ml-neural-networks-deep-learning-and-data-mining)ãĢč§Ļį™ēされた[Jen Looper](https://twitter.com/jenlooper)氏ãĢよるイãƒŗフりグナフã‚Ŗック - -## こぎã‚ŗãƒŧ゚でå­Ļãļこと - -こぎã‚ĢãƒĒキãƒĨナムでは、初åŋƒč€…がįŸĨãŖãĻおかãĒければãĒらãĒい抟æĸ°å­Ļįŋ’ぎã‚ŗã‚ĸãĒæĻ‚åŋĩぎãŋを取り上げぞす。į§ãŸãĄãŒã€Œå¤å…¸įš„ãĒ抟æĸ°å­Ļįŋ’」とå‘ŧãļもぎを、多くぎå­Ļį”ŸãŒåŸēį¤Žã‚’å­ĻãļためãĢäŊŋį”¨ã™ã‚‹å„ĒれたナイブナãƒĒであるScikit-learnをä¸ģãĢäŊŋãŖãĻã‚Ģバãƒŧしぞす。äēēåˇĨįŸĨčƒŊã‚„æˇąåą¤å­Ļįŋ’ãĒおぎよりåēƒã„æĻ‚åŋĩをį†č§ŖするためãĢは、抟æĸ°å­Ļįŋ’ぎåŧˇåŠ›ãĒåŸēį¤ŽįŸĨč­˜ãŒä¸å¯æŦ ã§ã™ãŽã§ã€ã“こで提䞛しぞす。 - -- 抟æĸ°å­Ļįŋ’ぎ核とãĒるã‚ŗãƒŗã‚ģプト -- MLãŽæ­´å˛ -- MLとå…Ŧåšŗ性 -- MLãĢよる回帰ぎ手æŗ• -- MLãĢã‚ˆã‚‹åˆ†éĄžæŠ€čĄ“ -- MLãĢよるクナ゚ã‚ŋãƒĒãƒŗグ -- MLãĢよるč‡Ēį„ļ言čĒžå‡Ļį†ãŽæŠ€čĄ“ -- MLãĢよる時įŗģ列äēˆæ¸ŦãŽæŠ€čĄ“ -- åŧˇåŒ–å­Ļįŋ’ -- MLぎįžåŽŸä¸–į•Œã¸ãŽåŋœį”¨ -## こぎã‚ŗãƒŧã‚šã§æ‰ąã‚ãĒいこと - -- デã‚Ŗãƒŧプナãƒŧニãƒŗグ -- ニãƒĨãƒŧナãƒĢネットワãƒŧク -- AI - -ニãƒĨãƒŧナãƒĢネットワãƒŧクやデã‚Ŗãƒŧプナãƒŧニãƒŗグīŧˆãƒ‹ãƒĨãƒŧナãƒĢネットワãƒŧクをį”¨ã„ãŸå¤šåą¤įš„ãĒãƒĸデãƒĢ構į¯‰īŧ‰ã€AIãĒãŠãŽč¤‡é›‘ãĒåˆ†é‡Žã¯ã€ã‚ˆã‚Šč‰¯ã„å­Ļįŋ’į’°åĸƒã‚’提䞛するためãĢéŋけãĻいぞすが、これらはåˆĨぎã‚ĢãƒĒキãƒĨナムで取り上げぞす。ぞた、それらぎ大きãĒ分野ぎ中でもį‰šãĢデãƒŧã‚ŋã‚ĩイエãƒŗã‚šãĢį„Ļį‚šã‚’åŊ“ãĻたã‚ĢãƒĒキãƒĨナムを提䞛するäēˆåŽšã§ã™ã€‚ -## ãĒぜ抟æĸ°å­Ļįŋ’ã‚’å­Ļãļぎか - -抟æĸ°å­Ļįŋ’ã¨ã¯ã€ã‚ˇã‚šãƒ†ãƒ ãŽčĻŗį‚šã‹ã‚‰ã€ãƒ‡ãƒŧã‚ŋから隠れたパã‚ŋãƒŧãƒŗをå­Ļįŋ’し、įŸĨįš„ãĒ意思æąē厚を支援するč‡Ēå‹•åŒ–ã•ã‚ŒãŸã‚ˇã‚šãƒ†ãƒ ã‚’æ§‹į¯‰ã™ã‚‹ã“とと厚įžŠã•ã‚Œãžã™ã€‚ - -こぎ動抟は、äēē間ぎč„ŗが外į•Œã‹ã‚‰čĒč­˜ã—たデãƒŧã‚ŋãĢåŸēãĨいãĻį‰šåŽšãŽäē‹æŸ„ã‚’å­Ļįŋ’するäģ•įĩ„ãŋãĢ、ゆるやかãĢイãƒŗ゚パイã‚ĸされãĻいぞす。 - -✅ ãĒぜビジネ゚では、ハãƒŧドã‚ŗãƒŧドされたãƒĢãƒŧãƒĢベãƒŧ゚ぎエãƒŗジãƒŗをäŊœã‚‹ãŽã§ã¯ãĒく、抟æĸ°å­Ļįŋ’æˆĻį•ĨをäŊŋãŖãĻãŋã‚ˆã†ã¨æ€ã†ãŽã‹ã€ãĄã‚‡ãŖã¨č€ƒãˆãĻãŋãĻください。 - - -### 抟æĸ°å­Ļįŋ’ぎåŋœį”¨ - -抟æĸ°å­Ļįŋ’ぎã‚ĸプãƒĒã‚ąãƒŧã‚ˇãƒ§ãƒŗは、äģŠã‚„ãģとんおおこãĢでもあり、゚マãƒŧトフりãƒŗやã‚ŗネクテッドデバイ゚、そぎäģ–ãŽã‚ˇã‚šãƒ†ãƒ ã‹ã‚‰į”Ÿæˆã•ã‚Œã€į§ãŸãĄãŽį¤žäŧšãĢæĩã‚ŒãĻいるデãƒŧã‚ŋと同様ãĢありãĩれたもぎとãĒãŖãĻいぞす。最先įĢ¯ãŽæŠŸæĸ°å­Ļįŋ’ã‚ĸãƒĢゴãƒĒã‚ēãƒ ãŽč¨ˆã‚ŠįŸĨれãĒい可čƒŊæ€§ã‚’č€ƒæ…Žã—ãĻ、į ”įŠļč€…ãŸãĄã¯ã€å¤šæŦĄå…ƒįš„ãƒģ多分野įš„ãĒįžåŽŸãŽå•éĄŒã‚’č§ŖæąēするためãĢそぎčƒŊ力をæŽĸæą‚ã—ã€éžå¸¸ãĢč‰¯ã„įĩæžœã‚’åž—ãĻいぞす。 - -**抟æĸ°å­Ļįŋ’は様々ãĒåŊĸで刊į”¨ã§ããžã™**: - -- æ‚Ŗč€…ãŽį—…æ­´ã‚„å ąå‘Šæ›¸ã‹ã‚‰į—…気ぎ可čƒŊ性をäēˆæ¸Ŧする。 -- æ°—čąĄãƒ‡ãƒŧã‚ŋをæ´ģį”¨ã—ãĻæ°—čąĄįžčąĄã‚’äēˆæ¸Ŧする。 -- 文įĢ ãŽæ„Ÿæƒ…ã‚’į†č§Ŗする。 -- プロパã‚Ŧãƒŗãƒ€ãŽæ‹Ąæ•Ŗã‚’é˜˛ããŸã‚ãĢフェイクニãƒĨãƒŧ゚を検å‡ēする。 - -é‡‘čžã€įĩŒæ¸ˆã€åœ°įƒį§‘å­Ļ、厇厙開į™ē、į”Ÿį‰ŠåŒģå­ĻåˇĨå­Ļ、čĒįŸĨį§‘å­Ļ、さらãĢは文į§‘įŗģぎ分野でも、それぞれぎ分野ぎデãƒŧã‚ŋå‡Ļį†ãĢäŧ´ã†å›°é›ŖãĒå•éĄŒã‚’č§ŖæąēするためãĢ、抟æĸ°å­Ļįŋ’ãŒæŽĄį”¨ã•ã‚ŒãĻいぞす。 - -抟æĸ°å­Ļįŋ’は、原世į•ŒãŽãƒ‡ãƒŧã‚ŋやį”Ÿæˆã•ã‚ŒãŸãƒ‡ãƒŧã‚ŋから意å‘ŗぎある洞察をčĻ‹å‡ēし、パã‚ŋãƒŧãƒŗをį™ēčĻ‹ã™ã‚‹ãƒ—ロã‚ģã‚šã‚’č‡Ē動化しぞす。抟æĸ°å­Ļįŋ’は、ビジネ゚、åĨåēˇã€é‡‘辍ãĒおぎ分野で非常ãĢ有į”¨ã§ã‚ることがč¨ŧ明されãĻいぞす。 - -čŋ‘い将æĨ、抟æĸ°å­Ļįŋ’ぎåŸēį¤Žã‚’į†č§Ŗすることは、抟æĸ°å­Ļįŋ’ぎ晎及ãĢäŧ´ã„、あらゆる分野ぎäēē々ãĢとãŖãĻåŋ…須ぎもぎとãĒるでしょう。 - ---- -## 🚀 Challenge -AI、MLã€æˇąåą¤å­Ļįŋ’、デãƒŧã‚ŋã‚ĩイエãƒŗ゚ぎ違いãĢついãĻį†č§ŖしãĻいることを、į´™ã‚„[Excalidraw](https://excalidraw.com/)ãĒおぎã‚Ēãƒŗナイãƒŗã‚ĸプãƒĒをäŊŋãŖãĻã‚šã‚ąãƒƒãƒã—ãĻãã ã•ã„ã€‚ãžãŸã€ãã‚Œãžã‚ŒãŽæŠ€čĄ“ãŒåž—æ„ã¨ã™ã‚‹å•éĄŒãŽã‚ĸイデã‚ĸを加えãĻãŋãĻください。 - -## [Post-lecture quiz](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/2?loc=ja) - -## 振りčŋ”りとč‡Ēįŋ’ - -クナã‚Ļド上でMLã‚ĸãƒĢゴãƒĒã‚ēムをおぎようãĢæ‰ąã†ã“ã¨ãŒã§ãã‚‹ã‹ãĢついãĻは、こぎ[ナãƒŧニãƒŗグパ゚](https://docs.microsoft.com/learn/paths/create-no-code-predictive-models-azure-machine-learning/?WT.mc_id=academic-77952-leestott)ãĢåž“ãŖãĻください。 - -## čĒ˛éĄŒ - -[į¨ŧ働させる](assignment.ja.md) diff --git a/1-Introduction/1-intro-to-ML/translations/README.ko.md b/1-Introduction/1-intro-to-ML/translations/README.ko.md deleted file mode 100644 index eb9757d3..00000000 --- a/1-Introduction/1-intro-to-ML/translations/README.ko.md +++ /dev/null @@ -1,113 +0,0 @@ -# 머ė‹ ëŸŦ닝 ė†Œę°œ - -[![ML, AI, deep learning - What's the difference?](https://img.youtube.com/vi/lTd9RSxS9ZE/0.jpg)](https://youtu.be/lTd9RSxS9ZE "ML, AI, deep learning - What's the difference?") - -> đŸŽĨ 머ė‹ ëŸŦ닝, AI ꡸ëĻŦęŗ  ë”ĨëŸŦ닝ė˜ ė°¨ė´ëĨŧ ė„¤ëĒ…하는 ė˜ėƒė„ ëŗ´ë ¤ëŠ´ ėœ„ ė´ë¯¸ė§€ëĨŧ 클ëĻ­í•Šë‹ˆë‹¤. - -## [강ė˜ ė „ 퀴ėĻˆ](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/1/) - -### ė†Œę°œ - -ėž…ëŦ¸ėžëĨŧ ėœ„í•œ classical 머ė‹ ëŸŦ닝 ėŊ”ėŠ¤ė— ė˜¤ė‹  것ė„ 환ė˜í•Šë‹ˆë‹¤! ė´ 토í”Ŋė— ė™„ë˛Ŋ하게 ėƒˆëĄœ ė ‘í•´ëŗ´ęą°ë‚˜, 한 ëļ„ė•ŧė— ė™„ë˛Ŋ해ė§€ęŗ  ė‹ļė–´í•˜ëŠ” ML ė‹¤ëŦ´ėžë„ ė €íŦė™€ 함ęģ˜í•˜ę˛Œ 되늴 ėĸ‹ėŠĩ니다! ML ė—°ęĩŦëĨŧ ėœ„í•œ ėšœėˆ™í•œ ė‹œėž‘ė ė„ 만들ęŗ  ė‹ļęŗ , 당ė‹ ė˜ [feedback](https://github.com/microsoft/ML-For-Beginners/discussions)ė„ 평가, ė‘ë‹ĩ하ęŗ  반ė˜í•˜ę˛ ėŠĩ니다. - -[![Introduction to ML](https://img.youtube.com/vi/h0e2HAPTGF4/0.jpg)](https://youtu.be/h0e2HAPTGF4 "Introduction to ML") - -> đŸŽĨ 동ė˜ėƒė„ ëŗ´ë ¤ëŠ´ ėœ„ ė´ë¯¸ė§€ 클ëĻ­: MITė˜ John Guttag가 머ė‹ ëŸŦ닝ė„ ė†Œę°œí•Šë‹ˆë‹¤. -### 머ė‹ ëŸŦ닝 ė‹œėž‘í•˜ę¸° - -ė´ ėģ¤ëĻŦ큘ëŸŧė„ ė‹œėž‘í•˜ę¸° ė „, ėģ´í“¨í„°ëĨŧ ė„¸íŒ…하ęŗ  노트ëļė„ 로ėģŦė—ė„œ ė‹¤í–‰í•  ėˆ˜ ėžˆę˛Œ ė¤€ëš„í•´ė•ŧ 합니다. - -- **ė´ ė˜ėƒėœŧ로 ėģ´í“¨í„° ė„¸íŒ…í•˜ę¸°**. [ė˜ėƒ 플레ė´ëĻŦėŠ¤íŠ¸](https://www.youtube.com/playlist?list=PLlrxD0HtieHhS8VzuMCfQD4uJ9yne1mE6)ė—ė„œ ėģ´í“¨í„°ëĨŧ ė„¸íŒ…하는 방법ė— 대하ė—Ŧ ėžė„¸ížˆ ė•Œė•„봅니다. -- **Python ë°°ėš°ę¸°**. ė´ ėŊ”ėŠ¤ė—ė„œ ė‚ŦėšŠí•  데ė´í„° ė‚Ŧė´ė–¸í‹°ėŠ¤íŠ¸ė—ę˛Œ ėœ ėšŠí•œ 프로그래밍 ė–¸ė–´ė¸ [Python](https://docs.microsoft.com/learn/paths/python-language/?WT.mc_id=academic-77952-leestott)ė— 대한 기ëŗ¸ė ė¸ ė´í•´ëĨŧ 해ė•ŧ ėĸ‹ėŠĩ니다. -- **Node.js ė™€ JavaScript ë°°ėš°ę¸°**. ė´ ėŊ”ėŠ¤ė—ė„œ ė›šė•ąė„ 빌드할 때 JavaScriptëĨŧ ė‚ŦėšŠí•˜ë¯€ëĄœ, [node](https://nodejs.org) ė™€ [npm](https://www.npmjs.com/)ė„ ė„¤ėš˜í•´ė•ŧ 합니다. Python ęŗŧ JavaScriptė˜ 개발환ę˛Ŋ ëĒ¨ë‘ ė“¸ ėˆ˜ ėžˆëŠ” [Visual Studio Code](https://code.visualstudio.com/)도 ėžˆėŠĩ니다. -- **GitHub ęŗ„ė • 만들기**. [GitHub](https://github.com) ęŗ„ė •ė´ 혚ė‹œ ė—†ë‹¤ëŠ´, ęŗ„ė •ė„ 만든 뒤ė— ė´ ėģ¤ëĻŦ큘ëŸŧė„ íŦíŦ해ė„œ 개ė¸ė— 맞게 ė“¸ ėˆ˜ ėžˆėŠĩ니다. (star 하ė…”도 됩니다 😊) -- **Scikit-learn ė°žė•„ëŗ´ę¸°**. ė´ 강ė˜ė—ė„œ ė°¸ėĄ°í•˜ęŗ  ėžˆëŠ” ML ëŧė´ë¸ŒëŸŦëĻŦ ė…‹ė¸ [Scikit-learn](https://scikit-learn.org/stable/user_guide.html)ė„ ėˆ™ė§€í•Šë‹ˆë‹¤. - -### 머ė‹ ëŸŦ닝ė€ ëŦ´ė—‡ė¸ę°€ėš”? - -'머ė‹ ëŸŦ닝'ė€ ėĩœęˇŧ 가ėžĨ ė¸ę¸°ėžˆęŗ  ėžėŖŧ ė–¸ę¸‰ë˜ëŠ” ėšŠė–´ėž…니다. ė–´ë–¤ ëļ„ė•ŧ든 기ėˆ ė— ė–´ëŠ ė •ë„ ėĩėˆ™í•´ė§€ëŠ´ ė´ëŸŦ한 ėšŠė–´ëĨŧ 한 번ėĻˆėŒ 들ė–´ëŗ¸ ė ė´ ėžˆė—ˆė„ 것ėž…니다. ꡸ëŸŦ나, 머ė‹ ëŸŦ닝ė˜ ęĩŦėĄ°ëŠ” 대ëļ€ëļ„ė˜ ė‚Ŧ람들ė—ę˛ 미ėŠ¤í…ŒëĻŦėž…니다. 머ė‹ ëŸŦ닝 ėž…ëŦ¸ėžė—ę˛ ėŖŧė œę°€ 때때로 ėˆ¨ë§‰íž ėˆ˜ ėžˆėŠĩ니다. 때ëŦ¸ė— 머ė‹ ëŸŦ닝ė´ ė‹¤ė œëĄœ ė–´ë–¤ė§€ ė´í•´í•˜ęŗ  ė‹¤ė œ ė ėšŠëœ ė˜ˆė‹œëĄœ 단ęŗ„ëŗ„ 학ėŠĩė„ ė§„행하는 것ė´ ė¤‘ėš”핊니다. - -![ml hype curve](../images/hype.png) - -> Google Trendsė˜ '머ė‹ ëŸŦ닝' ėšŠė–´ė˜ ėĩœęˇŧ 'hype curve' ėž…니다. - -ėš°ëĻŦ는 매ėš° ė‹ ëš„í•œ ėš°ėŖŧė— ė‚´ęŗ  ėžˆėŠĩ니다. Stephen Hawking, Albert Einsteinęŗŧ 같ė€ ėœ„대한 ęŗŧ학ėžë“¤ė€ ėŖŧëŗ€ ė„¸ęŗ„ė˜ ė‹ ëš„ëĨŧ 밝혀ë‚ŧ ė˜ë¯¸ėžˆëŠ” ė •ëŗ´ëĨŧ ė°žëŠ” 데 ėŧėƒė„ 바ėŗ¤ėŠĩ니다. ė´ęą´ ė‚Ŧ람ė˜ 학ėŠĩ ėĄ°ęą´ė´ėŖ . ė•„ė´ëŠ” ė„ąė¸ė´ 되늴ė„œ 해마다 ėƒˆëĄœėš´ 것ė„ ë°°ėš°ęŗ  ė„¸ęŗ„ė˜ ęĩŦėĄ°ë“¤ė„ 발ę˛Ŧ합니다. - -ė•„ė´ė˜ 뇌ė™€ 감각ė€ ėŖŧëŗ€ 환ę˛Ŋė˜ ė‚Ŧė‹¤ë“¤ė„ ė¸ė§€í•˜ęŗ  학ėŠĩ된 패턴ė„ ė‹ëŗ„í•˜ę¸° ėœ„í•œ ë…ŧëĻŦė ė¸ 규ėš™ė„ 만드는 패턴ė„ ė ė°¨ė ėœŧ로 ë°°ė›ë‹ˆë‹¤. ė¸ę°„ė˜ 두뇌ė˜ 학ėŠĩ ęŗŧė •ė€ ė¸ę°„ė„ ė„¸ėƒė—ė„œ 가ėžĨ ė •ęĩí•œ ėƒëĒ…ė˛´ëĄœ 만듭니다. ėˆ¨ę˛¨ė§„ 패턴ė„ 발ę˛Ŧ하ęŗ  ꡸ 패턴ė„ 혁ė‹ í•¨ėœŧ로ė¨ ė§€ė†ė ėœŧ로 학ėŠĩ하는 것ė€ ėš°ëĻŦ가 ėŧėƒ 동ė•ˆ ė ė  더 나ė€ ėžė‹ ė„ 만들 ėˆ˜ ėžˆę˛Œ 해ė¤ë‹ˆë‹¤. ė´ëŸŦ한 학ėŠĩ ëŠĨë Ĩęŗŧ 발ė „하는 ëŠĨë Ĩė€ [brain plasticity 뇌ė˜ 가ė†Œė„ą](https://www.simplypsychology.org/brain-plasticity.html)ė´ëŧęŗ  ëļˆëĻŦ는 개념ęŗŧ 관련ė´ ėžˆėŠĩ니다. í”ŧėƒė ėœŧ로, ėš°ëĻŦ는 ė¸ę°„ė˜ 두뇌ė˜ 학ėŠĩ ęŗŧė •ęŗŧ 기ęŗ„ 학ėŠĩė˜ 개념 ė‚Ŧė´ė— 동기ëļ€ė—Ŧė˜ ėœ ė‚Ŧė„ąė„ 끌ė–´ë‚ŧ ėˆ˜ ėžˆėŠĩ니다. - -[ė¸ę°„ė˜ 뇌](https://www.livescience.com/29365-human-brain.html)는 현ė‹¤ ė„¸ęŗ„ė˜ 것들ė„ ė¸ė‹í•˜ęŗ , ė¸ė‹ëœ ė •ëŗ´ëĨŧ ė˛˜ëĻŦ하ęŗ , 합ëĻŦė ė¸ 결ė •ė„ 내ëĻŦęŗ , ėƒí™Šė— 따ëŧ 특ė •í•œ 행동ė„ 합니다. ė´ę˛ƒė´ ėš°ëĻŦ가 ė§€ė  행동ė´ëŧęŗ  ëļ€ëĨ´ëŠ” 것ėž…니다. ėš°ëĻŦ가 ė§€ëŠĨė ė¸ 행동 ęŗŧė •ė˜ 팩ė‹œë°€ëĻŦëĨŧ 기ęŗ„ė— 프로그래밍 할 때, ꡸것ė€ ė¸ęŗĩė§€ëŠĨ(AI)ė´ëŧęŗ  ëļˆëĻŊ니다. - -ėšŠė–´ę°€ 헷갈ëĻ´ ėˆ˜ ėžˆė§€ë§Œ, 머ė‹ ëŸŦ닝(ML)ė€ ė¤‘ėš”í•œ ė¸ęŗĩ ė§€ëŠĨė˜ 한 ëļ€ëļ„ėž…니다. **MLė€ 특ėˆ˜í•œ ė•Œęŗ ëĻŦėĻ˜ė„ ė¨ė„œ ė˜ë¯¸ėžˆëŠ” ė •ëŗ´ëĨŧ ė°žęŗ  ė¸ė‹í•œ 데ė´í„°ė—ė„œ ėˆ¨ę˛¨ė§„ 패턴ė„ ė°žė•„ 합ëĻŦė ėœŧ로 판단할 프로ė„¸ėŠ¤ëĨŧ 확ė‹¤í•˜ę˛Œ ėˆ˜í–‰í•˜ëŠ” 것ė— ė§‘ė¤‘하ęŗ  ėžˆë‹¤ęŗ  할 ėˆ˜ ėžˆėŠĩ니다**. - -![AI, ML, deep learning, data science](../images/ai-ml-ds.png) - -> AI, ML, ë”ĨëŸŦ닝, ꡸ëĻŦęŗ  데ė´í„° ė‚Ŧė´ė–¸í‹°ėŠ¤ 간ė˜ 관ęŗ„ëĨŧ ëŗ´ė—ŦėŖŧ는 다ė´ė–´ęˇ¸ëž¨. [ė´ęŗŗ](https://softwareengineering.stackexchange.com/questions/366996/distinction-between-ai-ml-neural-networks-deep-learning-and-data-mining)ė—ė„œ ė˜ę°ė„ 받ė€ [Jen Looper](https://twitter.com/jenlooper)ė˜ ė¸íŦ그래í”Ŋ - -## ė´ ėŊ”ėŠ¤ė—ė„œ ë°°ėš¸ ėģ¨ė…‰ë“¤ - -ė´ ėģ¤ëĻŦ큘ëŸŧė—ė„œëŠ” ėž…ëŦ¸ėžę°€ 반드ė‹œ ė•Œė•„ė•ŧ 할 머ė‹ ëŸŦ닝ė˜ í•ĩė‹Ŧė ė¸ 개념만 다ëŖ° 것ėž…니다. 많ė€ 학ėƒë“¤ė´ 기ė´ˆëĨŧ ë°°ėš°ę¸° ėœ„í•´ ė‚ŦėšŠí•˜ëŠ” 훌ëĨ­í•œ ëŧė´ë¸ŒëŸŦëĻŦė¸, Scikit-learnėœŧ로 'classical machine learning'ė´ëŧęŗ  ëļ€ëĨ´ëŠ” 것ė„ 다ëŖšë‹ˆë‹¤. ė¸ęŗĩ ė§€ëŠĨ 또는 ë”ĨëŸŦ닝ė˜ 대ëžĩė ė¸ 개념ė„ ė´í•´í•˜ë ¤ëŠ´ 머ė‹ ëŸŦ닝ė— 대한 강ë Ĩ한 기ė´ˆ ė§€ė‹ė´ ęŧ­ 필ėš”í•˜ë¯€ëĄœ, 해당 내ėšŠė„ ëŗ¸ 강ė˜ė—ė„œ ė œęŗĩ하ęŗ ėž 합니다. - -## ė´ ėŊ”ėŠ¤ė—ė„œ 다ëŖ¨ëŠ” 것: - -- 머ė‹ ëŸŦ닝ė˜ í•ĩė‹Ŧ ėģ¨ė…‰ -- ML ė˜ ė—­ė‚Ŧ -- ML ęŗŧ ęŗĩė •ė„ą -- regression ML 기ėˆ  -- classification ML 기ėˆ  -- clustering ML 기ėˆ  -- natural language processing ML 기ėˆ  -- time series forecasting ML 기ėˆ  -- 강화 학ėŠĩ -- real-world ė• í”ŒëĻŦėŧ€ė´ė…˜ for ML - -## 다ëŖ¨ė§€ ė•ŠëŠ” 것: - -- ë”ĨëŸŦ닝 -- ė‹ ę˛Ŋ망 -- AI - -ėš°ëĻŦ는 더 나ė€ 학ėŠĩ ę˛Ŋ험ė„ 만들기 ėœ„í•´ ëŗ¸ ėŊ”ėŠ¤ė—ė„œëŠ” ė‹ ę˛Ŋ망, ė‹ ę˛Ŋ망ė„ ė´ėšŠí•œ 다ė¸ĩ ëĒ¨ë¸ ęĩŦėļ•ė¸ 'ë”ĨëŸŦ닝', ꡸ëĻŦęŗ  AI는 ë…ŧė˜í•˜ė§€ ė•Šė„ 것ėž…니다. 또한, 더 큰 필드ė— ė´ˆė ė„ 맞ėļ”기 ėœ„하ė—Ŧ í–Ĩ후 데ė´í„° ė‚Ŧė´ė–¸ėŠ¤ ėģ¤ëĻŦ큘ëŸŧė„ ė œęŗĩ할 ė˜ˆė •ėž…니다. - -## ė™œ 머ė‹ ëŸŦ닝ė„ ë°°ėš°ë‚˜ėš”? - -ė‹œėŠ¤í…œ 관ė ė—ė„œ 머ė‹ ëŸŦ닝ė€ 데ė´í„°ė˜ ėˆ¨ę˛¨ė§„ 패턴ė„ 학ėŠĩ하ė—Ŧ 현ëĒ…í•œ ė˜ė‚Ŧ결ė •ė„ ė§€ė›í•˜ëŠ” ėžë™í™”된 ė‹œėŠ¤í…œė„ 만드는 것ėœŧ로 ė •ė˜ëŠë‹ˆë‹¤. - -ė´ę˛ƒė€ ė¸ę°„ė˜ 두뇌가 ė™¸ëļ€ëĄœëļ€í„° ė¸ė§€í•˜ëŠ” 데ė´í„°ëĨŧ 바탕ėœŧ로 ė–´ë–ģ게 특ė •í•œ 것들ė„ ë°°ėš°ëŠ”ė§€ė— ė˜í•´ ė–´ëŠ ė •ë„ ė˜ę°ė„ 받ė•˜ėŠĩ니다. - -✅ 하드 ėŊ”딊된 규ėš™ 기반 ė—”ė§„ė„ 만드는 것ëŗ´ë‹¤ 기ęŗ„ 학ėŠĩ ė „ëžĩė„ ė‚ŦėšŠí•˜ëŠ” ė´ėœ ëĨŧ ėž ė‹œ ėƒę°í•´ 봅ė‹œë‹¤. - -### 머ė‹ ëŸŦ닝ė˜ ė• í”ŒëĻŦėŧ€ė´ė…˜ - -머ė‹ ëŸŦ닝ė˜ ė‘ėšŠė€ ė´ė œ ęą°ė˜ ëĒ¨ë“  ęŗŗė— ėžˆėœŧ늰, ėš°ëĻŦė˜ ėŠ¤ë§ˆíŠ¸í°, ė—°ę˛°ëœ 기기, ꡸ëĻŦęŗ  다ëĨ¸ ė‹œėŠ¤í…œë“¤ė— ė˜í•´ ėƒė„ąëœ ėš°ëĻŦ ė‚Ŧ회ė˜ 방대한 데ė´í„°ë§Œíŧ ė–´ë””ė—ë‚˜ ėĄ´ėžŦ합니다. ėĩœė˛¨ë‹¨ 머ė‹ ëŸŦ닝 ė•Œęŗ ëĻŦėĻ˜ė˜ ė—„ė˛­ë‚œ ėž ėžŦë Ĩė„ ęŗ ë ¤í•˜ė—Ŧ ė—°ęĩŦė›ë“¤ė€ 다ė°¨ė›ė ė´ęŗ  다ëļ„ė•ŧė ė¸ ė‹¤ė œ ëŦ¸ė œëĨŧ 큰 긍ė •ė ė¸ 결ęŗŧ로 해결할 ėˆ˜ ėžˆëŠ” ëŠĨë Ĩė„ 탐ęĩŦ하ęŗ  ėžˆėŠĩ니다. - -**다ė–‘í•œ ë°Šė‹ėœŧ로 머ė‹ ëŸŦ닝ė„ ė‚ŦėšŠí•  ėˆ˜ ėžˆėŠĩ니다**: - -- 환ėžė˜ ëŗ‘ë Ĩė´ë‚˜ ëŗ´ęŗ ė„œëĨŧ 기반ėœŧ로 ė§ˆëŗ‘ 가ëŠĨė„ąė„ ė˜ˆė¸Ąí•Šë‹ˆë‹¤. -- 날ė”¨ 데ė´í„°ëĄœ ęŗ„ė ˆ ė´ë˛¤íŠ¸ëĨŧ ė˜ˆė¸Ąí•Šë‹ˆë‹¤. -- ëŦ¸ėžĨė˜ 감ė •ė„ ė´í•´í•Šë‹ˆë‹¤. -- 가ė§œ 뉴ėŠ¤ëĨŧ 감ė§€í•˜ęŗ  ė„ ë™ė„ 막ėŠĩ니다. - -금ėœĩ, ę˛Ŋė œí•™, ė§€ęĩŦ ęŗŧ학, ėš°ėŖŧ 탐험, ėƒëŦŧ ęŗĩ학, ė¸ė§€ ęŗŧ학, ꡸ëĻŦęŗ  ė¸ëŦ¸í•™ęšŒė§€ 머ė‹ ëŸŦ닝ė„ ė ėšŠí•˜ė—Ŧ ė–´ë ĩęŗ , 데ė´í„° ė˛˜ëĻŦ가 버거ėš´ ė´ėŠˆëĨŧ 해결했ėŠĩ니다. - -**결률**: - -머ė‹ ëŸŦ닝ė€ ė‹¤ė œ 또는 ėƒė„ąëœ 데ė´í„°ė—ė„œ ė˜ë¯¸ ėžˆëŠ” 패턴ė„ ė°žëŠ” 프로ė„¸ėŠ¤ëĨŧ ėžë™í™”핊니다. ëŦ´ė—‡ëŗ´ë‹¤ë„ 비ėĻˆë‹ˆėŠ¤, 건강 및 ėžŦëŦ´ ė• í”ŒëĻŦėŧ€ė´ė…˜ė—ė„œ 높ė€ 가ėš˜ëĨŧ ė§€ë‹Œë‹¤ëŠ” 것ė´ ėž…ėĻë˜ė—ˆėŠĩ니다. - -가까ėš´ 미래ė—, 머ė‹ ëŸŦ닝ė˜ 광범ėœ„í•œ ėą„택ėœŧ로 ëĒ¨ë“  ëļ„ė•ŧė˜ ė‚Ŧ람들ė´ 머ė‹ ëŸŦ닝ė˜ 기ëŗ¸ė„ ė´í•´í•˜ëŠ” 것ė´ 필ėˆ˜ė ė´ 될 것ėž…니다. - ---- -## 🚀 도ė „ - -ėĸ…ė´ė— ꡸ëĻŦ거나, [Excalidraw](https://excalidraw.com/)ė˛˜ëŸŧ ė˜¨ëŧė¸ ė•ąė„ ė´ėšŠí•˜ė—Ŧ AI, ML, ë”ĨëŸŦ닝, ꡸ëĻŦęŗ  데ė´í„° ė‚Ŧė´ė–¸ėŠ¤ė˜ ė°¨ė´ëĨŧ ė´í•´í•Šė‹œë‹¤. 각 기ėˆ ë“¤ė´ ėž˜ 해결할 ėˆ˜ ėžˆëŠ” ëŦ¸ė œė— 대해 ė•„ė´ë””ė–´ëĨŧ 합ėŗëŗ´ė„¸ėš”. - -## [강ė˜ 후 퀴ėĻˆ](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/2/) - -## ëĻŦ롰 & ėžę¸°ėŖŧ도 학ėŠĩ - -클ëŧėš°ë“œė—ė„œ ML ė•Œęŗ ëĻŦėĻ˜ė„ ė–´ë–ģ게 ė‚ŦėšŠí•˜ëŠ” ė§€ ėžė„¸ížˆ ė•Œė•„ëŗ´ë ¤ëŠ´, [학ėŠĩ ę˛Ŋ로](https://docs.microsoft.com/learn/paths/create-no-code-predictive-models-azure-machine-learning/?WT.mc_id=academic-77952-leestott)ëĨŧ 따ëĻ…니다. - -MLė˜ 기ė´ˆė— 대한 [학ėŠĩ ę˛Ŋ로](https://docs.microsoft.com/learn/modules/introduction-to-machine-learning/?WT.mc_id=academic-77952-leestott)ëĨŧ 봅니다. - -## ęŗŧė œ - -[Get up and running](../assignment.md) diff --git a/1-Introduction/1-intro-to-ML/translations/README.pt-br.md b/1-Introduction/1-intro-to-ML/translations/README.pt-br.md deleted file mode 100644 index 9b5f94c0..00000000 --- a/1-Introduction/1-intro-to-ML/translations/README.pt-br.md +++ /dev/null @@ -1,113 +0,0 @@ -# IntroduçÃŖo ao machine learning - -[![ML, AI, deep learning - Qual Ê a diferença?](https://img.youtube.com/vi/lTd9RSxS9ZE/0.jpg)](https://youtu.be/lTd9RSxS9ZE "ML, AI, deep learning - Qual Ê a diferença?") - -> đŸŽĨ Clique na imagem acima para assistir um vídeo que ilustra a diferença entre machine learning, AI, e deep learning. - -## [QuestionÃĄrio inicial](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/1?loc=ptbr) - -### IntroduçÃŖo - -Nossas boas vindas a este curso de machine learning clÃĄssico para iniciantes! Quer vocÃĒ seja completamente novo neste tÃŗpico, ou um praticante de ML experiente que esteja procurando se atualizar em uma ÃĄrea, estamos felizes por vocÃĒ se juntar a nÃŗs! Queremos criar um ponto de lançamento amigÃĄvel para seu estudo de ML e ficaríamos felizes em avaliar, responder e incorporar o seu [feedback](https://github.com/microsoft/ML-For-Beginners/discussions). - -[![IntroduçÃŖo ao ML](https://img.youtube.com/vi/h0e2HAPTGF4/0.jpg)](https://youtu.be/h0e2HAPTGF4 "IntroduçÃŖo ao ML") - -> đŸŽĨ Clique na imagem acima para assistir: John Guttag, do MIT, apresenta o machine learning. - -### Primeiros passos com machine learning - -Antes de iniciar este curso, vocÃĒ precisa ter seu computador configurado e pronto para executar notebooks localmente. - -- **Configure sua mÃĄquina com estes vídeos**. Use os links a seguir para aprender [como instalar o Python](https://youtu.be/CXZYvNRIAKM) em seu sistema e [configurar um editor de texto](https://youtu.be/EU8eayHWoZg) para desenvolvimento. -- **Aprenda Python**. TambÊm Ê recomendÃĄvel ter um conhecimento bÃĄsico de [Python](https://docs.microsoft.com/learn/paths/python-language/?WT.mc_id=academic-77952-leestott), uma linguagem de programaçÃŖo Ãētil para cientistas de dados (data scientists) que usamos neste curso. -- **Aprenda Node.js e JavaScript**. TambÊm usamos JavaScript algumas vezes neste curso para criar aplicativos web, entÃŖo vocÃĒ precisarÃĄ ter [node](https://nodejs.org) e [npm](https://www.npmjs.com/) instalado, assim como o [Visual Studio Code](https://code.visualstudio.com/) disponível para desenvolvimento em Python e JavaScript. -- **Crie uma conta no GitHub**. Como vocÃĒ nos encontrou aqui no [GitHub](https://github.com),talvez vocÃĒ jÃĄ tenha uma conta, mas se nÃŖo, crie uma e faça um fork deste curso para usar por conta prÃŗpria. (Sinta-se à vontade para nos dar uma estrela tambÊm 😊). -- **Explore o Scikit-learn**. Familiarize-se com o [Scikit-learn](https://scikit-learn.org/stable/user_guide.html), um conjunto de bibliotecas de ML referenciadas nestas liçÃĩes. - -### O que Ê machine learning? - -O termo 'machine learning' Ê um dos termos mais populares e usados ​​atualmente. HÃĄ uma boa chance de vocÃĒ jÃĄ ter ouvido esse termo pelo menos uma vez se estiver familiarizado com tecnologia, independentemente do campo em que trabalha. A mecÃĸnica do aprendizado de mÃĄquina (machine learning), entretanto, Ê um mistÊrio para a maioria das pessoas. Para um iniciante em machine learning, o assunto às vezes pode parecer opressor. Portanto, Ê importante entender o que realmente Ê o machine learning e aprender sobre isso passo a passo, por meio de exemplos prÃĄticos. - -![curva de hype de ml](../images/hype.png) - -> Google Trends mostra a recente 'curva de hype' do termo 'machine learning'. - -Vivemos em um universo cheio de mistÊrios fascinantes. Grandes cientistas como Stephen Hawking, Albert Einstein e muitos outros dedicaram suas vidas à busca de informaçÃĩes significativas que desvendam os mistÊrios do mundo ao nosso redor. Esta Ê a condiçÃŖo humana de aprendizagem: uma criança humana aprende coisas novas e descobre a estrutura de seu mundo ano a ano à medida que chega à idade adulta. - -O cÊrebro e os sentidos de uma criança percebem os fatos ao seu redor e gradualmente aprendem os padrÃĩes ocultos de vida que ajudam a criança a criar regras lÃŗgicas para identificar os padrÃĩes aprendidos. O processo de aprendizagem do cÊrebro humano torna os humanos a criatura viva mais sofisticada deste mundo. Aprender continuamente, descobrindo padrÃĩes ocultos e, em seguida, inovar nesses padrÃĩes permite que nos tornemos cada vez melhores ao longo de nossa vida. Esta capacidade de aprendizagem e capacidade de evoluçÃŖo estÃĄ relacionada a um conceito chamado [plasticidade cerebral](https://www.simplypsychology.org/brain-plasticity.html). Superficialmente, podemos traçar algumas semelhanças motivacionais entre o processo de aprendizado do cÊrebro humano e os conceitos de aprendizado de mÃĄquina. - -O [cÊrebro humano](https://www.livescience.com/29365-human-brain.html) percebe coisas do mundo real, processa as informaçÃĩes percebidas, toma decisÃĩes racionais e executa certas açÃĩes com base nas circunstÃĸncias. Isso Ê o que chamamos de comportamento inteligente. Quando programamos um fac-símile do processo comportamental inteligente para uma mÃĄquina, isso Ê chamado de inteligÃĒncia artificial (AI). - -Embora os termos possam ser confundidos, o machine learning (ML) Ê um subconjunto importante da inteligÃĒncia artificial. **ML se preocupa em usar algoritmos especializados para descobrir informaçÃĩes significativas e encontrar padrÃĩes ocultos de dados percebidos para corroborar o processo de tomada de decisÃŖo racional**. - -![AI, ML, deep learning, data science](../images/ai-ml-ds.png) - -> Um diagrama que mostra as relaçÃĩes entre AI, ML, deep learning, and data science. InfogrÃĄfico de [Jen Looper](https://twitter.com/jenlooper) inspirado [neste grÃĄfico](https://softwareengineering.stackexchange.com/questions/366996/distinction-between-ai-ml-neural-networks-deep-learning-and-data-mining) - -## O que vocÃĒ aprenderÃĄ neste curso - -Nesta seçÃŖo, vamos cobrir apenas os conceitos bÃĄsicos de machine learning que um iniciante deve conhecer. Abordamos o que chamamos de 'machine learning clÃĄssico' principalmente usando o Scikit-learn, uma excelente biblioteca que muitos alunos usam para aprender o bÃĄsico. Para compreender conceitos mais amplos de inteligÃĒncia artificial ou deep learning, Ê indispensÃĄvel um forte conhecimento fundamental de machine learning e, por isso, gostaríamos de oferecÃĒ-lo aqui. - -Neste curso vocÃĒ aprenderÃĄ: - -- conceitos fundamentais de machine learning -- a histÃŗria do ML -- ML e justiça -- tÊcnicas de regressÃŖo de ML -- tÊcnicas de classificaçÃŖo com ML -- tÊcnicas de agrupamento de ML -- tÊcnicas de processamento de linguagem natural de ML -- tÊcnicas de ML de previsÃŖo de sÊries temporais -- aprendizagem por reforço -- aplicativos do mundo real para ML - -## O que nÃŖo cobriremos - -- deep learning -- redes neurais (neural networks) -- AI - -Para tornar essa experiÃĒncia de aprendizado melhor, evitaremos as complexidades das redes neurais, 'deep learning' - construçÃŖo de modelos em vÃĄrias camadas usando redes neurais - e AI, que discutiremos em um currículo diferente. TambÊm ofereceremos um futuro currículo de ciÃĒncia de dados para consolidar esse aspecto desse campo mais amplo. - -## Por que estudar machine learning? - -O machine learning, de uma perspectiva de sistemas, Ê definido como a criaçÃŖo de sistemas automatizados que podem aprender padrÃĩes ocultos de dados para ajudar na tomada de decisÃĩes inteligentes. - -Essa motivaçÃŖo Ê vagamente inspirada em como o cÊrebro humano aprende certas coisas com base nos dados que percebe do mundo exterior. - -✅ Pense por um minuto por que uma empresa iria querer tentar usar estratÊgias de machine learning em vez de criar um mecanismo baseado em regras embutido. - -### AplicaçÃĩes do machine learning - -Os aplicativos de machine learning agora estÃŖo em quase todos os lugares e sÃŖo tÃŖo onipresentes quanto os dados que fluem em nossas sociedades, gerados por nossos smartphones, dispositivos conectados e outros sistemas. Considerando o imenso potencial dos algoritmos de aprendizado de mÃĄquina (machine learning) de Ãēltima geraçÃŖo, os pesquisadores tÃĒm explorado sua capacidade de resolver problemas multidimensionais e multidisciplinares da vida real com excelentes resultados positivos. - -**VocÃĒ pode usar o machine learning de vÃĄrias maneiras**: - -- Para prever a probabilidade de doença a partir do histÃŗrico mÊdico ou relatÃŗrios de um paciente. -- Para aproveitar os dados meteorolÃŗgicos para prever eventos meteorolÃŗgicos. -- Para entender o sentimento de um texto. -- Para detectar notícias falsas (fake news) e impedir a propagaçÃŖo de propaganda. - -Finanças, economia, ciÃĒncias da terra, exploraçÃŖo espacial, engenharia biomÊdica, ciÃĒncias cognitivas e atÊ mesmo campos das humanidades adaptaram o machine learning para resolver os ÃĄrduos e pesados problemas de processamento de dados de seu domínio. - -O machine learning automatiza o processo de descoberta de padrÃĩes, encontrando insights significativos do mundo real ou dados gerados. Ele provou ser altamente valioso em aplicaçÃĩes comerciais, de saÃēde e financeiras, entre outras. - -Em um futuro prÃŗximo, compreender os fundamentos do machine learning serÃĄ uma obrigaçÃŖo para pessoas de qualquer domínio devido à sua ampla adoçÃŖo. - ---- - -## 🚀 Desafio - -Esboce, no papel ou usando um aplicativo online como [Excalidraw](https://excalidraw.com/), sua compreensÃŖo das diferenças entre AI, ML, deep learning e data science. Adicione algumas idÊias de problemas que cada uma dessas tÊcnicas Ê boa para resolver. - -## [QuestionÃĄrio pÃŗs-aula](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/2?loc=ptbr) - -## RevisÃŖo e autoestudo - -Para saber mais sobre como vocÃĒ pode trabalhar com algoritmos de ML na nuvem, siga este [Caminho de aprendizagem](https://docs.microsoft.com/learn/paths/create-no-code-predictive-models-azure-machine-learning/?WT.mc_id=academic-77952-leestott). - -Faça o [Caminho de aprendizagem](https://docs.microsoft.com/learn/modules/introduction-to-machine-learning/?WT.mc_id=academic-77952-leestott) sobre os fundamentos do ML. - -## Tarefa - -[Comece a trabalhar](assignment.pt-br.md) diff --git a/1-Introduction/1-intro-to-ML/translations/README.ru.md b/1-Introduction/1-intro-to-ML/translations/README.ru.md deleted file mode 100644 index e7a19915..00000000 --- a/1-Introduction/1-intro-to-ML/translations/README.ru.md +++ /dev/null @@ -1,149 +0,0 @@ -# ВвĐĩĐ´ĐĩĐŊиĐĩ в ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐĩ ОйŅƒŅ‡ĐĩĐŊиĐĩ - - - -[![ML, AI, ĐŗĐģŅƒĐąĐžĐēĐžĐĩ ОйŅƒŅ‡ĐĩĐŊиĐĩ - в Ņ‡ĐĩĐŧ Ņ€Đ°ĐˇĐŊиŅ†Đ°?](https://img.youtube.com/vi/lTd9RSxS9ZE/0.jpg)](https://youtu.be/lTd9RSxS9ZE "ML, AI, ĐŗĐģŅƒĐąĐžĐēĐžĐĩ ОйŅƒŅ‡ĐĩĐŊиĐĩ - в Ņ‡ĐĩĐŧ Ņ€Đ°ĐˇĐŊиŅ†Đ°?") - -> đŸŽĨ НаĐļĐŧиŅ‚Đĩ ĐŊĐ° иСОйŅ€Đ°ĐļĐĩĐŊиĐĩ вŅ‹ŅˆĐĩ, Ņ‡Ņ‚ОйŅ‹ ĐŋŅ€ĐžŅĐŧĐžŅ‚Ņ€ĐĩŅ‚ŅŒ видĐĩĐž, в ĐēĐžŅ‚ĐžŅ€ĐžĐŧ ОйŅŅƒĐļĐ´Đ°ĐĩŅ‚ŅŅ Ņ€Đ°ĐˇĐŊиŅ†Đ° ĐŧĐĩĐļĐ´Ņƒ ĐŧĐ°ŅˆĐ¸ĐŊĐŊŅ‹Đŧ ОйŅƒŅ‡ĐĩĐŊиĐĩĐŧ, иŅĐēŅƒŅŅŅ‚вĐĩĐŊĐŊŅ‹Đŧ иĐŊŅ‚ĐĩĐģĐģĐĩĐēŅ‚ĐžĐŧ и ĐŗĐģŅƒĐąĐžĐēиĐŧ ОйŅƒŅ‡ĐĩĐŊиĐĩĐŧ. - -## [ĐĸĐĩŅŅ‚ ĐŋĐĩŅ€ĐĩĐ´ ĐģĐĩĐēŅ†Đ¸ĐĩĐš](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/1/) - ---- - -ДобŅ€Đž ĐŋĐžĐļĐ°ĐģОваŅ‚ŅŒ ĐŊĐ° ĐēŅƒŅ€Ņ ĐēĐģĐ°ŅŅĐ¸Ņ‡ĐĩŅĐēĐžĐŗĐž ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐŗĐž ОйŅƒŅ‡ĐĩĐŊиŅ Đ´ĐģŅ ĐŊĐ°Ņ‡Đ¸ĐŊĐ°ŅŽŅ‰Đ¸Ņ…! ЕŅĐģи вŅ‹ ĐŊОвиŅ‡ĐžĐē в ŅŅ‚ОК Ņ‚ĐĩĐŧĐĩ иĐģи ĐžĐŋŅ‹Ņ‚ĐŊŅ‹Đš ŅĐŋĐĩŅ†Đ¸Đ°ĐģиŅŅ‚ ĐŋĐž ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐŧŅƒ ОйŅƒŅ‡ĐĩĐŊиŅŽ, ĐļĐĩĐģĐ°ŅŽŅ‰Đ¸Đš ĐžŅĐ˛ĐĩĐļиŅ‚ŅŒ ŅĐ˛ĐžĐ¸ СĐŊĐ°ĐŊиŅ в ĐēĐ°ĐēОК-ĐģийО ОйĐģĐ°ŅŅ‚и, ĐŧŅ‹ Ņ€Đ°Đ´Ņ‹, Ņ‡Ņ‚Đž вŅ‹ ĐŋŅ€Đ¸ŅĐžĐĩдиĐŊиĐģиŅŅŒ Đē ĐŊĐ°Đŧ! МŅ‹ Ņ…ĐžŅ‚иĐŧ ŅĐžĐˇĐ´Đ°Ņ‚ŅŒ ŅƒĐ´ĐžĐąĐŊŅƒŅŽ ŅŅ‚Đ°Ņ€Ņ‚ОвŅƒŅŽ ĐŋĐģĐžŅ‰Đ°Đ´ĐēŅƒ Đ´ĐģŅ ваŅˆĐĩĐŗĐž иСŅƒŅ‡ĐĩĐŊиŅ ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐŗĐž ОйŅƒŅ‡ĐĩĐŊиŅ и ĐąŅƒĐ´ĐĩĐŧ Ņ€Đ°Đ´Ņ‹ ĐžŅ‚вĐĩŅ‚иŅ‚ŅŒ и ŅƒŅ‡ĐĩŅŅ‚ŅŒ ваŅˆĐ¸ [ĐžŅ‚СŅ‹Đ˛Ņ‹](https://github.com/microsoft/ML-For-Beginners/discussions). - -[![ВвĐĩĐ´ĐĩĐŊиĐĩ в ML](https://img.youtube.com/vi/h0e2HAPTGF4/0.jpg)](https://youtu.be/h0e2HAPTGF4 "ВвĐĩĐ´ĐĩĐŊиĐĩ в ML") - -> đŸŽĨ НаĐļĐŧиŅ‚Đĩ ĐŊĐ° иСОйŅ€Đ°ĐļĐĩĐŊиĐĩ вŅ‹ŅˆĐĩ, Ņ‡Ņ‚ОйŅ‹ ĐŋŅ€ĐžŅĐŧĐžŅ‚Ņ€ĐĩŅ‚ŅŒ видĐĩĐž: ДĐļĐžĐŊ ГŅƒŅ‚Ņ‚Đ°Đŗ иС МаŅŅĐ°Ņ‡ŅƒŅĐĩŅ‚ŅĐēĐžĐŗĐž Ņ‚ĐĩŅ…ĐŊĐžĐģĐžĐŗиŅ‡ĐĩŅĐēĐžĐŗĐž иĐŊŅŅ‚иŅ‚ŅƒŅ‚Đ° ĐŋŅ€ĐĩĐ´ŅŅ‚авĐģŅĐĩŅ‚ ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐĩ ОйŅƒŅ‡ĐĩĐŊиĐĩ - ---- -## НаŅ‡Đ°ĐģĐž Ņ€Đ°ĐąĐžŅ‚Ņ‹ Ņ ĐŧĐ°ŅˆĐ¸ĐŊĐŊŅ‹Đŧ ОйŅƒŅ‡ĐĩĐŊиĐĩĐŧ - -ПĐĩŅ€ĐĩĐ´ Ņ‚ĐĩĐŧ, ĐēĐ°Đē ĐŋŅ€Đ¸ŅŅ‚ŅƒĐŋиŅ‚ŅŒ Đē иСŅƒŅ‡ĐĩĐŊиŅŽ ŅŅ‚ОК ŅƒŅ‡ĐĩĐąĐŊОК ĐŋŅ€ĐžĐŗŅ€Đ°ĐŧĐŧŅ‹, ваĐŧ ĐŊĐĩОйŅ…ОдиĐŧĐž ĐŊĐ°ŅŅ‚Ņ€ĐžĐ¸Ņ‚ŅŒ ĐēĐžĐŧĐŋŅŒŅŽŅ‚ĐĩŅ€ и ĐŋОдĐŗĐžŅ‚ОвиŅ‚ŅŒ ĐĩĐŗĐž Đ´ĐģŅ Ņ€Đ°ĐąĐžŅ‚Ņ‹ Ņ ĐŊĐžŅƒŅ‚ĐąŅƒĐēĐ°Đŧи ĐģĐžĐēĐ°ĐģŅŒĐŊĐž. - -- **НаŅŅ‚Ņ€ĐžĐšŅ‚Đĩ ŅĐ˛ĐžŅŽ ĐŧĐ°ŅˆĐ¸ĐŊŅƒ Ņ ĐŋĐžĐŧĐžŅ‰ŅŒŅŽ ŅŅ‚иŅ… видĐĩĐž**. ВоŅĐŋĐžĐģŅŒĐˇŅƒĐšŅ‚ĐĩŅŅŒ ŅĐģĐĩĐ´ŅƒŅŽŅ‰Đ¸Đŧи ŅŅŅ‹ĐģĐēĐ°Đŧи, Ņ‡Ņ‚ОйŅ‹ ŅƒĐˇĐŊĐ°Ņ‚ŅŒ [ĐēĐ°Đē ŅƒŅŅ‚Đ°ĐŊОвиŅ‚ŅŒ Python](https://youtu.be/CXZYvNRIAKM) в ваŅˆĐĩĐš ŅĐ¸ŅŅ‚ĐĩĐŧĐĩ и [ĐŊĐ°ŅŅ‚Ņ€ĐžĐ¸Ņ‚ŅŒ Ņ‚ĐĩĐēŅŅ‚ОвŅ‹Đš Ņ€ĐĩĐ´Đ°ĐēŅ‚ĐžŅ€](https://youtu.be/EU8eayHWoZg) Đ´ĐģŅ Ņ€Đ°ĐˇŅ€Đ°ĐąĐžŅ‚Đēи. -- **ИСŅƒŅ‡Đ¸Ņ‚Đĩ Python**. ĐĸĐ°ĐēĐļĐĩ Ņ€ĐĩĐēĐžĐŧĐĩĐŊĐ´ŅƒĐĩŅ‚ŅŅ иĐŧĐĩŅ‚ŅŒ йаСОвŅ‹Đĩ СĐŊĐ°ĐŊиŅ Đž [Python](https://docs.microsoft.com/learn/paths/python-language/?WT.mc_id=academic-77952-leestott), ŅĐˇŅ‹ĐēĐĩ ĐŋŅ€ĐžĐŗŅ€Đ°ĐŧĐŧиŅ€ĐžĐ˛Đ°ĐŊиŅ, ĐŋĐžĐģĐĩСĐŊĐžĐŧ Đ´ĐģŅ ŅĐŋĐĩŅ†Đ¸Đ°ĐģиŅŅ‚Ов ĐŋĐž Đ´Đ°ĐŊĐŊŅ‹Đŧ, ĐēĐžŅ‚ĐžŅ€Ņ‹Đš ĐŧŅ‹ иŅĐŋĐžĐģŅŒĐˇŅƒĐĩĐŧ в ŅŅ‚ĐžĐŧ ĐēŅƒŅ€ŅĐĩ. -- **ИСŅƒŅ‡Đ¸Ņ‚Đĩ Node.js и JavaScript**. МŅ‹ Ņ‚Đ°ĐēĐļĐĩ ĐŊĐĩŅĐēĐžĐģŅŒĐēĐž Ņ€Đ°Đˇ иŅĐŋĐžĐģŅŒĐˇŅƒĐĩĐŧ JavaScript в ŅŅ‚ĐžĐŧ ĐēŅƒŅ€ŅĐĩ ĐŋŅ€Đ¸ ŅĐžĐˇĐ´Đ°ĐŊии вĐĩĐą-ĐŋŅ€Đ¸ĐģĐžĐļĐĩĐŊиК, ĐŋĐžŅŅ‚ĐžĐŧŅƒ ваĐŧ ĐŋĐžŅ‚Ņ€ĐĩĐąŅƒĐĩŅ‚ŅŅ ŅƒŅŅ‚Đ°ĐŊОвиŅ‚ŅŒ [node](https://nodejs.org) и [npm](https://www.npmjs.com/), Đ° Ņ‚Đ°ĐēĐļĐĩ [Visual Studio Code](https://code.visualstudio.com/), Đ´ĐžŅŅ‚ŅƒĐŋĐŊŅ‹Đš Đ´ĐģŅ Ņ€Đ°ĐˇŅ€Đ°ĐąĐžŅ‚Đēи ĐēĐ°Đē ĐŊĐ° Python, Ņ‚Đ°Đē и ĐŊĐ° JavaScript. -- **ХОСдаКŅ‚Đĩ ŅƒŅ‡ĐĩŅ‚ĐŊŅƒŅŽ СаĐŋиŅŅŒ GitHub**. ПоŅĐēĐžĐģŅŒĐēŅƒ вŅ‹ ĐŊĐ°ŅˆĐģи ĐŊĐ°Ņ ĐŊĐ° [GitHub](https://github.com), вОСĐŧĐžĐļĐŊĐž, Ņƒ ваŅ ŅƒĐļĐĩ ĐĩŅŅ‚ŅŒ ŅƒŅ‡ĐĩŅ‚ĐŊĐ°Ņ СаĐŋиŅŅŒ, ĐŊĐž ĐĩŅĐģи ĐŊĐĩŅ‚, ŅĐžĐˇĐ´Đ°ĐšŅ‚Đĩ ĐĩĐĩ, Đ° СаŅ‚ĐĩĐŧ ŅĐžĐˇĐ´Đ°ĐšŅ‚Đĩ Ņ„ĐžŅ€Đē ŅŅ‚ОК ŅƒŅ‡ĐĩĐąĐŊОК ĐŋŅ€ĐžĐŗŅ€Đ°ĐŧĐŧŅ‹, Ņ‡Ņ‚ОйŅ‹ иŅĐŋĐžĐģŅŒĐˇĐžĐ˛Đ°Ņ‚ŅŒ ĐĩĐĩ ŅĐ°ĐŧĐžŅŅ‚ĐžŅŅ‚ĐĩĐģŅŒĐŊĐž. (НĐĩ ŅŅ‚ĐĩŅĐŊŅĐšŅ‚ĐĩŅŅŒ ĐŋĐžŅŅ‚авиŅ‚ŅŒ СвĐĩСдŅƒ ŅŅ‚ĐžĐŧŅƒ Ņ€ĐĩĐŋОСиŅ‚ĐžŅ€Đ¸ŅŽ 😊) -- **ОзĐŊĐ°ĐēĐžĐŧŅŒŅ‚ĐĩŅŅŒ ŅĐž Scikit-learn**. ОзĐŊĐ°ĐēĐžĐŧŅŒŅ‚ĐĩŅŅŒ ŅĐž [Scikit-learn](https://scikit-learn.org/stable/user_guide.html), ĐŊайОŅ€ĐžĐŧ йийĐģиОŅ‚ĐĩĐē Đ´ĐģŅ ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐŗĐž ОйŅƒŅ‡ĐĩĐŊиŅ, ĐŊĐ° ĐēĐžŅ‚ĐžŅ€Ņ‹Đĩ ĐŧŅ‹ ŅŅŅ‹ĐģĐ°ĐĩĐŧŅŅ в ŅŅ‚иŅ… ŅƒŅ€ĐžĐēĐ°Ņ…. - ---- -## ЧŅ‚Đž Ņ‚Đ°ĐēĐžĐĩ ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐĩ ОйŅƒŅ‡ĐĩĐŊиĐĩ? - -ĐĸĐĩŅ€ĐŧиĐŊ "ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐĩ ОйŅƒŅ‡ĐĩĐŊиĐĩ" - ОдиĐŊ иС ŅĐ°ĐŧŅ‹Ņ… ĐŋĐžĐŋŅƒĐģŅŅ€ĐŊŅ‹Ņ… и Ņ‡Đ°ŅŅ‚Đž иŅĐŋĐžĐģŅŒĐˇŅƒĐĩĐŧŅ‹Ņ… ŅĐĩĐŗОдĐŊŅ Ņ‚ĐĩŅ€ĐŧиĐŊОв. ОŅ‡ĐĩĐŊŅŒ вĐĩŅ€ĐžŅŅ‚ĐŊĐž, Ņ‡Ņ‚Đž вŅ‹ ŅĐģŅ‹ŅˆĐ°Đģи ŅŅ‚ĐžŅ‚ Ņ‚ĐĩŅ€ĐŧиĐŊ Ņ…ĐžŅ‚Ņ ĐąŅ‹ Ņ€Đ°Đˇ, ĐĩŅĐģи вŅ‹ Ņ…ĐžŅ‚ŅŒ ĐŊĐĩĐŧĐŊĐžĐŗĐž СĐŊĐ°ĐēĐžĐŧŅ‹ Ņ Ņ‚ĐĩŅ…ĐŊĐžĐģĐžĐŗиŅĐŧи, ĐŊĐĩСавиŅĐ¸ĐŧĐž ĐžŅ‚ Ņ‚ĐžĐŗĐž, в ĐēĐ°ĐēОК ОйĐģĐ°ŅŅ‚и вŅ‹ Ņ€Đ°ĐąĐžŅ‚Đ°ĐĩŅ‚Đĩ. ОдĐŊĐ°ĐēĐž ĐŧĐĩŅ…Đ°ĐŊиĐēĐ° ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐŗĐž ОйŅƒŅ‡ĐĩĐŊиŅ ĐžŅŅ‚Đ°ĐĩŅ‚ŅŅ СаĐŗĐ°Đ´ĐēОК Đ´ĐģŅ йОĐģŅŒŅˆĐ¸ĐŊŅŅ‚ва ĐģŅŽĐ´ĐĩĐš. ДĐģŅ ĐŊОвиŅ‡ĐēĐ° в ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐŧ ОйŅƒŅ‡ĐĩĐŊии ŅŅ‚Đ° Ņ‚ĐĩĐŧĐ° иĐŊĐžĐŗĐ´Đ° ĐŧĐžĐļĐĩŅ‚ ĐŋĐžĐēаСаŅ‚ŅŒŅŅ ŅĐģĐžĐļĐŊОК. ПоŅŅ‚ĐžĐŧŅƒ ваĐļĐŊĐž ĐŋĐžĐŊиĐŧĐ°Ņ‚ŅŒ, Ņ‡Ņ‚Đž Ņ‚Đ°ĐēĐžĐĩ ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐĩ ОйŅƒŅ‡ĐĩĐŊиĐĩ ĐŊĐ° ŅĐ°ĐŧĐžĐŧ Đ´ĐĩĐģĐĩ, и иСŅƒŅ‡Đ°Ņ‚ŅŒ ĐĩĐŗĐž ŅˆĐ°Đŗ Са ŅˆĐ°ĐŗĐžĐŧ ĐŊĐ° ĐŋŅ€Đ°ĐēŅ‚иŅ‡ĐĩŅĐēиŅ… ĐŋŅ€Đ¸ĐŧĐĩŅ€Đ°Ņ…. - ---- -## КŅ€Đ¸Đ˛Đ°Ņ Ņ…Đ°ĐšĐŋĐ° - -![ĐēŅ€Đ¸Đ˛Đ°Ņ Ņ…Đ°ĐšĐŋĐ° ML](../images/hype.png) - -> Google Trends ĐŋĐžĐēаСŅ‹Đ˛Đ°ĐĩŅ‚ ĐŊĐĩдавĐŊŅŽŅŽ "ĐēŅ€Đ¸Đ˛ŅƒŅŽ Ņ…Đ°ĐšĐŋĐ°" Ņ‚ĐĩŅ€ĐŧиĐŊĐ° "ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐĩ ОйŅƒŅ‡ĐĩĐŊиĐĩ". - ---- -## ЗаĐŗĐ°Đ´ĐžŅ‡ĐŊĐ°Ņ вŅĐĩĐģĐĩĐŊĐŊĐ°Ņ - -МŅ‹ ĐļивĐĩĐŧ вО вŅĐĩĐģĐĩĐŊĐŊОК, ĐŋĐžĐģĐŊОК СавОŅ€Đ°ĐļиваŅŽŅ‰Đ¸Ņ… СаĐŗĐ°Đ´ĐžĐē. ВĐĩĐģиĐēиĐĩ ŅƒŅ‡ĐĩĐŊŅ‹Đĩ, Ņ‚Đ°ĐēиĐĩ ĐēĐ°Đē ĐĄŅ‚ивĐĩĐŊ ĐĨĐžĐēиĐŊĐŗ, АĐģŅŒĐąĐĩŅ€Ņ‚ Đ­ĐšĐŊŅˆŅ‚ĐĩĐšĐŊ и ĐŧĐŊĐžĐŗиĐĩ Đ´Ņ€ŅƒĐŗиĐĩ, ĐŋĐžŅĐ˛ŅŅ‚иĐģи ŅĐ˛ĐžŅŽ ĐļиСĐŊŅŒ ĐŋОиŅĐēŅƒ СĐŊĐ°Ņ‡Đ¸ĐŧОК иĐŊŅ„ĐžŅ€ĐŧĐ°Ņ†Đ¸Đ¸, Ņ€Đ°ŅĐēŅ€Ņ‹Đ˛Đ°ŅŽŅ‰ĐĩĐš Ņ‚Đ°ĐšĐŊŅ‹ ĐžĐēŅ€ŅƒĐļĐ°ŅŽŅ‰ĐĩĐŗĐž ĐŊĐ°Ņ ĐŧиŅ€Đ°. Đ­Ņ‚Đž ŅƒŅĐģОвиĐĩ ОйŅƒŅ‡ĐĩĐŊиŅ: Ņ€ĐĩĐąĐĩĐŊĐžĐē иС ĐŗОда в ĐŗОд ŅƒĐˇĐŊĐ°ĐĩŅ‚ ĐŊОвОĐĩ и Ņ€Đ°ŅĐēŅ€Ņ‹Đ˛Đ°ĐĩŅ‚ ŅŅ‚Ņ€ŅƒĐēŅ‚ŅƒŅ€Ņƒ ĐžĐēŅ€ŅƒĐļĐ°ŅŽŅ‰ĐĩĐŗĐž ĐŧиŅ€Đ° ĐŋĐž ĐŧĐĩŅ€Đĩ вСŅ€ĐžŅĐģĐĩĐŊиŅ. - ---- -## МозĐŗ Ņ€ĐĩĐąĐĩĐŊĐēĐ° - -МозĐŗ и ĐžŅ€ĐŗĐ°ĐŊŅ‹ Ņ‡ŅƒĐ˛ŅŅ‚в Ņ€ĐĩĐąĐĩĐŊĐēĐ° вОŅĐŋŅ€Đ¸ĐŊиĐŧĐ°ŅŽŅ‚ Ņ„Đ°ĐēŅ‚Ņ‹ иС ŅĐ˛ĐžĐĩĐŗĐž ĐžĐēŅ€ŅƒĐļĐĩĐŊиŅ и ĐŋĐžŅŅ‚ĐĩĐŋĐĩĐŊĐŊĐž иСŅƒŅ‡Đ°ŅŽŅ‚ ŅĐēŅ€Ņ‹Ņ‚Ņ‹Đĩ СаĐēĐžĐŊĐžĐŧĐĩŅ€ĐŊĐžŅŅ‚и ĐļиСĐŊи, ĐēĐžŅ‚ĐžŅ€Ņ‹Đĩ ĐŋĐžĐŧĐžĐŗĐ°ŅŽŅ‚ Ņ€ĐĩĐąĐĩĐŊĐēŅƒ вŅ‹Ņ€Đ°ĐąĐžŅ‚Đ°Ņ‚ŅŒ ĐģĐžĐŗиŅ‡ĐĩŅĐēиĐĩ ĐŋŅ€Đ°Đ˛Đ¸ĐģĐ° Đ´ĐģŅ ĐžĐŋŅ€ĐĩĐ´ĐĩĐģĐĩĐŊиŅ ŅƒŅĐ˛ĐžĐĩĐŊĐŊŅ‹Ņ… СаĐēĐžĐŊĐžĐŧĐĩŅ€ĐŊĐžŅŅ‚ĐĩĐš. ПŅ€ĐžŅ†ĐĩŅŅ ОйŅƒŅ‡ĐĩĐŊиŅ Ņ‡ĐĩĐģОвĐĩŅ‡ĐĩŅĐēĐžĐŗĐž ĐŧОСĐŗĐ° Đ´ĐĩĐģĐ°ĐĩŅ‚ ĐģŅŽĐ´ĐĩĐš ŅĐ°ĐŧŅ‹Đŧи иСОŅ‰Ņ€ĐĩĐŊĐŊŅ‹Đŧи ĐļивŅ‹Đŧи ŅŅƒŅ‰ĐĩŅŅ‚ваĐŧи в ŅŅ‚ĐžĐŧ ĐŧиŅ€Đĩ. ПоŅŅ‚ĐžŅĐŊĐŊĐžĐĩ ОйŅƒŅ‡ĐĩĐŊиĐĩ, ОйĐŊĐ°Ņ€ŅƒĐļĐĩĐŊиĐĩ ŅĐēŅ€Ņ‹Ņ‚Ņ‹Ņ… СаĐēĐžĐŊĐžĐŧĐĩŅ€ĐŊĐžŅŅ‚ĐĩĐš и ĐŋĐžŅĐģĐĩĐ´ŅƒŅŽŅ‰ĐĩĐĩ вĐŊĐĩĐ´Ņ€ĐĩĐŊиĐĩ иĐŊĐŊОваŅ†Đ¸Đš, ĐŋОСвОĐģŅĐĩŅ‚ ĐŊĐ°Đŧ ŅŅ‚Đ°ĐŊОвиŅ‚ŅŒŅŅ ĐģŅƒŅ‡ŅˆĐĩ и ĐģŅƒŅ‡ŅˆĐĩ ĐŊĐ° ĐŋŅ€ĐžŅ‚ŅĐļĐĩĐŊии вŅĐĩĐš ĐļиСĐŊи. Đ­Ņ‚Đ° ŅĐŋĐžŅĐžĐąĐŊĐžŅŅ‚ŅŒ Đē ОйŅƒŅ‡ĐĩĐŊиŅŽ и ŅĐŋĐžŅĐžĐąĐŊĐžŅŅ‚ŅŒ Đē Ņ€Đ°ĐˇĐ˛Đ¸Ņ‚иŅŽ ŅĐ˛ŅĐˇĐ°ĐŊŅ‹ Ņ ĐēĐžĐŊŅ†ĐĩĐŋŅ†Đ¸ĐĩĐš, ĐŊаСŅ‹Đ˛Đ°ĐĩĐŧОК [ĐŋĐģĐ°ŅŅ‚иŅ‡ĐŊĐžŅŅ‚ŅŒ ĐŧОСĐŗĐ°](https://www.simplypsychology.org/brain-plasticity.html). На ĐŋĐĩŅ€Đ˛Ņ‹Đš вСĐŗĐģŅĐ´, ĐŧŅ‹ ĐŧĐžĐļĐĩĐŧ вŅ‹ŅĐ˛Đ¸Ņ‚ŅŒ ĐŊĐĩĐēĐžŅ‚ĐžŅ€Ņ‹Đĩ ĐŧĐžŅ‚иваŅ†Đ¸ĐžĐŊĐŊŅ‹Đĩ ŅŅ…ОдŅŅ‚ва ĐŧĐĩĐļĐ´Ņƒ ĐŋŅ€ĐžŅ†ĐĩŅŅĐžĐŧ ОйŅƒŅ‡ĐĩĐŊиŅ Ņ‡ĐĩĐģОвĐĩŅ‡ĐĩŅĐēĐžĐŗĐž ĐŧОСĐŗĐ° и ĐēĐžĐŊŅ†ĐĩĐŋŅ†Đ¸ŅĐŧи ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐŗĐž ОйŅƒŅ‡ĐĩĐŊиŅ. - ---- -## ЧĐĩĐģОвĐĩŅ‡ĐĩŅĐēиК ĐŧОСĐŗ - -[ЧĐĩĐģОвĐĩŅ‡ĐĩŅĐēиК ĐŧОСĐŗ](https://www.livescience.com/29365-human-brain.html) вОŅĐŋŅ€Đ¸ĐŊиĐŧĐ°ĐĩŅ‚ вĐĩŅ‰Đ¸ иС Ņ€ĐĩĐ°ĐģŅŒĐŊĐžĐŗĐž ĐŧиŅ€Đ°, ОйŅ€Đ°ĐąĐ°Ņ‚Ņ‹Đ˛Đ°ĐĩŅ‚ вОŅĐŋŅ€Đ¸ĐŊиĐŧĐ°ĐĩĐŧŅƒŅŽ иĐŊŅ„ĐžŅ€ĐŧĐ°Ņ†Đ¸ŅŽ, ĐŋŅ€Đ¸ĐŊиĐŧĐ°ĐĩŅ‚ Ņ€Đ°Ņ†Đ¸ĐžĐŊĐ°ĐģŅŒĐŊŅ‹Đĩ Ņ€ĐĩŅˆĐĩĐŊиŅ и вŅ‹ĐŋĐžĐģĐŊŅĐĩŅ‚ ĐžĐŋŅ€ĐĩĐ´ĐĩĐģĐĩĐŊĐŊŅ‹Đĩ Đ´ĐĩĐšŅŅ‚виŅ в СавиŅĐ¸ĐŧĐžŅŅ‚и ĐžŅ‚ ОйŅŅ‚ĐžŅŅ‚ĐĩĐģŅŒŅŅ‚в. Đ­Ņ‚Đž Ņ‚Đž, Ņ‡Ņ‚Đž ĐŧŅ‹ ĐŊаСŅ‹Đ˛Đ°ĐĩĐŧ Ņ€Đ°ĐˇŅƒĐŧĐŊŅ‹Đŧ ĐŋОвĐĩĐ´ĐĩĐŊиĐĩĐŧ. КоĐŗĐ´Đ° ĐŧŅ‹ ĐŋŅ€ĐžĐŗŅ€Đ°ĐŧĐŧиŅ€ŅƒĐĩĐŧ ĐēĐžĐŋиŅŽ иĐŊŅ‚ĐĩĐģĐģĐĩĐēŅ‚ŅƒĐ°ĐģŅŒĐŊĐžĐŗĐž ĐŋОвĐĩĐ´ĐĩĐŊŅ‡ĐĩŅĐēĐžĐŗĐž ĐŋŅ€ĐžŅ†ĐĩŅŅĐ° ĐŊĐ° ĐēĐžĐŧĐŋŅŒŅŽŅ‚ĐĩŅ€Đĩ, ŅŅ‚Đž ĐŊаСŅ‹Đ˛Đ°ĐĩŅ‚ŅŅ иŅĐēŅƒŅŅŅ‚вĐĩĐŊĐŊŅ‹Đŧ иĐŊŅ‚ĐĩĐģĐģĐĩĐēŅ‚ĐžĐŧ (ИИ). - ---- -## НĐĩĐŧĐŊĐžĐŗĐž Ņ‚ĐĩŅ€ĐŧиĐŊĐžĐģĐžĐŗии - -ĐĨĐžŅ‚Ņ Ņ‚ĐĩŅ€ĐŧиĐŊŅ‹ ĐŧĐžĐŗŅƒŅ‚ СаĐŋŅƒŅ‚Đ°Ņ‚ŅŒ, ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐĩ ОйŅƒŅ‡ĐĩĐŊиĐĩ (ML) ŅĐ˛ĐģŅĐĩŅ‚ŅŅ ваĐļĐŊŅ‹Đŧ ĐŋОдĐŧĐŊĐžĐļĐĩŅŅ‚вОĐŧ иŅĐēŅƒŅŅŅ‚вĐĩĐŊĐŊĐžĐŗĐž иĐŊŅ‚ĐĩĐģĐģĐĩĐēŅ‚Đ°. **МаŅˆĐ¸ĐŊĐŊĐžĐĩ ОйŅƒŅ‡ĐĩĐŊиĐĩ СаĐŊиĐŧĐ°ĐĩŅ‚ŅŅ иŅĐŋĐžĐģŅŒĐˇĐžĐ˛Đ°ĐŊиĐĩĐŧ ŅĐŋĐĩŅ†Đ¸Đ°ĐģиСиŅ€ĐžĐ˛Đ°ĐŊĐŊŅ‹Ņ… Đ°ĐģĐŗĐžŅ€Đ¸Ņ‚ĐŧОв Đ´ĐģŅ Ņ€Đ°ŅĐēŅ€Ņ‹Ņ‚иŅ СĐŊĐ°Ņ‡Đ¸ĐŧОК иĐŊŅ„ĐžŅ€ĐŧĐ°Ņ†Đ¸Đ¸ и ĐŋОиŅĐēĐ° ŅĐēŅ€Ņ‹Ņ‚Ņ‹Ņ… СаĐēĐžĐŊĐžĐŧĐĩŅ€ĐŊĐžŅŅ‚ĐĩĐš иС вОŅĐŋŅ€Đ¸ĐŊиĐŧĐ°ĐĩĐŧŅ‹Ņ… Đ´Đ°ĐŊĐŊŅ‹Ņ… Đ´ĐģŅ ĐŋОдŅ‚вĐĩŅ€ĐļĐ´ĐĩĐŊиŅ Ņ€Đ°Ņ†Đ¸ĐžĐŊĐ°ĐģŅŒĐŊĐžĐŗĐž ĐŋŅ€ĐžŅ†ĐĩŅŅĐ° ĐŋŅ€Đ¸ĐŊŅŅ‚иŅ Ņ€ĐĩŅˆĐĩĐŊиК**. - ---- -## AI, ML, ĐŗĐģŅƒĐąĐžĐēĐžĐĩ ОйŅƒŅ‡ĐĩĐŊиĐĩ - -![AI, ML, ĐŗĐģŅƒĐąĐžĐēĐžĐĩ ОйŅƒŅ‡ĐĩĐŊиĐĩ, ĐŊĐ°ŅƒĐēĐ° Đž Đ´Đ°ĐŊĐŊŅ‹Ņ…](../images/ai-ml-ds.png) - -> ДиаĐŗŅ€Đ°ĐŧĐŧĐ°, ĐŋĐžĐēаСŅ‹Đ˛Đ°ŅŽŅ‰Đ°Ņ вСаиĐŧĐžŅĐ˛ŅĐˇŅŒ ĐŧĐĩĐļĐ´Ņƒ ИИ, ĐŧĐ°ŅˆĐ¸ĐŊĐŊŅ‹Đŧ ОйŅƒŅ‡ĐĩĐŊиĐĩĐŧ, ĐŗĐģŅƒĐąĐžĐēиĐŧ ОйŅƒŅ‡ĐĩĐŊиĐĩĐŧ и ĐŊĐ°ŅƒĐēОК Đž Đ´Đ°ĐŊĐŊŅ‹Ņ…. ИĐŊŅ„ĐžĐŗŅ€Đ°Ņ„иĐēĐ° [Jen Looper](https://twitter.com/jenlooper), вдОŅ…ĐŊОвĐģĐĩĐŊĐŊĐ°Ņ [ŅŅ‚иĐŧ Ņ€Đ¸ŅŅƒĐŊĐēĐžĐŧ](https://softwareengineering.stackexchange.com/questions/366996/distinction-between-ai-ml-neural-networks-deep-learning-and-data-mining) - ---- -## КоĐŊŅ†ĐĩĐŋŅ†Đ¸Đ¸, ĐēĐžŅ‚ĐžŅ€Ņ‹Đĩ ĐžŅ…ваŅ‚Ņ‹Đ˛Đ°ĐĩŅ‚ ŅŅ‚ĐžŅ‚ ĐēŅƒŅ€Ņ - -В ŅŅ‚ОК ŅƒŅ‡ĐĩĐąĐŊОК ĐŋŅ€ĐžĐŗŅ€Đ°ĐŧĐŧĐĩ ĐŧŅ‹ ŅĐžĐąĐ¸Ņ€Đ°ĐĩĐŧŅŅ ĐžŅ…ваŅ‚иŅ‚ŅŒ Ņ‚ĐžĐģŅŒĐēĐž ĐžŅĐŊОвĐŊŅ‹Đĩ ĐēĐžĐŊŅ†ĐĩĐŋŅ†Đ¸Đ¸ ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐŗĐž ОйŅƒŅ‡ĐĩĐŊиŅ, ĐēĐžŅ‚ĐžŅ€Ņ‹Đĩ Đ´ĐžĐģĐļĐĩĐŊ СĐŊĐ°Ņ‚ŅŒ ĐŊОвиŅ‡ĐžĐē. МŅ‹ Ņ€Đ°ŅŅĐŧĐ°Ņ‚Ņ€Đ¸Đ˛Đ°ĐĩĐŧ Ņ‚Đž, Ņ‡Ņ‚Đž ĐŧŅ‹ ĐŊаСŅ‹Đ˛Đ°ĐĩĐŧ ÂĢĐēĐģĐ°ŅŅĐ¸Ņ‡ĐĩŅĐēиĐŧ ĐŧĐ°ŅˆĐ¸ĐŊĐŊŅ‹Đŧ ОйŅƒŅ‡ĐĩĐŊиĐĩĐŧÂģ, в ĐŋĐĩŅ€Đ˛ŅƒŅŽ ĐžŅ‡ĐĩŅ€ĐĩĐ´ŅŒ Ņ иŅĐŋĐžĐģŅŒĐˇĐžĐ˛Đ°ĐŊиĐĩĐŧ Scikit-learn, ĐžŅ‚ĐģиŅ‡ĐŊОК йийĐģиОŅ‚ĐĩĐēи, ĐēĐžŅ‚ĐžŅ€ŅƒŅŽ ĐŧĐŊĐžĐŗиĐĩ ŅŅ‚ŅƒĐ´ĐĩĐŊŅ‚Ņ‹ иŅĐŋĐžĐģŅŒĐˇŅƒŅŽŅ‚ Đ´ĐģŅ иСŅƒŅ‡ĐĩĐŊиŅ ĐžŅĐŊОв. ЧŅ‚ОйŅ‹ ĐŋĐžĐŊŅŅ‚ŅŒ йОĐģĐĩĐĩ ŅˆĐ¸Ņ€ĐžĐēиĐĩ ĐēĐžĐŊŅ†ĐĩĐŋŅ†Đ¸Đ¸ иŅĐēŅƒŅŅŅ‚вĐĩĐŊĐŊĐžĐŗĐž иĐŊŅ‚ĐĩĐģĐģĐĩĐēŅ‚Đ° иĐģи ĐŗĐģŅƒĐąĐžĐēĐžĐŗĐž ОйŅƒŅ‡ĐĩĐŊиŅ, ĐŊĐĩОйŅ…ОдиĐŧŅ‹ ŅĐ¸ĐģŅŒĐŊŅ‹Đĩ Ņ„ŅƒĐŊĐ´Đ°ĐŧĐĩĐŊŅ‚Đ°ĐģŅŒĐŊŅ‹Đĩ СĐŊĐ°ĐŊиŅ Đž ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐŧ ОйŅƒŅ‡ĐĩĐŊии, и ĐŋĐžŅŅ‚ĐžĐŧŅƒ ĐŧŅ‹ Ņ…ĐžŅ‚ĐĩĐģи ĐąŅ‹ ĐŋŅ€ĐĩĐ´ĐģĐžĐļиŅ‚ŅŒ иŅ… СдĐĩŅŅŒ. - ---- -## В ŅŅ‚ĐžĐŧ ĐēŅƒŅ€ŅĐĩ вŅ‹ ŅƒĐˇĐŊĐ°ĐĩŅ‚Đĩ: - -- ĐžŅĐŊОвĐŊŅ‹Đĩ ĐēĐžĐŊŅ†ĐĩĐŋŅ†Đ¸Đ¸ ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐŗĐž ОйŅƒŅ‡ĐĩĐŊиŅ -- иŅŅ‚ĐžŅ€Đ¸Ņ ML -- ML и Ņ€Đ°Đ˛ĐŊОдОŅŅ‚ŅƒĐŋĐŊĐžŅŅ‚ŅŒ -- ĐŧĐĩŅ‚ОдŅ‹ Ņ€ĐĩĐŗŅ€ĐĩŅŅĐ¸ĐžĐŊĐŊĐžĐŗĐž ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐŗĐž ОйŅƒŅ‡ĐĩĐŊиŅ -- ĐēĐģĐ°ŅŅĐ¸Ņ„иĐēĐ°Ņ†Đ¸Ņ ĐŧĐĩŅ‚ОдОв ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐŗĐž ОйŅƒŅ‡ĐĩĐŊиŅ -- ĐŧĐĩŅ‚ОдŅ‹ ĐēĐģĐ°ŅŅ‚ĐĩŅ€Đ¸ĐˇĐ°Ņ†Đ¸Đ¸ ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐŗĐž ОйŅƒŅ‡ĐĩĐŊиŅ -- ĐŧĐĩŅ‚ОдŅ‹ ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐŗĐž ОйŅƒŅ‡ĐĩĐŊиŅ ОйŅ€Đ°ĐąĐžŅ‚Đēи ĐĩŅŅ‚ĐĩŅŅ‚вĐĩĐŊĐŊĐžĐŗĐž ŅĐˇŅ‹ĐēĐ° -- ĐŧĐĩŅ‚ОдŅ‹ ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐŗĐž ОйŅƒŅ‡ĐĩĐŊиŅ ĐŋŅ€ĐžĐŗĐŊОСиŅ€ĐžĐ˛Đ°ĐŊиŅ вŅ€ĐĩĐŧĐĩĐŊĐŊŅ‹Ņ… Ņ€ŅĐ´ĐžĐ˛ -- ОйŅƒŅ‡ĐĩĐŊиĐĩ Ņ ĐŋОдĐēŅ€ĐĩĐŋĐģĐĩĐŊиĐĩĐŧ -- Ņ€ĐĩĐ°ĐģŅŒĐŊŅ‹Đĩ ĐŋŅ€Đ¸ĐģĐžĐļĐĩĐŊиŅ Đ´ĐģŅ ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐŗĐž ОйŅƒŅ‡ĐĩĐŊиŅ - ---- -## ЧŅ‚Đž ĐŧŅ‹ ĐŊĐĩ ĐąŅƒĐ´ĐĩĐŧ Ņ€Đ°ŅŅĐēаСŅ‹Đ˛Đ°Ņ‚ŅŒ - -- ĐŗĐģŅƒĐąĐžĐēĐžĐĩ ОйŅƒŅ‡ĐĩĐŊиĐĩ -- ĐŊĐĩĐšŅ€ĐžĐŊĐŊŅ‹Đĩ ŅĐĩŅ‚и -- AI - -ЧŅ‚ОйŅ‹ ŅƒĐģŅƒŅ‡ŅˆĐ¸Ņ‚ŅŒ ĐŋŅ€ĐžŅ†ĐĩŅŅ иСŅƒŅ‡ĐĩĐŊиŅ, ĐŧŅ‹ ĐąŅƒĐ´ĐĩĐŧ иСйĐĩĐŗĐ°Ņ‚ŅŒ ŅĐģĐžĐļĐŊĐžŅŅ‚ĐĩĐš ĐŊĐĩĐšŅ€ĐžĐŊĐŊŅ‹Ņ… ŅĐĩŅ‚ĐĩĐš, ÂĢĐŗĐģŅƒĐąĐžĐēĐžĐŗĐž ОйŅƒŅ‡ĐĩĐŊиŅÂģ - ĐŧĐŊĐžĐŗĐžŅƒŅ€ĐžĐ˛ĐŊĐĩвОĐŗĐž ĐŋĐžŅŅ‚Ņ€ĐžĐĩĐŊиŅ ĐŧОдĐĩĐģĐĩĐš Ņ иŅĐŋĐžĐģŅŒĐˇĐžĐ˛Đ°ĐŊиĐĩĐŧ ĐŊĐĩĐšŅ€ĐžĐŊĐŊŅ‹Ņ… ŅĐĩŅ‚ĐĩĐš - и иŅĐēŅƒŅŅŅ‚вĐĩĐŊĐŊĐžĐŗĐž иĐŊŅ‚ĐĩĐģĐģĐĩĐēŅ‚Đ°, ĐēĐžŅ‚ĐžŅ€Ņ‹Đĩ ĐŧŅ‹ ОйŅŅƒĐ´Đ¸Đŧ в Đ´Ņ€ŅƒĐŗОК ŅƒŅ‡ĐĩĐąĐŊОК ĐŋŅ€ĐžĐŗŅ€Đ°ĐŧĐŧĐĩ. МŅ‹ Ņ‚Đ°ĐēĐļĐĩ ĐŋŅ€ĐĩĐ´ŅŅ‚авиĐŧ ŅƒŅ‡ĐĩĐąĐŊŅƒŅŽ ĐŋŅ€ĐžĐŗŅ€Đ°ĐŧĐŧŅƒ ĐŋĐž ĐŊĐ°ŅƒĐēĐĩ Đž Đ´Đ°ĐŊĐŊŅ‹Ņ…, Ņ‡Ņ‚ОйŅ‹ ŅĐžŅŅ€ĐĩĐ´ĐžŅ‚ĐžŅ‡Đ¸Ņ‚ŅŒŅŅ ĐŊĐ° ŅŅ‚ĐžĐŧ Đ°ŅĐŋĐĩĐēŅ‚Đĩ ŅŅ‚ОК йОĐģĐĩĐĩ ŅˆĐ¸Ņ€ĐžĐēОК ОйĐģĐ°ŅŅ‚и. - ---- -## ЗаŅ‡ĐĩĐŧ иСŅƒŅ‡Đ°Ņ‚ŅŒ ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐĩ ОйŅƒŅ‡ĐĩĐŊиĐĩ? - -МаŅˆĐ¸ĐŊĐŊĐžĐĩ ОйŅƒŅ‡ĐĩĐŊиĐĩ Ņ ŅĐ¸ŅŅ‚ĐĩĐŧĐŊОК Ņ‚ĐžŅ‡Đēи СŅ€ĐĩĐŊиŅ ĐžĐŋŅ€ĐĩĐ´ĐĩĐģŅĐĩŅ‚ŅŅ ĐēĐ°Đē ŅĐžĐˇĐ´Đ°ĐŊиĐĩ авŅ‚ĐžĐŧĐ°Ņ‚иСиŅ€ĐžĐ˛Đ°ĐŊĐŊŅ‹Ņ… ŅĐ¸ŅŅ‚ĐĩĐŧ, ĐēĐžŅ‚ĐžŅ€Ņ‹Đĩ ĐŧĐžĐŗŅƒŅ‚ иСŅƒŅ‡Đ°Ņ‚ŅŒ ŅĐēŅ€Ņ‹Ņ‚Ņ‹Đĩ СаĐēĐžĐŊĐžĐŧĐĩŅ€ĐŊĐžŅŅ‚и иС Đ´Đ°ĐŊĐŊŅ‹Ņ…, Ņ‡Ņ‚ОйŅ‹ ĐŋĐžĐŧĐžŅ‡ŅŒ в ĐŋŅ€Đ¸ĐŊŅŅ‚ии Ņ€Đ°ĐˇŅƒĐŧĐŊŅ‹Ņ… Ņ€ĐĩŅˆĐĩĐŊиК. - -Đ­Ņ‚Đ° ĐŧĐžŅ‚иваŅ†Đ¸Ņ вО ĐŧĐŊĐžĐŗĐžĐŧ ĐžŅĐŊОваĐŊĐ° ĐŊĐ° Ņ‚ĐžĐŧ, ĐēĐ°Đē Ņ‡ĐĩĐģОвĐĩŅ‡ĐĩŅĐēиК ĐŧОСĐŗ ŅƒŅ‡Đ¸Ņ‚ŅŅ ĐžĐŋŅ€ĐĩĐ´ĐĩĐģĐĩĐŊĐŊŅ‹Đŧ вĐĩŅ‰Đ°Đŧ ĐŊĐ° ĐžŅĐŊОвĐĩ Đ´Đ°ĐŊĐŊŅ‹Ņ…, ĐēĐžŅ‚ĐžŅ€Ņ‹Đĩ ĐžĐŊ вОŅĐŋŅ€Đ¸ĐŊиĐŧĐ°ĐĩŅ‚ иС вĐŊĐĩŅˆĐŊĐĩĐŗĐž ĐŧиŅ€Đ°. - -✅ ЗадŅƒĐŧĐ°ĐšŅ‚ĐĩŅŅŒ ĐŊĐ° ĐŧиĐŊŅƒŅ‚ĐēŅƒ, ĐŋĐžŅ‡ĐĩĐŧŅƒ ĐēĐžĐŧĐŋĐ°ĐŊиŅ ĐŧĐžĐļĐĩŅ‚ ĐŋĐžĐŋŅ‹Ņ‚Đ°Ņ‚ŅŒŅŅ иŅĐŋĐžĐģŅŒĐˇĐžĐ˛Đ°Ņ‚ŅŒ ŅŅ‚Ņ€Đ°Ņ‚ĐĩĐŗии ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐŗĐž ОйŅƒŅ‡ĐĩĐŊиŅ вĐŧĐĩŅŅ‚Đž ŅĐžĐˇĐ´Đ°ĐŊиŅ ĐļĐĩŅŅ‚ĐēĐž СаĐŋŅ€ĐžĐŗŅ€Đ°ĐŧĐŧиŅ€ĐžĐ˛Đ°ĐŊĐŊĐžĐŗĐž ĐŧĐĩŅ…Đ°ĐŊиСĐŧĐ° ĐŊĐ° ĐžŅĐŊОвĐĩ ĐŋŅ€Đ°Đ˛Đ¸Đģ. - ---- -## ПŅ€Đ¸ĐģĐžĐļĐĩĐŊиŅ ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐŗĐž ОйŅƒŅ‡ĐĩĐŊиŅ - -ПŅ€Đ¸ĐģĐžĐļĐĩĐŊиŅ ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐŗĐž ОйŅƒŅ‡ĐĩĐŊиŅ ŅĐĩĐšŅ‡Đ°Ņ ĐĩŅŅ‚ŅŒ ĐŋĐžŅ‡Ņ‚и ĐŋОвŅŅŽĐ´Ņƒ, и ĐžĐŊи ŅŅ‚ĐžĐģŅŒ ĐļĐĩ ĐŋОвŅĐĩĐŧĐĩŅŅ‚ĐŊŅ‹, ĐēĐ°Đē и Đ´Đ°ĐŊĐŊŅ‹Đĩ, ĐēĐžŅ‚ĐžŅ€Ņ‹Đĩ ĐŋŅ€Đ¸ŅŅƒŅ‚ŅŅ‚вŅƒŅŽŅ‰Đ¸Đĩ в ĐŊĐ°ŅˆĐĩĐŧ ОйŅ‰ĐĩŅŅ‚вĐĩ, ĐŗĐĩĐŊĐĩŅ€Đ¸Ņ€ŅƒĐĩĐŧŅ‹Đĩ ĐŊĐ°ŅˆĐ¸Đŧи ŅĐŧĐ°Ņ€Ņ‚Ņ„ĐžĐŊĐ°Đŧи, ĐŋОдĐēĐģŅŽŅ‡ĐĩĐŊĐŊŅ‹Đŧи Đē ŅĐĩŅ‚и ŅƒŅŅ‚Ņ€ĐžĐšŅŅ‚ваĐŧи и Đ´Ņ€ŅƒĐŗиĐŧи ŅĐ¸ŅŅ‚ĐĩĐŧĐ°Đŧи. ĐŖŅ‡Đ¸Ņ‚Ņ‹Đ˛Đ°Ņ ĐžĐŗŅ€ĐžĐŧĐŊŅ‹Đš ĐŋĐžŅ‚ĐĩĐŊŅ†Đ¸Đ°Đģ ŅĐžĐ˛Ņ€ĐĩĐŧĐĩĐŊĐŊŅ‹Ņ… Đ°ĐģĐŗĐžŅ€Đ¸Ņ‚ĐŧОв ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐŗĐž ОйŅƒŅ‡ĐĩĐŊиŅ, иŅŅĐģĐĩдОваŅ‚ĐĩĐģи иСŅƒŅ‡Đ°Đģи иŅ… ŅĐŋĐžŅĐžĐąĐŊĐžŅŅ‚ŅŒ Ņ€ĐĩŅˆĐ°Ņ‚ŅŒ ĐŧĐŊĐžĐŗĐžĐŧĐĩŅ€ĐŊŅ‹Đĩ и ĐŧĐĩĐļдиŅŅ†Đ¸ĐŋĐģиĐŊĐ°Ņ€ĐŊŅ‹Đĩ ĐŋŅ€ĐžĐąĐģĐĩĐŧŅ‹ Ņ€ĐĩĐ°ĐģŅŒĐŊОК ĐļиСĐŊи Ņ ĐžŅ‚ĐģиŅ‡ĐŊŅ‹Đŧи ĐŋĐžĐģĐžĐļиŅ‚ĐĩĐģŅŒĐŊŅ‹Đŧи Ņ€ĐĩСŅƒĐģŅŒŅ‚Đ°Ņ‚Đ°Đŧи. - ---- -## ПŅ€Đ¸ĐŧĐĩŅ€Ņ‹ ĐŋŅ€Đ¸ĐŧĐĩĐŊŅĐĩĐŧĐžĐŗĐž ML - -**МаŅˆĐ¸ĐŊĐŊĐžĐĩ ОйŅƒŅ‡ĐĩĐŊиĐĩ ĐŧĐžĐļĐŊĐž иŅĐŋĐžĐģŅŒĐˇĐžĐ˛Đ°Ņ‚ŅŒ Ņ€Đ°ĐˇĐŊŅ‹Đŧи ŅĐŋĐžŅĐžĐąĐ°Đŧи**: - -- ПŅ€ĐĩĐ´ŅĐēаСаŅ‚ŅŒ вĐĩŅ€ĐžŅŅ‚ĐŊĐžŅŅ‚ŅŒ СайОĐģĐĩваĐŊиŅ ĐŊĐ° ĐžŅĐŊОваĐŊии иŅŅ‚ĐžŅ€Đ¸Đ¸ йОĐģĐĩСĐŊи ĐŋĐ°Ņ†Đ¸ĐĩĐŊŅ‚Đ° иĐģи ĐžŅ‚Ņ‡ĐĩŅ‚Ов. -- ИŅĐŋĐžĐģŅŒĐˇĐžĐ˛Đ°ĐŊиĐĩ Đ´Đ°ĐŊĐŊŅ‹Ņ… Đž ĐŋĐžĐŗОдĐĩ Đ´ĐģŅ ĐŋŅ€ĐžĐŗĐŊОСиŅ€ĐžĐ˛Đ°ĐŊиŅ ĐŋĐžĐŗОдĐŊŅ‹Ņ… ŅĐ˛ĐģĐĩĐŊиК. -- ЧŅ‚ОйŅ‹ ĐŋĐžĐŊŅŅ‚ŅŒ Ņ‚ĐžĐŊĐ°ĐģŅŒĐŊĐžŅŅ‚ŅŒ Ņ‚ĐĩĐēŅŅ‚Đ°. -- ДĐģŅ ОйĐŊĐ°Ņ€ŅƒĐļĐĩĐŊиŅ Ņ„ĐĩĐšĐēОвŅ‹Ņ… ĐŊОвОŅŅ‚ĐĩĐš, Ņ‡Ņ‚ОйŅ‹ ĐžŅŅ‚Đ°ĐŊОвиŅ‚ŅŒ Ņ€Đ°ŅĐŋŅ€ĐžŅŅ‚Ņ€Đ°ĐŊĐĩĐŊиĐĩ ĐŋŅ€ĐžĐŋĐ°ĐŗĐ°ĐŊĐ´Ņ‹. - -ФиĐŊĐ°ĐŊŅŅ‹, ŅĐēĐžĐŊĐžĐŧиĐēĐ°, ĐŊĐ°ŅƒĐēи Đž ЗĐĩĐŧĐģĐĩ, ĐžŅĐ˛ĐžĐĩĐŊиĐĩ ĐēĐžŅĐŧĐžŅĐ°, йиОĐŧĐĩдиŅ†Đ¸ĐŊŅĐēĐ°Ņ иĐŊĐļĐĩĐŊĐĩŅ€Đ¸Ņ, ĐēĐžĐŗĐŊиŅ‚ивиŅŅ‚иĐēĐ° и Đ´Đ°ĐļĐĩ ОйĐģĐ°ŅŅ‚и ĐŗŅƒĐŧĐ°ĐŊиŅ‚Đ°Ņ€ĐŊŅ‹Ņ… ĐŊĐ°ŅƒĐē Đ°Đ´Đ°ĐŋŅ‚иŅ€ĐžĐ˛Đ°Đģи ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐĩ ОйŅƒŅ‡ĐĩĐŊиĐĩ Đ´ĐģŅ Ņ€ĐĩŅˆĐĩĐŊиŅ ŅĐģĐžĐļĐŊŅ‹Ņ… СадаŅ‡ ОйŅ€Đ°ĐąĐžŅ‚Đēи Đ´Đ°ĐŊĐŊŅ‹Ņ… в ŅĐ˛ĐžĐĩĐš ОйĐģĐ°ŅŅ‚и. - ---- -## ЗаĐēĐģŅŽŅ‡ĐĩĐŊиĐĩ - -МаŅˆĐ¸ĐŊĐŊĐžĐĩ ОйŅƒŅ‡ĐĩĐŊиĐĩ авŅ‚ĐžĐŧĐ°Ņ‚иСиŅ€ŅƒĐĩŅ‚ ĐŋŅ€ĐžŅ†ĐĩŅŅ ОйĐŊĐ°Ņ€ŅƒĐļĐĩĐŊиŅ ŅˆĐ°ĐąĐģĐžĐŊОв, ĐŊĐ°Ņ…ОдŅ ваĐļĐŊŅ‹Đĩ СаĐēĐžĐŊĐžĐŧĐĩŅ€ĐŊĐžŅŅ‚и иС Ņ€ĐĩĐ°ĐģŅŒĐŊŅ‹Ņ… иĐģи ŅĐŗĐĩĐŊĐĩŅ€Đ¸Ņ€ĐžĐ˛Đ°ĐŊĐŊŅ‹Ņ… Đ´Đ°ĐŊĐŊŅ‹Ņ…. ОĐŊĐž СаŅ€ĐĩĐēĐžĐŧĐĩĐŊдОваĐģĐž ŅĐĩĐąŅ, ŅŅ€Đĩди ĐŋŅ€ĐžŅ‡ĐĩĐŗĐž, ĐēĐ°Đē ĐžŅ‡ĐĩĐŊŅŒ Ņ†ĐĩĐŊĐŊŅ‹Đš иĐŊŅŅ‚Ņ€ŅƒĐŧĐĩĐŊŅ‚ Đ´ĐģŅ йиСĐŊĐĩŅĐ°, СдŅ€Đ°Đ˛ĐžĐžŅ…Ņ€Đ°ĐŊĐĩĐŊиŅ и Ņ„иĐŊĐ°ĐŊŅĐžĐ˛. - -В ĐąĐģиĐļĐ°ĐšŅˆĐĩĐŧ ĐąŅƒĐ´ŅƒŅ‰ĐĩĐŧ ĐŋĐžĐŊиĐŧĐ°ĐŊиĐĩ ĐžŅĐŊОв ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐŗĐž ОйŅƒŅ‡ĐĩĐŊиŅ ŅŅ‚Đ°ĐŊĐĩŅ‚ ОйŅĐˇĐ°Ņ‚ĐĩĐģŅŒĐŊŅ‹Đŧ Đ´ĐģŅ ĐģŅŽĐ´ĐĩĐš иС ĐģŅŽĐąĐžĐš ОйĐģĐ°ŅŅ‚и иС-Са ĐĩĐŗĐž ŅˆĐ¸Ņ€ĐžĐēĐžĐŗĐž Ņ€Đ°ŅĐŋŅ€ĐžŅŅ‚Ņ€Đ°ĐŊĐĩĐŊиŅ. - ---- -# 🚀 ВŅ‹ĐˇĐžĐ˛ - -НабŅ€ĐžŅĐ°ĐšŅ‚Đĩ ĐŊĐ° ĐąŅƒĐŧĐ°ĐŗĐĩ иĐģи Ņ ĐŋĐžĐŧĐžŅ‰ŅŒŅŽ ĐžĐŊĐģĐ°ĐšĐŊ-ĐŋŅ€Đ¸ĐģĐžĐļĐĩĐŊиŅ, Ņ‚Đ°ĐēĐžĐŗĐž ĐēĐ°Đē [Excalidraw](https://excalidraw.com/), ваŅˆĐĩ ĐŋĐžĐŊиĐŧĐ°ĐŊиĐĩ Ņ€Đ°ĐˇĐģиŅ‡Đ¸Đš ĐŧĐĩĐļĐ´Ņƒ AI, ML, ĐŗĐģŅƒĐąĐžĐēиĐŧ ОйŅƒŅ‡ĐĩĐŊиĐĩĐŧ и ĐŊĐ°ŅƒĐēОК Đž Đ´Đ°ĐŊĐŊŅ‹Ņ…. ДобавŅŒŅ‚Đĩ ĐŊĐĩŅĐēĐžĐģŅŒĐēĐž идĐĩĐš Đž ĐŋŅ€ĐžĐąĐģĐĩĐŧĐ°Ņ…, ĐēĐžŅ‚ĐžŅ€Ņ‹Đĩ ĐŧĐžĐļĐĩŅ‚ Ņ€ĐĩŅˆĐ¸Ņ‚ŅŒ ĐēĐ°ĐļĐ´Ņ‹Đš иС ŅŅ‚иŅ… ĐŧĐĩŅ‚ОдОв. - -# [ĐĸĐĩŅŅ‚ ĐŋĐžŅĐģĐĩ ĐģĐĩĐēŅ†Đ¸Đ¸](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/2/) - ---- -# ОбзоŅ€ и ŅĐ°ĐŧООйŅƒŅ‡ĐĩĐŊиĐĩ - -ЧŅ‚ОйŅ‹ ŅƒĐˇĐŊĐ°Ņ‚ŅŒ йОĐģŅŒŅˆĐĩ Đž Ņ‚ĐžĐŧ, ĐēĐ°Đē вŅ‹ ĐŧĐžĐļĐĩŅ‚Đĩ Ņ€Đ°ĐąĐžŅ‚Đ°Ņ‚ŅŒ Ņ Đ°ĐģĐŗĐžŅ€Đ¸Ņ‚ĐŧĐ°Đŧи ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐŗĐž ОйŅƒŅ‡ĐĩĐŊиŅ в ОйĐģĐ°ĐēĐĩ, ŅĐģĐĩĐ´ŅƒĐšŅ‚Đĩ ĐēŅƒŅ€ŅŅƒ [Learning Path](https://docs.microsoft.com/learn/paths/create-no-code-predictive-models-azure-machine-learning/?WT.mc_id=academic-77952-leestott). - -ПŅ€ĐžĐšĐ´Đ¸Ņ‚Đĩ ĐēŅƒŅ€Ņ [Learning Path](https://docs.microsoft.com/learn/modules/introduction-to-machine-learning/?WT.mc_id=academic-77952-leestott) ĐŋĐž ĐžŅĐŊОваĐŧ ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐŗĐž ОйŅƒŅ‡ĐĩĐŊиŅ. - ---- -# ЗадаĐŊиĐĩ - -[ПодĐŗĐžŅ‚ОвŅŒŅ‚Đĩ ŅŅ€ĐĩĐ´Ņƒ Ņ€Đ°ĐˇŅ€Đ°ĐąĐžŅ‚Đēи](assignment.ru.md) diff --git a/1-Introduction/1-intro-to-ML/translations/README.tr.md b/1-Introduction/1-intro-to-ML/translations/README.tr.md deleted file mode 100644 index 79744c52..00000000 --- a/1-Introduction/1-intro-to-ML/translations/README.tr.md +++ /dev/null @@ -1,114 +0,0 @@ -# Makine Öğrenimine Giriş - -[![ML, AI, Derin Ãļğrenme - FarklarÄą nelerdir?](https://img.youtube.com/vi/lTd9RSxS9ZE/0.jpg)](https://youtu.be/lTd9RSxS9ZE "ML, AI, Derin Ãļğrenme - FarklarÄą nelerdir?") - -> đŸŽĨ Makine Ãļğrenimi, yapay zeka ve derin Ãļğrenme arasÄąndaki farkÄą tartÄąÅŸan bir video için yukarÄądaki resme tÄąklayÄąn. - -## [Ders Ãļncesi sÄąnav](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/1?loc=tr) - -### Introduction - -Yeni başlayanlar için klasik makine Ãļğrenimi Ãŧzerine olan bu kursa hoş geldiniz! Ä°ster bu konuda tamamen yeni olun, ister belli bir alandaki bilgilerini tazelemek isteyen deneyimli bir makine Ãļğrenimi uygulayÄącÄąsÄą olun, aramÄąza katÄąlmanÄązdan mutluluk duyarÄąz! Makine Ãļğrenimi çalÄąÅŸmanÄąz için samimi bir başlangÄąÃ§ ​​noktasÄą oluşturmak istiyoruz ve [geri bildiriminizi](https://github.com/microsoft/ML-For-Beginners/discussions) değerlendirmekten, yanÄątlamaktan ve hayata geçirmekten memnuniyet duyarÄąz. - -[![Makine Öğrenimine Giriş](https://img.youtube.com/vi/h0e2HAPTGF4/0.jpg)](https://youtu.be/h0e2HAPTGF4 "Makine Öğrenimine Giriş") - -> đŸŽĨ Video için yukarÄądaki resme tÄąklayÄąn: MIT'den John Guttag, makine Ãļğrenimini tanÄątÄąyor -### Makine Öğrenimine Başlamak - -Bu mÃŧfredata başlamadan Ãļnce, bilgisayarÄąnÄązÄąn yerel olarak (Jupyter) not defterlerini çalÄąÅŸtÄąrmak için hazÄąr olmasÄą gerekir. - -- **Makinenizi bu videolar rehberliğinde yapÄąlandÄąrÄąn**. Bu [video setinde](https://www.youtube.com/playlist?list=PLlrxD0HtieHhS8VzuMCfQD4uJ9yne1mE6) makinenizi nasÄąl kuracağınÄąz hakkÄąnda daha fazla bilgi edinin. -- **Python Ãļğrenin**. AyrÄąca, veri bilimciler için faydalÄą bir programlama dili olan ve bu derslerde kullandığımÄąz [Python](https://docs.microsoft.com/learn/paths/python-language/?WT.mc_id=academic-77952-leestott) programlama dili hakkÄąnda temel bilgilere sahip olmanÄąz da Ãļnerilir. -- **Node.js ve JavaScript'i Ãļğrenin**. Web uygulamalarÄą oluştururken de bu kursta JavaScript'i birkaç kez kullanÄąyoruz, bu nedenle [node](https://nodejs.org), [npm](https://www.npmjs.com/) ve ayrÄąca hem Python hem de JavaScript geliştirme için kullanÄąlabilen [Visual Studio Code](https://code.visualstudio.com/) yÃŧklÃŧ olmalÄądÄąr. -- **GitHub hesabÄą oluşturun**. Bizi burada [GitHub](https://github.com) Ãŧzerinde bulduğunuza gÃļre, zaten bir hesabÄąnÄąz olabilir, ancak mevcut değilse, bir tane hesap oluşturun ve ardÄąndan bu mÃŧfredatÄą kendi baÅŸÄąnÄąza kullanmak için çatallayÄąn (fork). (Bize de yÄąldÄąz vermekten çekinmeyin 😊) -- **Scikit-learn'Ãŧ keşfedin**. Bu derslerde referans verdiğimiz, bir dizi ML kÃŧtÃŧphanesinden oluşan [Scikit-learn](https://scikit-learn.org/stable/user_guide.html) hakkÄąnda bilgi edinin. - -### Makine Ãļğrenimi nedir? - -'Makine Ãļğrenimi' terimi, gÃŧnÃŧmÃŧzÃŧn en popÃŧler ve sÄąk kullanÄąlan terimlerinden biridir. Hangi alanda çalÄąÅŸÄąrsanÄąz çalÄąÅŸÄąn, teknolojiyle ilgili bir tÃŧr aşinalığınÄąz varsa, bu terimi en az bir kez duymuş olma ihtimaliniz yÃŧksektir. Bununla birlikte, makine Ãļğreniminin mekanikleri, yani çalÄąÅŸma prensipleri, çoğu insan için bir gizemdir. Makine Ãļğrenimine yeni başlayan biri için konu bazen bunaltÄącÄą gelebilir. Bu nedenle, makine Ãļğreniminin gerçekte ne olduğunu anlamak ve pratik Ãļrnekler Ãŧzerinden adÄąm adÄąm Ãļğrenmek Ãļnemlidir. - -![ML heyecan eğrisi](../images/hype.png) - -> Google Trendler, 'makine Ãļğrenimi' teriminin son 'heyecan eğrisini' gÃļsteriyor - -BÃŧyÃŧleyici gizemlerle dolu bir evrende yaÅŸÄąyoruz. Stephen Hawking, Albert Einstein ve daha pek çoğu gibi bÃŧyÃŧk bilim adamlarÄą, hayatlarÄąnÄą çevremizdeki dÃŧnyanÄąn gizemlerini ortaya Ã§Äąkaran anlamlÄą bilgiler aramaya adadÄąlar. Öğrenmenin insani yÃļnÃŧ de budur: insan evladÄą yeni şeyler Ãļğrenir ve yetişkinliğe doğru bÃŧyÃŧdÃŧkçe her yÄąl kendi dÃŧnyasÄąnÄąn yapÄąsÄąnÄą ortaya Ã§ÄąkarÄąr. - -Bir çocuğun beyni ve duyularÄą, çevrelerindeki gerçekleri algÄąlar ve çocuğun, Ãļğrenilen kalÄąplarÄą tanÄąmlamak için mantÄąksal kurallar oluşturmasÄąna yardÄąmcÄą olan gizli yaşam kalÄąplarÄąnÄą yavaş yavaş Ãļğrenir. Ä°nsan beyninin Ãļğrenme sÃŧreci, insanÄą bu dÃŧnyanÄąn en gelişmiş canlÄąsÄą yapar. Gizli kalÄąplarÄą keşfederek sÃŧrekli Ãļğrenmek ve sonra bu kalÄąplar Ãŧzerinde yenilik yapmak, yaşamÄąmÄąz boyunca kendimizi giderek daha iyi hale getirmemizi sağlar. Bu Ãļğrenme kapasitesi ve gelişen kabiliyet, [beyin plastisitesi](https://www.simplypsychology.org/brain-plasticity.html) adÄą verilen bir kavramla ilgilidir. YÃŧzeysel olarak, insan beyninin Ãļğrenme sÃŧreci ile makine Ãļğrenimi kavramlarÄą arasÄąnda bazÄą motivasyonel benzerlikler çizebiliriz. - -[Ä°nsan beyni](https://www.livescience.com/29365-human-brain.html) gerçek dÃŧnyadaki şeyleri algÄąlar, algÄąlanan bilgileri işler, mantÄąksal kararlar verir ve koşullara gÃļre belirli eylemler gerçekleştirir. AkÄąllÄąca davranmak dediğimiz şey buydu işte. Bir makineye akÄąllÄą davranÄąÅŸ sÃŧrecinin bir kopyasÄąnÄą programladığımÄązda buna yapay zeka (Ä°ngilizce haliyle artificial intelligence, kÄąsaca **AI**) denir. - -Terimler karÄąÅŸtÄąrÄąlabilse de, makine Ãļğrenimi (Ä°ngilizce haliyle machine learning, kÄąsaca **ML**), yapay zekanÄąn Ãļnemli bir alt kÃŧmesidir. **ML, mantÄąklÄą karar verme sÃŧrecini desteklemek için anlamlÄą bilgileri ortaya Ã§Äąkarmak ve algÄąlanan verilerden gizli kalÄąplarÄą bulmak için Ãļzel algoritmalar kullanmakla ilgilenir**. - -![AI, ML, derin Ãļğrenme, veri bilimi](../images/ai-ml-ds.png) - -> Yapay zeka, makine Ãļğrenimi, derin Ãļğrenme ve veri bilimi arasÄąndaki ilişkileri gÃļsteren bir diyagram. Bu infografik, [şu grafikten](https://softwareengineering.stackexchange.com/questions/366996/distinction-between-ai-ml-neural-networks-) ilham alan [Jen Looper](https://twitter.com/jenlooper) tarafÄąndan hazÄąrlanmÄąÅŸtÄąr. - -> AI (Artificial Intelligence): Yapay zekÃĸ -> ML(Machine Learning): Makine Ãļğrenimi -> Deep Learning: Derin Öğrenme -> Data Science: Veri bilimi - -## Bu kursta neler Ãļğreneceksiniz - -Bu mÃŧfredatta, yalnÄązca yeni başlayanlarÄąn bilmesi gereken makine Ãļğreniminin temel kavramlarÄąnÄą ele alacağız. 'Klasik makine Ãļğrenimi' dediğimiz şeyi, Ãļncelikle birçok Ãļğrencinin temel bilgileri Ãļğrenmek için kullandığı mÃŧkemmel bir kÃŧtÃŧphane olan Scikit-learn'Ãŧ kullanarak ele alÄąyoruz. Daha geniş yapay zeka veya derin Ãļğrenme kavramlarÄąnÄą anlamak için, gÃŧçlÃŧ bir temel makine Ãļğrenimi bilgisi vazgeçilmezdir ve bu yÃŧzden onu burada sunmak istiyoruz. - -Bu kursta şunlarÄą Ãļğreneceksiniz: - -- makine Ãļğreniminin temel kavramlarÄą -- ML'nin tarihi -- ML ve adillik -- regresyon ML teknikleri -- sÄąnÄąflandÄąrma ML teknikleri -- kÃŧmeleme ML teknikleri -- doğal dil işleme ML teknikleri -- zaman serisi tahmini ML teknikleri -- pekiştirmeli Ãļğrenme -- ML için gerçek-dÃŧnya uygulamalarÄą - -## Neyi kapsamayacağız - -- derin Ãļğrenme -- sinir ağlarÄą -- yapay zeka - -Daha iyi bir Ãļğrenme deneyimi sağlamak için, farklÄą bir mÃŧfredatta tartÄąÅŸacağımÄąz sinir ağlarÄą, 'derin Ãļğrenme' (sinir ağlarÄąnÄą kullanarak çok katmanlÄą modeller oluşturma) ve yapay zekÃĸnÄąn karmaÅŸÄąklÄąklarÄąndan kaÃ§Äąnacağız. AyrÄąca, bu daha geniş alanÄąn bu yÃļnÃŧne odaklanmak için yakÄąnda Ã§Äąkacak bir veri bilimi mÃŧfredatÄą sunacağız. - -## Neden makine Ãļğrenimi Ãŧzerinde çalÄąÅŸmalÄąsÄąnÄąz? - -Sistemler perspektifinden makine Ãļğrenimi, akÄąllÄą kararlar almaya yardÄąmcÄą olmak için verilerden gizli kalÄąplarÄą Ãļğrenebilen otomatik sistemlerin oluşturulmasÄą olarak tanÄąmlanÄąr. - -Bu motivasyon, insan beyninin dÄąÅŸ dÃŧnyadan algÄąladığı verilere dayanarak belirli şeyleri nasÄąl Ãļğrendiğinden bir miktar esinlenmiştir. - -✅ Bir işletmenin, sabit kurallara dayalÄą bir karar aracÄą oluşturmak yerine neden makine Ãļğrenimi stratejilerini kullanmayÄą denemek isteyebileceklerini bir an için dÃŧşÃŧnÃŧn. - -### Makine Ãļğrenimi uygulamalarÄą - -Makine Ãļğrenimi uygulamalarÄą artÄąk neredeyse her yerde ve akÄąllÄą telefonlarÄąmÄąz, internete bağlÄą cihazlarÄąmÄąz ve diğer sistemlerimiz tarafÄąndan Ãŧretilen, toplumlarÄąmÄązda akan veriler kadar yaygÄąn hale gelmiş durumda. Son teknoloji makine Ãļğrenimi algoritmalarÄąnÄąn muazzam potansiyelini gÃļz ÃļnÃŧnde bulunduran araştÄąrmacÄąlar, bu algoritmalarÄąn çok boyutlu ve çok disiplinli gerçek hayat problemlerini çÃļzme yeteneklerini araştÄąrÄąyorlar ve oldukça olumlu sonuçlar alÄąyorlar. - -**Makine Ãļğrenimini birçok şekilde kullanabilirsiniz**: - -- Bir hastanÄąn tÄąbbi geçmişinden veya raporlarÄąndan hastalÄąk olasÄąlığınÄą tahmin etmek -- Hava olaylarÄąnÄą tahmin etmek için hava durumu verilerini kullanmak -- Bir metnin duygu durumunu anlamak -- PropagandanÄąn yayÄąlmasÄąnÄą durdurmak için sahte haberleri tespit etmek - -Finans, ekonomi, yer bilimi, uzay araştÄąrmalarÄą, biyomedikal mÃŧhendislik, bilişsel bilim ve hatta beşeri bilimlerdeki alanlar, kendi alanlarÄąnÄąn zorlu ve ağır veri işleme sorunlarÄąnÄą çÃļzmek için makine Ãļğrenimini tekniklerini kullanmaya başladÄąlar. - -Makine Ãļğrenimi, gerçek dÃŧnyadan veya oluşturulan verilerden anlamlÄą içgÃļrÃŧler bularak ÃļrÃŧntÃŧ bulma sÃŧrecini otomatikleştirir. Diğerlerinin yanÄą sÄąra iş, sağlÄąk ve finansal uygulamalarda son derece değerli olduğunu kanÄątlamÄąÅŸtÄąr. - -YakÄąn gelecekte, yaygÄąn olarak benimsenmesi nedeniyle makine Ãļğreniminin temellerini anlamak, tÃŧm alanlardan insanlar için bir zorunluluk olacak. - ---- -## 🚀 Meydan Okuma - -Kağıt Ãŧzerinde veya [Excalidraw](https://excalidraw.com/) gibi çevrimiçi bir uygulama kullanarak AI, makine Ãļğrenimi, derin Ãļğrenme ve veri bilimi arasÄąndaki farklarÄą anladığınÄązdan emin olun. Bu tekniklerin her birinin çÃļzmede iyi olduğu bazÄą problem fikirleri ekleyin. - -## [Ders sonrasÄą test](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/2?loc=tr) - -## Ä°nceleme ve Bireysel ÇalÄąÅŸma - -Bulutta makine Ãļğrenimi algoritmalarÄąyla nasÄąl çalÄąÅŸabileceğiniz hakkÄąnda daha fazla bilgi edinmek için bu [Eğitim PatikasÄąnÄą](https://docs.microsoft.com/learn/paths/create-no-code-predictive-models-azure-machine-learning/?WT.mc_id=academic-77952-leestott) izleyin. - -## Ödev - -[Haydi başlayalÄąm!](assignment.tr.md) \ No newline at end of file diff --git a/1-Introduction/1-intro-to-ML/translations/README.zh-cn.md b/1-Introduction/1-intro-to-ML/translations/README.zh-cn.md deleted file mode 100644 index e919ff02..00000000 --- a/1-Introduction/1-intro-to-ML/translations/README.zh-cn.md +++ /dev/null @@ -1,107 +0,0 @@ -# æœē器å­Ļäš äģ‹įģ - -[![æœē器å­Ļäš īŧŒäēēåˇĨæ™ēčƒŊīŧŒæˇąåēĻå­Ļäš -有äģ€äšˆåŒēåˆĢ?](https://img.youtube.com/vi/lTd9RSxS9ZE/0.jpg)](https://youtu.be/lTd9RSxS9ZE "æœē器å­Ļäš īŧŒäēēåˇĨæ™ēčƒŊīŧŒæˇąåēĻå­Ļäš -有äģ€äšˆåŒēåˆĢ?") - -> đŸŽĨ į‚šå‡ģ上éĸįš„回į‰‡č§‚įœ‹čŽ¨čŽēæœē器å­Ļ䚠、äēēåˇĨæ™ēčƒŊå’ŒæˇąåēĻå­Ļ习之间åŒēåˆĢįš„视éĸ‘。 - -## [č¯žå‰æĩ‹éĒŒ](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/1/) - -### äģ‹įģ - -æŦĸčŋŽæĨ到čŋ™ä¸Ēįģå…¸æœē器å­Ļäš įš„初å­Ļč€…č¯žį¨‹īŧæ— čŽēäŊ æ˜¯čŋ™ä¸Ēä¸ģéĸ˜įš„新手īŧŒčŋ˜æ˜¯ä¸€ä¸Ē有įģéĒŒįš„ ML äģŽä¸šč€…īŧŒæˆ‘äģŦéƒŊ垈éĢ˜å…´äŊ čƒŊ加å…Ĩ我äģŦīŧæˆ‘äģŦ希望ä¸ēäŊ įš„ ML į ”įŠļ创åģē一ä¸ĒåĨŊįš„åŧ€å§‹īŧŒåšļåžˆäšæ„č¯„äŧ°ã€å›žåē”å’ŒæŽĨ受äŊ įš„[反éĻˆ](https://github.com/microsoft/ML-For-Beginners/discussions)。 - -[![æœē器å­Ļäš įŽ€äģ‹](https://img.youtube.com/vi/h0e2HAPTGF4/0.jpg)](https://youtu.be/h0e2HAPTGF4 "Introduction to ML") - -> đŸŽĨ 单å‡ģä¸Šå›žč§‚įœ‹č§†éĸ‘īŧšéēģįœį†åˇĨå­Ļé™ĸįš„ John Guttag äģ‹įģæœē器å­Ļäš  -### æœē器å­Ļäš å…Ĩ门 - -在åŧ€å§‹æœŦč¯žį¨‹äš‹å‰īŧŒäŊ éœ€čĻčŽžįŊŽčŽĄįŽ—æœēčƒŊ在æœŦ地čŋčĄŒ Jupyter Notebooks。 - -- **按į…§čŋ™äē›č§†éĸ‘里įš„莲č§Ŗ配įŊŽäŊ įš„莥įŽ—æœē**。äē†č§Ŗ有å…ŗåĻ‚äŊ•åœ¨æ­¤[视éĸ‘集](https://www.youtube.com/playlist?list=PLlrxD0HtieHhS8VzuMCfQD4uJ9yne1mE6)中莞įŊŽčŽĄįŽ—æœēįš„更多äŋĄæ¯ã€‚ -- **å­Ļäš  Python**。 čŋ˜åģē莎äŊ å¯š [Python](https://docs.microsoft.com/learn/paths/python-language/?WT.mc_id=academic-77952-leestott) 有一ä¸ĒåŸēæœŦįš„äē†č§Ŗ。čŋ™æ˜¯æˆ‘äģŦ在æœŦč¯žį¨‹ä¸­äŊŋį”¨įš„一į§å¯šæ•°æŽį§‘å­ĻåŽļ有į”¨įš„įŧ–į¨‹č¯­č¨€ã€‚ -- **å­Ļäš  Node.js 和 JavaScript**。在æœŦč¯žį¨‹ä¸­īŧŒæˆ‘äģŦ在构åģē web åē”į”¨į¨‹åēæ—ļ也äŊŋį”¨čŋ‡å‡ æŦĄ JavaScriptīŧŒå› æ­¤äŊ éœ€čĻæœ‰ [Node.js](https://nodejs.org) 和 [npm](https://www.npmjs.com/) äģĨ及 [Visual Studio Code](https://code.visualstudio.com/) į”¨äēŽ Python 和 JavaScript åŧ€å‘。 -- **创åģē GitHub å¸æˆˇ**。æ—ĸį„ļäŊ åœ¨ [GitHub](https://github.com) 上扞到我äģŦīŧŒäŊ å¯čƒŊåˇ˛įģæœ‰äē†ä¸€ä¸Ēå¸æˆˇīŧŒäŊ†åĻ‚æžœæ˛Ąæœ‰īŧŒč¯ˇåˆ›åģē一ä¸Ēå¸æˆˇīŧŒį„ļ后 fork æ­¤č¯žį¨‹č‡ĒåˇąäŊŋį”¨(也įģ™æˆ‘äģŦ一éĸ—æ˜Ÿæ˜Ÿå§đŸ˜Š) -- **æŽĸį´ĸ Scikit-learn**. į†Ÿæ‚‰ [Scikit-learn]([https://scikit-learn.org/stable/user_guide.html)īŧŒæˆ‘äģŦ在čŋ™äē›č¯žį¨‹ä¸­åŧ•į”¨įš„一įģ„ ML åē“。 - -### äģ€äšˆæ˜¯æœē器å­Ļäš īŧŸ - -æœ¯č¯­â€œæœē器å­Ļ䚠”是åŊ“äģŠæœ€æĩčĄŒå’Œæœ€å¸¸į”¨įš„æœ¯č¯­äš‹ä¸€ã€‚ åĻ‚æžœäŊ å¯šį§‘技有某į§į¨‹åēĻįš„į†Ÿæ‚‰īŧŒé‚Ŗ䚈垈可čƒŊäŊ č‡ŗ少åŦč¯´čŋ‡čŋ™ä¸Ēæœ¯č¯­ä¸€æŦĄīŧŒæ— čŽēäŊ åœ¨å“Ēä¸Ēéĸ†åŸŸåˇĨäŊœã€‚į„ļ而īŧŒæœē器å­Ļäš įš„æœēåˆļ寚大多数äēēæĨč¯´æ˜¯ä¸€ä¸Ēč°œã€‚ 寚äēŽæœē器å­Ļ䚠初å­Ļ者æĨč¯´īŧŒčŋ™ä¸Ēä¸ģéĸ˜æœ‰æ—ļäŧščŽŠäēē感到不įŸĨ所æŽĒ。 因此īŧŒäē†č§Ŗæœē器å­Ļäš įš„åŽžč´¨æ˜¯äģ€äšˆīŧŒåšļ通čŋ‡åŽžäž‹ä¸€æ­Ĩ一æ­Ĩ地äē†č§Ŗæœē器å­Ļ䚠是垈重čĻįš„。 - -![æœē器å­Ļäš čļ‹åŠŋæ›˛įēŋ](../images/hype.png) - -> č°ˇæ­Œčļ‹åŠŋ昞į¤ēäē†â€œæœē器å­Ļäš â€ä¸€č¯æœ€čŋ‘įš„“čļ‹åŠŋæ›˛įēŋ” - -我äģŦį”Ÿæ´ģ在一ä¸Ē充æģĄčŋˇäēēåĨĨį§˜įš„åŽ‡åŽ™ä¸­ã€‚åƒå˛č’‚čŠŦÂˇéœé‡‘ã€é˜ŋ尔äŧ¯į‰šÂˇįˆąå› æ–¯åĻį­‰äŧŸå¤§įš„į§‘å­ĻåŽļīŧŒäģĨ及更多įš„äēēīŧŒéƒŊč‡´åŠ›äēŽå¯ģ扞有意䚉įš„äŋĄæ¯īŧŒæ­į¤ē我äģŦ周围世į•Œįš„åĨĨį§˜ã€‚čŋ™å°ąæ˜¯äēēįąģå­Ļäš įš„æĄäģļīŧšä¸€ä¸Ēäēēįąģįš„孊子在é•ŋ大成äēēįš„čŋ‡į¨‹ä¸­īŧŒä¸€åš´åˆä¸€åš´åœ°å­Ļäš æ–°äē‹į‰Šåšļ揭į¤ē世į•Œįš„įģ“构。 - -孊子įš„å¤§č„‘å’Œæ„ŸåŽ˜æ„ŸįŸĨ到周围įš„äē‹åŽžīŧŒåšļ逐渐å­Ļ习隐藏įš„į”Ÿæ´ģæ¨ĄåŧīŧŒčŋ™æœ‰åŠŠäēŽå­Šå­åˆļ厚é€ģčž‘č§„åˆ™æĨč¯†åˆĢå­Ļäš æ¨Ąåŧã€‚äēēįąģå¤§č„‘įš„å­Ļäš čŋ‡į¨‹äŊŋäēēįąģ成ä¸ē世į•Œä¸Šæœ€å¤æ‚įš„į”Ÿį‰Šã€‚不断地å­Ļäš īŧŒé€ščŋ‡å‘įŽ°éšč—įš„æ¨ĄåŧīŧŒį„ļ后寚čŋ™äē›æ¨Ąåŧčŋ›čĄŒåˆ›æ–°īŧŒäŊŋ我äģŦčƒŊ够äŊŋč‡Ēåˇąåœ¨ä¸€į”Ÿä¸­å˜åž—čļŠæĨčļŠåĨŊ。čŋ™į§å­Ļäš čƒŊ力和čŋ›åŒ–čƒŊ力与一ä¸ĒåĢ做[å¤§č„‘å¯åĄ‘æ€§](https://www.simplypsychology.org/brain-plasticity.html)įš„æĻ‚åŋĩ有å…ŗ。äģŽčĄ¨éĸ上įœ‹īŧŒæˆ‘äģŦ可äģĨ在äēē脑įš„å­Ļäš čŋ‡į¨‹å’Œæœē器å­Ļäš įš„æĻ‚åŋĩ䚋间扞到一äē›åŠ¨æœē上įš„į›¸äŧŧ䚋处。 - -[äēē脑](https://www.livescience.com/29365-human-brain.html) äģŽįŽ°åŽžä¸–į•Œä¸­æ„ŸįŸĨäē‹į‰ŠīŧŒå¤„į†æ„ŸįŸĨ到įš„äŋĄæ¯īŧŒåšå‡ēį†æ€§įš„å†ŗ厚īŧŒåšļ栚捎įŽ¯åĸƒæ‰§čĄŒæŸäē›čĄŒåŠ¨ã€‚čŋ™å°ąæ˜¯æˆ‘äģŦæ‰€č¯´įš„æ™ēčƒŊ行ä¸ē。åŊ“我äģŦ将æ™ēčƒŊ行ä¸ēčŋ‡į¨‹įš„复åˆļ品įŧ–į¨‹åˆ°čŽĄįŽ—æœē上æ—ļīŧŒåŽƒčĸĢį§°ä¸ēäēēåˇĨæ™ēčƒŊ (AI)。 - -å°ŊįŽĄčŋ™äē›æœ¯č¯­å¯čƒŊäŧšæˇˇæˇ†īŧŒäŊ†æœē器å­Ļäš  (ML) 是äēēåˇĨæ™ēčƒŊįš„一ä¸Ē重čĻå­é›†ã€‚ **æœē器å­Ļäš å…ŗæŗ¨äŊŋį”¨ä¸“é—¨įš„įŽ—æŗ•æĨ发įŽ°æœ‰æ„äš‰įš„äŋĄæ¯īŧŒåšļäģŽæ„ŸįŸĨæ•°æŽä¸­æ‰žåˆ°éšč—įš„æ¨ĄåŧīŧŒäģĨč¯åŽžį†æ€§įš„å†ŗį­–čŋ‡į¨‹**。 - -![äēēåˇĨæ™ēčƒŊ、æœē器å­Ļäš ã€æˇąåēĻå­Ļ䚠、数捎į§‘å­Ļ](../images/ai-ml-ds.png) - -> 昞į¤ē AI、MLã€æˇąåēĻå­Ļ䚠和数捎į§‘å­Ļ之间å…ŗįŗģįš„å›žčĄ¨ã€‚å›žį‰‡äŊœč€… [Jen Looper](https://twitter.com/jenlooper)īŧŒįĩ感æĨč‡Ē[čŋ™åŧ å›ž](https://softwareengineering.stackexchange.com/questions/366996/distinction-between-ai-ml-neural-networks-deep-learning-and-data-mining) - -## äŊ å°†åœ¨æœŦč¯žį¨‹ä¸­å­Ļ到äģ€äšˆ - -在æœŦč¯žį¨‹ä¸­īŧŒæˆ‘äģŦ将äģ…æļĩį›–初å­Ļ者åŋ…éĄģäē†č§Ŗįš„æœē器å­Ļäš įš„æ ¸åŋƒæĻ‚åŋĩ。 我äģŦä¸ģčĻäŊŋį”¨ Scikit-learn æĨäģ‹įģæˆ‘äģŦæ‰€č°“įš„“įģå…¸æœē器å­Ļ习”īŧŒčŋ™æ˜¯ä¸€ä¸ĒčŽ¸å¤šå­Ļį”Ÿį”¨æĨå­Ļäš åŸēįĄ€įŸĨč¯†įš„äŧ˜į§€åē“。čĻį†č§Ŗ更åšŋæŗ›įš„äēēåˇĨæ™ēčƒŊæˆ–æˇąåēĻå­Ļäš įš„æĻ‚åŋĩīŧŒæœē器å­Ļäš įš„åŸēįĄ€įŸĨč¯†æ˜¯åŋ…不可少įš„īŧŒæ‰€äģĨ我äģŦæƒŗ在čŋ™é‡Œæäž›åŽƒã€‚ - -在æœŦč¯žį¨‹ä¸­īŧŒäŊ å°†å­Ļäš īŧš - -- æœē器å­Ļäš įš„æ ¸åŋƒæĻ‚åŋĩ -- æœē器å­Ļäš įš„åŽ†å˛ -- æœē器å­Ļäš å’Œå…Ŧåšŗ性 -- 回åŊ’ -- 分įąģ -- 聚įąģ -- č‡Ēį„ļč¯­č¨€å¤„į† -- æ—ļåēéĸ„æĩ‹ -- åŧē化å­Ļäš  -- æœē器å­Ļäš įš„厞际åē”į”¨ -## 我äģŦ不äŧšæļĩį›–įš„内厚 - -- æˇąåēĻå­Ļäš  -- įĨžįģįŊ‘įģœ -- AI - -ä¸ēäē†čŽˇåž—æ›´åĨŊįš„å­Ļäš äŊ“éĒŒīŧŒæˆ‘äģŦ将éŋ免įĨžįģįŊ‘įģœã€â€œæˇąåēĻå­Ļ习”īŧˆäŊŋį”¨įĨžįģįŊ‘įģœįš„å¤šåą‚æ¨Ąåž‹æž„åģēīŧ‰å’ŒäēēåˇĨæ™ēčƒŊįš„复杂性īŧŒæˆ‘äģŦ将在不同įš„č¯žį¨‹ä¸­čŽ¨čŽēčŋ™äē›é—Žéĸ˜ã€‚ 我äģŦčŋ˜å°†æäž›åŗ将推å‡ēįš„数捎į§‘å­Ļč¯žį¨‹īŧŒäģĨ专æŗ¨äēŽčŋ™ä¸Ē更大éĸ†åŸŸįš„čŋ™ä¸€æ–šéĸ。 -## ä¸ēäģ€äšˆčĻå­Ļäš æœē器å­Ļäš īŧŸ - -äģŽįŗģįģŸįš„角åēĻæĨįœ‹īŧŒæœē器å­Ļäš čĸĢ厚䚉ä¸ē创åģē可äģĨäģŽæ•°æŽä¸­å­Ļäš éšč—æ¨ĄåŧäģĨ帎劊做å‡ēæ™ēčƒŊå†ŗį­–įš„č‡Ē动化įŗģįģŸã€‚ - -čŋ™į§åŠ¨æœēå¤§č‡´æ˜¯å—äēē脑åĻ‚äŊ•æ šæŽåŽƒäģŽå¤–部世į•Œæ„ŸįŸĨ到įš„数捎æĨå­Ļ䚠某äē›ä¸œčĨŋįš„启发。 - -✅ æƒŗ一æƒŗä¸ēäģ€äšˆäŧä¸šæƒŗčĻå°č¯•äŊŋį”¨æœē器å­Ļäš į­–į•Ĩč€Œä¸æ˜¯åˆ›åģēåŸēäēŽįĄŦįŧ–į įš„č§„åˆ™åŧ•æ“Žã€‚ - -### æœē器å­Ļäš įš„åē”į”¨ - -æœē器å­Ļäš įš„åē”į”¨įŽ°åœ¨å‡ äšŽæ— å¤„不在īŧŒå°ąåƒæˆ‘äģŦįš„æ™ēčƒŊ手æœē、äē’č”čŽžå¤‡å’Œå…ļäģ–įŗģįģŸäē§į”Ÿįš„æ•°æŽä¸€æ ˇæ— å¤„ä¸åœ¨ã€‚č€ƒč™‘åˆ°æœ€å…ˆčŋ›įš„æœē器å­Ļäš įŽ—æŗ•įš„åˇ¨å¤§æŊœåŠ›īŧŒį ”įŠļäēē员一į›´åœ¨æŽĸį´ĸå…ļč§Ŗå†ŗ多įģ´å¤šå­Ļį§‘įŽ°åŽžé—Žéĸ˜įš„čƒŊ力īŧŒåšļ取垗äē†åˇ¨å¤§įš„į§¯æžæˆæžœã€‚ - -**äŊ å¯äģĨ在垈多斚éĸäŊŋį”¨æœē器å­Ļäš **: - -- 栚捎į—…äēēįš„į—…å˛æˆ–æŠĨ告æĨéĸ„æĩ‹æ‚Ŗį—…įš„可čƒŊ性。 -- 刊į”¨å¤Šæ°”数捎éĸ„æĩ‹å¤Šæ°”。 -- į†č§Ŗ文æœŦįš„情感。 -- æŖ€æĩ‹å‡æ–°é—ģäģĨé˜ģæ­ĸå…ļäŧ æ’­ã€‚ - -é‡‘čžã€įģæĩŽå­Ļ、地įƒį§‘å­Ļ、å¤ĒįŠēæŽĸį´ĸ、į”Ÿį‰ŠåŒģå­ĻåˇĨį¨‹ã€čŽ¤įŸĨį§‘å­ĻīŧŒį”šč‡ŗäēē文å­Ļį§‘éĸ†åŸŸéƒŊ采į”¨æœē器å­Ļäš æĨč§Ŗå†ŗå…ļéĸ†åŸŸä¸­č‰°åˇ¨įš„、数捎处į†įšé‡įš„é—Žéĸ˜ã€‚ - -æœē器å­Ļ习通čŋ‡äģŽįœŸåŽžä¸–į•Œæˆ–į”Ÿæˆįš„数捎中发įŽ°æœ‰æ„äš‰įš„见č§ŖīŧŒč‡Ē动化äē†æ¨Ąåŧå‘įŽ°įš„čŋ‡į¨‹ã€‚äē‹åŽžč¯æ˜ŽīŧŒåŽƒåœ¨å•†ä¸šã€åĨåēˇå’Œé‡‘辍åē”į”¨į­‰æ–šéĸå…ˇæœ‰åžˆéĢ˜įš„äģˇå€ŧ。 - -在不䚅įš„å°†æĨīŧŒį”ąäēŽæœē器å­Ļäš įš„åšŋæŗ›åē”į”¨īŧŒäē†č§Ŗæœē器å­Ļäš įš„åŸēįĄ€įŸĨč¯†å°†æˆä¸ēäģģäŊ•éĸ†åŸŸįš„äēēäģŦįš„åŋ…äŋŽč¯žã€‚ - ---- -## 🚀 挑战 - -在įē¸ä¸Šæˆ–äŊŋį”¨ [Excalidraw](https://excalidraw.com/) į­‰åœ¨įēŋåē”į”¨į¨‹åēįģ˜åˆļč‰å›žīŧŒäē†č§ŖäŊ å¯š AI、MLã€æˇąåēĻå­Ļ䚠和数捎į§‘å­Ļäš‹é—´åˇŽåŧ‚įš„į†č§Ŗ。æˇģ加一äē›å…ŗäēŽčŋ™äē›æŠ€æœ¯æ“…é•ŋč§Ŗå†ŗįš„é—Žéĸ˜įš„æƒŗæŗ•ã€‚ - -## [阅č¯ģ后æĩ‹éĒŒ](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/2/) - -## 复䚠与č‡Ēå­Ļ - -čĻäē†č§Ŗ有å…ŗåĻ‚äŊ•åœ¨äē‘中äŊŋį”¨ ML įŽ—æŗ•įš„更多äŋĄæ¯īŧŒč¯ˇéĩåžĒäģĨ下[å­Ļäš čˇ¯åž„](https://docs.microsoft.com/learn/paths/create-no-code-predictive-models-azure-machine-learning/?WT.mc_id=academic-77952-leestott)。 - -## äģģåŠĄ - -[启动åšļčŋčĄŒ](assignment.zh-cn.md) diff --git a/1-Introduction/1-intro-to-ML/translations/README.zh-tw.md b/1-Introduction/1-intro-to-ML/translations/README.zh-tw.md deleted file mode 100644 index bac84df3..00000000 --- a/1-Introduction/1-intro-to-ML/translations/README.zh-tw.md +++ /dev/null @@ -1,103 +0,0 @@ -# 抟器學įŋ’äģ‹į´š - -[![抟器學įŋ’īŧŒäēēåˇĨæ™ēčƒŊīŧŒæˇąåēĻå­¸įŋ’-有äģ€éēŊ區åˆĨ?](https://img.youtube.com/vi/lTd9RSxS9ZE/0.jpg)](https://youtu.be/lTd9RSxS9ZE "抟器學įŋ’īŧŒäēēåˇĨæ™ēčƒŊīŧŒæˇąåēĻå­¸įŋ’-有äģ€éēŊ區åˆĨ?") - -> đŸŽĨ éģžæ“Šä¸Šéĸįš„圖į‰‡č§€įœ‹č¨ŽčĢ–抟器學įŋ’、äēēåˇĨæ™ēčƒŊå’ŒæˇąåēĻå­¸įŋ’䚋間區åˆĨįš„čĻ–é ģ。 -## [čĒ˛å‰æ¸Ŧ驗](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/1/) - -### äģ‹į´š - -æ­ĄčŋŽäž†åˆ°é€™å€‹įļ“典抟器學įŋ’įš„åˆå­¸č€…čĒ˛į¨‹īŧį„ĄčĢ–äŊ æ˜¯é€™å€‹ä¸ģ題įš„新手īŧŒé‚„是一個有įļ“銗įš„ ML åžžæĨ­č€…īŧŒæˆ‘們éƒŊ垈éĢ˜čˆˆäŊ čƒŊ加å…Ĩ我們īŧæˆ‘們希望į‚ēäŊ įš„ ML į ”įŠļå‰ĩåģē一個åĨŊįš„開始īŧŒä¸Ļåžˆæ¨‚æ„čŠ•äŧ°ã€å›žæ‡‰å’ŒæŽĨ受äŊ įš„[反éĨ‹](https://github.com/microsoft/ML-For-Beginners/discussions)。 - -[![抟器學įŋ’į°Ąäģ‹](https://img.youtube.com/vi/h0e2HAPTGF4/0.jpg)](https://youtu.be/h0e2HAPTGF4 "Introduction to ML") - -> đŸŽĨ å–Žæ“Šä¸Šåœ–č§€įœ‹čĻ–é ģīŧšéēģįœį†åˇĨå­¸é™ĸįš„ John Guttag äģ‹į´šæŠŸå™¨å­¸įŋ’ -### 抟器學įŋ’å…Ĩ門 -在開始æœŦčĒ˛į¨‹äš‹å‰īŧŒäŊ éœ€čĻč¨­įŊŽč¨ˆįŽ—抟čƒŊ在æœŦåœ°é‹čĄŒ Jupyter Notebooks。 - -- **按į…§é€™äē›čĻ–é ģčŖįš„čŦ›č§Ŗ配įŊŽäŊ įš„č¨ˆįŽ—抟**。äē†č§Ŗ有關åĻ‚äŊ•åœ¨æ­¤[čĻ–é ģ集](https://www.youtube.com/playlist?list=PLlrxD0HtieHhS8VzuMCfQD4uJ9yne1mE6)中設įŊŽč¨ˆįŽ—抟įš„更多äŋĄæ¯ã€‚ -- **å­¸įŋ’ Python**。 還åģēč­°äŊ å° [Python](https://docs.microsoft.com/learn/paths/python-language/?WT.mc_id=academic-77952-leestott) 有一個åŸēæœŦįš„äē†č§Ŗ。這是我們在æœŦčĒ˛į¨‹ä¸­äŊŋį”¨įš„一į¨Žå°æ•¸æ“šį§‘å­¸åŽļ有į”¨įš„įˇ¨į¨‹čĒžč¨€ã€‚ -- **å­¸įŋ’ Node.js 和 JavaScript**。在æœŦčĒ˛į¨‹ä¸­īŧŒæˆ‘們在構åģē web 應į”¨į¨‹åēæ™‚䚟äŊŋį”¨éŽåšžæŦĄ JavaScriptīŧŒå› æ­¤äŊ éœ€čĻæœ‰ [Node.js](https://nodejs.org) 和 [npm](https://www.npmjs.com/) äģĨ及 [Visual Studio Code](https://code.visualstudio.com/) į”¨æ–ŧ Python 和 JavaScript 開į™ŧ。 -- **å‰ĩåģē GitHub å¸ŗæˆļ**。æ—ĸį„ļäŊ åœ¨ [GitHub](https://github.com) 上扞到我們īŧŒäŊ å¯čƒŊåˇ˛įļ“有äē†ä¸€å€‹å¸ŗæˆļīŧŒäŊ†åĻ‚æžœæ˛’æœ‰īŧŒčĢ‹å‰ĩåģē一個å¸ŗæˆļīŧŒį„ļ垌 fork æ­¤čĒ˛į¨‹č‡ĒåˇąäŊŋį”¨(也įĩĻæˆ‘å€‘ä¸€éĄ†æ˜Ÿæ˜Ÿå§đŸ˜Š) -- **æŽĸį´ĸ Scikit-learn**. į†Ÿæ‚‰ [Scikit-learn]([https://scikit-learn.org/stable/user_guide.html)īŧŒæˆ‘們在這äē›čĒ˛į¨‹ä¸­åŧ•į”¨įš„一įĩ„ ML åēĢ。 - -### äģ€éēŊ是抟器學įŋ’īŧŸ - -術čĒžã€ŒæŠŸå™¨å­¸įŋ’」是į•ļäģŠæœ€æĩčĄŒå’Œæœ€å¸¸į”¨įš„襓čĒžäš‹ä¸€ã€‚ åĻ‚æžœäŊ å°į§‘技有某į¨Žį¨‹åēĻįš„į†Ÿæ‚‰īŧŒé‚ŖéēŊ垈可čƒŊäŊ č‡ŗ少čŊčĒĒéŽé€™å€‹čĄ“čĒžä¸€æŦĄīŧŒį„ĄčĢ–äŊ åœ¨å“Ē個領域åˇĨäŊœã€‚į„ļ而īŧŒæŠŸå™¨å­¸įŋ’įš„抟čŖŊ對大多數äēē來čĒĒ是一個čŦŽã€‚ 對æ–ŧ抟器學įŋ’åˆå­¸č€…äž†čĒĒīŧŒé€™å€‹ä¸ģéĄŒæœ‰æ™‚æœƒčŽ“äēē感到不įŸĨ所æŽĒ。 因此īŧŒäē†č§Ŗ抟器學įŋ’įš„å¯ĻčŗĒ是äģ€éēŊīŧŒä¸Ļ通過å¯Ļ例一æ­Ĩ一æ­Ĩ地äē†č§Ŗ抟器學įŋ’是垈重čĻįš„。 - -![抟器學įŋ’čļ¨å‹ĸæ›˛įˇš](../images/hype.png) - -> č°ˇæ­Œčļ¨å‹ĸéĄ¯į¤ēäē†ã€ŒæŠŸå™¨å­¸įŋ’ã€ä¸€čŠžæœ€čŋ‘įš„「čļ¨å‹ĸæ›˛įˇšã€ -我們į”Ÿæ´ģ在一個充æģŋčŋˇäēēåĨ§į§˜įš„åŽ‡åŽ™ä¸­ã€‚åƒå˛č’‚čŠŦÂˇéœé‡‘ã€é˜ŋįˆžäŧ¯į‰šÂˇæ„›å› æ–¯åĻį­‰å‰å¤§įš„į§‘å­¸åŽļīŧŒäģĨ及更多įš„äēēīŧŒéƒŊč‡´åŠ›æ–ŧ尋扞有意įžŠįš„äŋĄæ¯īŧŒæ­į¤ē我們周圍世į•Œįš„åĨ§į§˜ã€‚é€™å°ąæ˜¯äēēéĄžå­¸įŋ’įš„æĸäģļīŧšä¸€å€‹äēē類įš„å­Šå­åœ¨é•ˇå¤§æˆäēēįš„過į¨‹ä¸­īŧŒä¸€åš´åˆä¸€åš´åœ°å­¸įŋ’æ–°äē‹į‰Šä¸Ļ揭į¤ē世į•Œįš„įĩæ§‹ã€‚ - -孊子įš„大č…Ļ和感厘感įŸĨ到周圍įš„äē‹å¯ĻīŧŒä¸Ļ逐æŧ¸å­¸įŋ’éšąč—įš„į”Ÿæ´ģæ¨ĄåŧīŧŒé€™æœ‰åŠŠæ–ŧ孊子čŖŊ厚邏čŧ¯čĻå‰‡äž†č­˜åˆĨå­¸įŋ’æ¨Ąåŧã€‚äēēéĄžå¤§č…Ļįš„å­¸įŋ’過į¨‹äŊŋäēēéĄžæˆį‚ē世į•Œä¸Šæœ€åžŠé›œįš„į”Ÿį‰Šã€‚ä¸æ–ˇåœ°å­¸įŋ’īŧŒé€šéŽį™ŧįžéšąč—įš„æ¨ĄåŧīŧŒį„ļ垌對這äē›æ¨Ąåŧé€˛čĄŒå‰ĩ新īŧŒäŊŋ我們čƒŊ夠äŊŋč‡Ēåˇąåœ¨ä¸€į”Ÿä¸­čŽŠåž—čļŠäž†čļŠåĨŊ。這į¨Žå­¸įŋ’čƒŊåŠ›å’Œé€˛åŒ–čƒŊåŠ›čˆ‡ä¸€å€‹åĢ做[大č…Ļå¯åĄ‘æ€§](https://www.simplypsychology.org/brain-plasticity.html)įš„æĻ‚åŋĩæœ‰é—œã€‚åžžčĄ¨éĸ上įœ‹īŧŒæˆ‘們可äģĨ在äēēč…Ļįš„å­¸įŋ’過į¨‹å’ŒæŠŸå™¨å­¸įŋ’įš„æĻ‚åŋĩ䚋間扞到一äē›å‹•æŠŸä¸Šįš„į›¸äŧŧäš‹č™•ã€‚ - -[äēēč…Ļ](https://www.livescience.com/29365-human-brain.html) åžžįžå¯Ļ世į•Œä¸­æ„ŸįŸĨäē‹į‰ŠīŧŒč™•į†æ„ŸįŸĨ到įš„äŋĄæ¯īŧŒåšå‡ēį†æ€§įš„æąē厚īŧŒä¸Ļæ šæ“šį’°åĸƒåŸˇčĄŒæŸäē›čĄŒå‹•ã€‚é€™å°ąæ˜¯æˆ‘å€‘æ‰€čĒĒįš„æ™ēčƒŊ行į‚ē。į•ļ我們將æ™ēčƒŊ行į‚ē過į¨‹įš„垊čŖŊ品įˇ¨į¨‹åˆ°č¨ˆįŽ—抟上時īŧŒåŽƒčĸĢį¨ąį‚ēäēēåˇĨæ™ēčƒŊ (AI)。 - -į›ĄįŽĄé€™äē›čĄ“čĒžå¯čƒŊæœƒæˇˇæˇ†īŧŒäŊ†æŠŸå™¨å­¸įŋ’ (ML) 是äēēåˇĨæ™ēčƒŊįš„一個重čĻå­é›†ã€‚ **抟器學įŋ’é—œč¨ģäŊŋį”¨å°ˆé–€įš„įŽ—æŗ•äž†į™ŧįžæœ‰æ„įžŠįš„äŋĄæ¯īŧŒä¸Ļåžžæ„ŸįŸĨæ•¸æ“šä¸­æ‰žåˆ°éšąč—įš„æ¨ĄåŧīŧŒäģĨ證å¯Ļį†æ€§įš„æąēį­–過į¨‹**。 - -![äēēåˇĨæ™ēčƒŊ、抟器學įŋ’ã€æˇąåēĻå­¸įŋ’、數據į§‘å­¸](../images/ai-ml-ds.png) - -> éĄ¯į¤ē AI、MLã€æˇąåēĻå­¸įŋ’和數據į§‘學䚋間關įŗģįš„åœ–čĄ¨ã€‚åœ–į‰‡äŊœč€… [Jen Looper](https://twitter.com/jenlooper)īŧŒéˆæ„Ÿäž†č‡Ē[這åŧĩ圖](https://softwareengineering.stackexchange.com/questions/366996/distinction-between-ai-ml-neural-networks-deep-learning-and-data-mining) -## äŊ å°‡åœ¨æœŦčĒ˛į¨‹ä¸­å­¸åˆ°äģ€éēŊ - -在æœŦčĒ˛į¨‹ä¸­īŧŒæˆ‘們將僅æļĩč“‹åˆå­¸č€…åŋ…é ˆäē†č§Ŗįš„抟器學įŋ’įš„æ ¸åŋƒæĻ‚åŋĩ。 我們ä¸ģčĻäŊŋį”¨ Scikit-learn 來äģ‹į´šæˆ‘們所čŦ‚įš„「įļ“典抟器學įŋ’」īŧŒé€™æ˜¯ä¸€å€‹č¨ąå¤šå­¸į”Ÿį”¨äž†å­¸įŋ’åŸēį¤ŽįŸĨ識įš„å„Ēį§€åēĢ。čĻį†č§Ŗ更åģŖæŗ›įš„äēēåˇĨæ™ēčƒŊæˆ–æˇąåēĻå­¸įŋ’įš„æĻ‚åŋĩīŧŒæŠŸå™¨å­¸įŋ’įš„åŸēį¤ŽįŸĨč­˜æ˜¯åŋ…不可少įš„īŧŒæ‰€äģĨ我們æƒŗ在這čŖæäž›åŽƒã€‚ - -在æœŦčĒ˛į¨‹ä¸­īŧŒäŊ å°‡å­¸įŋ’īŧš - -- 抟器學įŋ’įš„æ ¸åŋƒæĻ‚åŋĩ -- 抟器學įŋ’įš„æ­ˇå˛ -- 抟器學įŋ’å’Œå…Ŧåšŗ性 -- 回歸 -- åˆ†éĄž -- 聚類 -- č‡Ēį„ļčĒžč¨€č™•į† -- 時åēé æ¸Ŧ -- åŧˇåŒ–å­¸įŋ’ -- 抟器學įŋ’įš„å¯Ļ際應į”¨ -## 我們不會æļĩ蓋įš„內厚 - -- æˇąåēĻå­¸įŋ’ -- įĨžįļ“įļ˛įĩĄ -- AI - -į‚ēäē†į˛åž—æ›´åĨŊįš„å­¸įŋ’éĢ”銗īŧŒæˆ‘們將éŋ免įĨžįļ“įļ˛įĩĄã€ã€ŒæˇąåēĻå­¸įŋ’」īŧˆäŊŋį”¨įĨžįļ“įļ˛įĩĄįš„å¤šåą¤æ¨Ąåž‹æ§‹åģēīŧ‰å’ŒäēēåˇĨæ™ēčƒŊįš„垊雜性īŧŒæˆ‘們將在不同įš„čĒ˛į¨‹ä¸­č¨ŽčĢ–這äē›å•éĄŒã€‚ 我們還將提䞛åŗ將推å‡ēįš„數據į§‘å­¸čĒ˛į¨‹īŧŒäģĨ專č¨ģæ–ŧ這個更大領域įš„這一斚éĸ。 -## į‚ēäģ€éēŊčĻå­¸įŋ’抟器學įŋ’īŧŸ - -åžžįŗģįĩąįš„角åēĻ來įœ‹īŧŒæŠŸå™¨å­¸įŋ’čĸĢ厚įžŠį‚ēå‰ĩåģē可äģĨ垞數據中學įŋ’éšąč—æ¨ĄåŧäģĨåšĢ劊做å‡ēæ™ēčƒŊæąēį­–įš„č‡Ē動化įŗģįĩąã€‚ - -這į¨Žå‹•æŠŸå¤§č‡´æ˜¯å—äēēč…ĻåĻ‚äŊ•æ šæ“šåŽƒåžžå¤–部世į•Œæ„ŸįŸĨ到įš„數據䞆學įŋ’某äē›æąčĨŋįš„å•Ÿį™ŧ。 - -✅ æƒŗ一æƒŗį‚ēäģ€éēŊäŧæĨ­æƒŗčĻå˜—čŠĻäŊŋį”¨æŠŸå™¨å­¸įŋ’į­–į•Ĩč€Œä¸æ˜¯å‰ĩåģēåŸēæ–ŧįĄŦįˇ¨įĸŧįš„čĻå‰‡åŧ•æ“Žã€‚ - -### 抟器學įŋ’įš„應į”¨ - -抟器學įŋ’įš„應į”¨įžåœ¨åšžäšŽį„Ąč™•ä¸åœ¨īŧŒå°ąåƒæˆ‘們įš„æ™ēčƒŊ手抟、äē’č¯č¨­å‚™å’Œå…ļäģ–įŗģįĩąį”ĸį”Ÿįš„數據一æ¨Ŗį„Ąč™•ä¸åœ¨ã€‚č€ƒæ…Žåˆ°æœ€å…ˆé€˛įš„抟器學įŋ’įŽ—æŗ•įš„åˇ¨å¤§æŊ›åŠ›īŧŒį ”įŠļäēēå“Ąä¸€į›´åœ¨æŽĸį´ĸå…ļč§Ŗæąē多įļ­å¤šå­¸į§‘įžå¯Ļå•éĄŒįš„čƒŊ力īŧŒä¸Ļ取垗äē†åˇ¨å¤§įš„įŠæĨĩ成果。 - -**äŊ å¯äģĨ在垈多斚éĸäŊŋį”¨æŠŸå™¨å­¸įŋ’**: - -- æ šæ“šį—…äēēįš„į—…å˛æˆ–å ąå‘Šäž†é æ¸Ŧæ‚Ŗį—…įš„可čƒŊ性。 -- 刊į”¨å¤Šæ°Ŗ數據預æ¸Ŧ夊æ°Ŗ。 -- į†č§Ŗ文æœŦįš„情感。 -- æĒĸæ¸Ŧå‡æ–°čžäģĨé˜ģæ­ĸå…ļå‚ŗ播。 - -é‡‘čžã€įļ“æŋŸå­¸ã€åœ°įƒį§‘學、å¤ĒįŠēæŽĸį´ĸ、į”Ÿį‰Šé†Ģå­¸åˇĨį¨‹ã€čĒįŸĨį§‘å­¸īŧŒį”šč‡ŗäēē文學į§‘領域éƒŊ采į”¨æŠŸå™¨å­¸įŋ’䞆č§Ŗæąēå…ļé ˜åŸŸä¸­č‰ąåˇ¨įš„ã€æ•¸æ“šč™•į†įšé‡įš„å•éĄŒã€‚ - -抟器學įŋ’通過垞įœŸå¯Ļ世į•Œæˆ–į”Ÿæˆįš„數據中į™ŧįžæœ‰æ„įžŠįš„čĻ‹č§ŖīŧŒč‡Ē動化äē†æ¨Ąåŧį™ŧįžįš„過į¨‹ã€‚äē‹å¯Ļč­‰æ˜ŽīŧŒåŽƒåœ¨å•†æĨ­ã€åĨåēˇå’Œé‡‘čžæ‡‰į”¨į­‰æ–šéĸå…ˇæœ‰åžˆéĢ˜įš„僚å€ŧ。 - -在不䚅įš„將䞆īŧŒį”ąæ–ŧ抟器學įŋ’įš„åģŖæŗ›æ‡‰į”¨īŧŒäē†č§Ŗ抟器學įŋ’įš„åŸēį¤ŽįŸĨč­˜å°‡æˆį‚ēäģģäŊ•é ˜åŸŸįš„äēē們įš„åŋ…äŋŽčĒ˛ã€‚ - ---- -## 🚀 挑戰 - -在į´™ä¸Šæˆ–äŊŋį”¨ [Excalidraw](https://excalidraw.com/) į­‰åœ¨įˇšæ‡‰į”¨į¨‹åēįšĒčŖŊč‰åœ–īŧŒäē†č§ŖäŊ å° AI、MLã€æˇąåēĻå­¸įŋ’和數據į§‘å­¸äš‹é–“åˇŽį•°įš„į†č§Ŗ。æˇģ加一äē›é—œæ–ŧ這äē›æŠ€čĄ“æ“…é•ˇč§Ŗæąēįš„å•éĄŒįš„æƒŗæŗ•ã€‚ - -## [é–ąčŽ€åžŒæ¸Ŧ驗](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/2/) - -## 垊įŋ’čˆ‡č‡Ēå­¸ - -čĻäē†č§Ŗ有關åĻ‚äŊ•åœ¨é›˛ä¸­äŊŋį”¨ ML įŽ—æŗ•įš„更多äŋĄæ¯īŧŒčĢ‹éĩåžĒäģĨ下[å­¸įŋ’čˇ¯åž‘](https://docs.microsoft.com/learn/paths/create-no-code-predictive-models-azure-machine-learning/?WT.mc_id=academic-77952-leestott)。 - -## äģģ務 - -[啟動ä¸Ļ運行](assignment.zh-tw.md) \ No newline at end of file diff --git a/1-Introduction/1-intro-to-ML/translations/assignment.es.md b/1-Introduction/1-intro-to-ML/translations/assignment.es.md deleted file mode 100644 index 5b428135..00000000 --- a/1-Introduction/1-intro-to-ML/translations/assignment.es.md +++ /dev/null @@ -1,9 +0,0 @@ -# LÊvantate y corre - -## Instrucciones - -En esta tarea no calificada, debe repasar Python y hacer que su entorno estÊ en funcionamiento y sea capaz de ejecutar cuadernos. - -Tome esta [Ruta de aprendizaje de Python](https://docs.microsoft.com/learn/paths/python-language/?WT.mc_id=academic-77952-leestott), y luego configure sus sistemas con estos videos introductorios: - -https://www.youtube.com/playlist?list=PLlrxD0HtieHhS8VzuMCfQD4uJ9yne1mE6 diff --git a/1-Introduction/1-intro-to-ML/translations/assignment.fr.md b/1-Introduction/1-intro-to-ML/translations/assignment.fr.md deleted file mode 100644 index b8513048..00000000 --- a/1-Introduction/1-intro-to-ML/translations/assignment.fr.md +++ /dev/null @@ -1,10 +0,0 @@ -# Être opÊrationnel - - -## Instructions - -Dans ce devoir non notÊ, vous devez vous familiariser avec Python et rendre votre environnement opÊrationnel et capable d'exÊcuter des notebook. - -Suivez ce [parcours d'apprentissage Python](https://docs.microsoft.com/learn/paths/python-language/?WT.mc_id=academic-77952-leestott), puis configurez votre système en parcourant ces vidÊos introductives : - -https://www.youtube.com/playlist?list=PLlrxD0HtieHhS8VzuMCfQD4uJ9yne1mE6 diff --git a/1-Introduction/1-intro-to-ML/translations/assignment.id.md b/1-Introduction/1-intro-to-ML/translations/assignment.id.md deleted file mode 100644 index a22848f4..00000000 --- a/1-Introduction/1-intro-to-ML/translations/assignment.id.md +++ /dev/null @@ -1,9 +0,0 @@ -# Persiapan - -## Instruksi - -Dalam tugas yang tidak dinilai ini, kamu akan mempelajari Python dan mempersiapkan *environment* kamu sehingga dapat digunakan untuk menjalankan *notebook*. - -Ambil [Jalur Belajar Python](https://docs.microsoft.com/learn/paths/python-language/?WT.mc_id=academic-77952-leestott) ini, kemudian persiapkan sistem kamu dengan menonton video-video pengantar ini: - -https://www.youtube.com/playlist?list=PLlrxD0HtieHhS8VzuMCfQD4uJ9yne1mE6 diff --git a/1-Introduction/1-intro-to-ML/translations/assignment.it.md b/1-Introduction/1-intro-to-ML/translations/assignment.it.md deleted file mode 100644 index 15c41f29..00000000 --- a/1-Introduction/1-intro-to-ML/translations/assignment.it.md +++ /dev/null @@ -1,9 +0,0 @@ -# Tempi di apprendimento brevi - -## Istruzioni - -In questo compito senza valutazione, si dovrebbe rispolverare Python e rendere il proprio ambiente attivo e funzionante, in grado di eseguire notebook. - -Si segua questo [percorso di apprendimento di Python](https://docs.microsoft.com/learn/paths/python-language/?WT.mc_id=academic-77952-leestott) e quindi si configurino i propri sistemi seguendo questi video introduttivi: - -https://www.youtube.com/playlist?list=PLlrxD0HtieHhS8VzuMCfQD4uJ9yne1mE6 diff --git a/1-Introduction/1-intro-to-ML/translations/assignment.ja.md b/1-Introduction/1-intro-to-ML/translations/assignment.ja.md deleted file mode 100644 index 4c427561..00000000 --- a/1-Introduction/1-intro-to-ML/translations/assignment.ja.md +++ /dev/null @@ -1,9 +0,0 @@ -# į¨ŧ働させる - -## 指į¤ē - -ã“ãŽčŠ•äžĄãŽãĒいčĒ˛éĄŒã§ã¯ã€PythonãĢついãĻ垊įŋ’し、į’°åĸƒã‚’į¨ŧ働させãĻノãƒŧãƒˆãƒ–ãƒƒã‚¯ã‚’åŽŸčĄŒã§ãã‚‹ã‚ˆã†ãĢするåŋ…čĻãŒã‚りぞす。 - -こぎ[Pythonナãƒŧニãƒŗグパ゚](https://docs.microsoft.com/learn/paths/python-language/?WT.mc_id=academic-77952-leestott)を受čŦ›ã—、æŦĄãŽå…Ĩ門į”¨ãƒ“デã‚ĒãĢåž“ãŖãĻã‚ˇã‚šãƒ†ãƒ ã‚’ã‚ģットã‚ĸップしãĻください。 - -https://www.youtube.com/playlist?list=PLlrxD0HtieHhS8VzuMCfQD4uJ9yne1mE6 diff --git a/1-Introduction/1-intro-to-ML/translations/assignment.ko.md b/1-Introduction/1-intro-to-ML/translations/assignment.ko.md deleted file mode 100644 index 2b8e72a8..00000000 --- a/1-Introduction/1-intro-to-ML/translations/assignment.ko.md +++ /dev/null @@ -1,9 +0,0 @@ -# ė‹œėž‘í•´ 봅ė‹œë‹¤ - -## ė„¤ëĒ… - -ė´ 미ėą„ė  ęŗŧė œė—ė„œëŠ” 파ė´ėŦ(Python)ė„ ëŗĩėŠĩ하ęŗ  Python ė‹¤í–‰ 환ę˛Ŋ ė„¤ė • 및 노트ëļ(Jupyter Notebook) ė‹¤í–‰ 방법까ė§€ ėˆ™ė§€í•´ ëŗ´ė‹œę¸¸ 바랍니다. - -다ėŒ [Python Learning Path](https://docs.microsoft.com/learn/paths/python-language/?WT.mc_id=academic-77952-leestott)ëĨŧ ė´ėˆ˜í•˜ė‹œęŗ , ė•„래 Python ėž…ëŦ¸ 강ėĸŒëĨŧ í†ĩ해 Python ė„¤ėš˜ 및 ė‹¤í–‰ 환ę˛Ŋė„ ė„¤ė •í•´ ëŗ´ė„¸ėš”: - -https://www.youtube.com/playlist?list=PLlrxD0HtieHhS8VzuMCfQD4uJ9yne1mE6 diff --git a/1-Introduction/1-intro-to-ML/translations/assignment.pt-br.md b/1-Introduction/1-intro-to-ML/translations/assignment.pt-br.md deleted file mode 100644 index 983d930f..00000000 --- a/1-Introduction/1-intro-to-ML/translations/assignment.pt-br.md +++ /dev/null @@ -1,9 +0,0 @@ -# Comece a Trabalhar - -## InstruçÃĩes - -Nesta tarefa nÃŖo corrigida, vocÃĒ deve se aprimorar em Python e colocar seu ambiente em funcionamento e capaz de executar notebooks. - -Faça o [Caminho de aprendizagem do Python](https://docs.microsoft.com/learn/paths/python-language/?WT.mc_id=academic-77952-leestott), e, em seguida, faça a configuraçÃŖo de seus sistemas analisando estes vídeos introdutÃŗrios: - -https://www.youtube.com/playlist?list=PLlrxD0HtieHhS8VzuMCfQD4uJ9yne1mE6 diff --git a/1-Introduction/1-intro-to-ML/translations/assignment.ru.md b/1-Introduction/1-intro-to-ML/translations/assignment.ru.md deleted file mode 100644 index 8a06eedb..00000000 --- a/1-Introduction/1-intro-to-ML/translations/assignment.ru.md +++ /dev/null @@ -1,9 +0,0 @@ -# НаŅŅ‚Ņ€ĐžĐšŅ‚Đĩ ŅŅ€ĐĩĐ´Ņƒ Ņ€Đ°ĐˇŅ€Đ°ĐąĐžŅ‚Đēи - -## ИĐŊŅŅ‚Ņ€ŅƒĐēŅ†Đ¸Đ¸ - -Đ­Ņ‚Đž СадаĐŊиĐĩ ĐŊĐĩ ĐžŅ†ĐĩĐŊиваĐĩŅ‚ŅŅ. ВŅ‹ Đ´ĐžĐģĐļĐŊŅ‹ ĐžŅĐ˛ĐĩĐļиŅ‚ŅŒ в ĐŋĐ°ĐŧŅŅ‚и Python и ĐŊĐ°ŅŅ‚Ņ€ĐžĐ¸Ņ‚ŅŒ ŅĐ˛ĐžŅŽ ŅŅ€ĐĩĐ´Ņƒ, Ņ‡Ņ‚ОйŅ‹ ĐžĐŊĐ° ĐŧĐžĐŗĐģĐ° СаĐŋŅƒŅĐēĐ°Ņ‚ŅŒ ĐŊĐžŅƒŅ‚ĐąŅƒĐēи. - -ВоŅĐŋĐžĐģŅŒĐˇŅƒĐšŅ‚ĐĩŅŅŒ ŅŅ‚иĐŧ ĐēŅƒŅ€ŅĐžĐŧ [Python Learning Path](https://docs.microsoft.com/learn/paths/python-language/?WT.mc_id=academic-77952-leestott), Đ° СаŅ‚ĐĩĐŧ ĐŊĐ°ŅŅ‚Ņ€ĐžĐšŅ‚Đĩ ŅĐ˛ĐžŅŽ ŅĐ¸ŅŅ‚ĐĩĐŧŅƒ, ĐŋŅ€ĐžŅĐŧĐžŅ‚Ņ€Đĩв ŅŅ‚и ввОдĐŊŅ‹Đĩ видĐĩĐž: - -https://www.youtube.com/playlist?list=PLlrxD0HtieHhS8VzuMCfQD4uJ9yne1mE6 diff --git a/1-Introduction/1-intro-to-ML/translations/assignment.tr.md b/1-Introduction/1-intro-to-ML/translations/assignment.tr.md deleted file mode 100644 index ed70c424..00000000 --- a/1-Introduction/1-intro-to-ML/translations/assignment.tr.md +++ /dev/null @@ -1,9 +0,0 @@ -# Haydi BaşlayalÄąm - -## Talimatlar - -Bu not-verilmeyen Ãļdevde, Python bilgilerinizi tazelemeli, geliştirme ortamÄąnÄązÄą çalÄąÅŸÄąr duruma getirmeli ve not defterlerini çalÄąÅŸtÄąrabilmelisiniz. - -Bu [Python Eğitim PatikasÄąnÄą](https://docs.microsoft.com/learn/paths/python-language/?WT.mc_id=academic-77952-leestott) bitirin ve ardÄąndan bu tanÄątÄąm videolarÄąnÄą izleyerek sistem kurulumunuzu yapÄąn : - -https://www.youtube.com/playlist?list=PLlrxD0HtieHhS8VzuMCfQD4uJ9yne1mE6 \ No newline at end of file diff --git a/1-Introduction/1-intro-to-ML/translations/assignment.zh-cn.md b/1-Introduction/1-intro-to-ML/translations/assignment.zh-cn.md deleted file mode 100644 index 9aa0dd28..00000000 --- a/1-Introduction/1-intro-to-ML/translations/assignment.zh-cn.md +++ /dev/null @@ -1,9 +0,0 @@ -# 启动和čŋčĄŒ - -## č¯´æ˜Ž - -在čŋ™ä¸Ēä¸č¯„åˆ†įš„äŊœä¸šä¸­īŧŒäŊ åē”č¯Ĩ渊䚠一下 PythonīŧŒå°† Python įŽ¯åĸƒčƒŊ够čŋčĄŒčĩˇæĨīŧŒåšļ且可äģĨčŋčĄŒ notebooks。 - -å­Ļäš čŋ™ä¸Ē [Python å­Ļäš čˇ¯åž„](https://docs.microsoft.com/learn/paths/python-language/?WT.mc_id=academic-77952-leestott)īŧŒį„ļ后通čŋ‡čŋ™äē›äģ‹įģæ€§įš„视éĸ‘å°†äŊ įš„įŗģįģŸįŽ¯åĸƒčŽžįŊŽåĨŊīŧš - -https://www.youtube.com/playlist?list=PLlrxD0HtieHhS8VzuMCfQD4uJ9yne1mE6 diff --git a/1-Introduction/1-intro-to-ML/translations/assignment.zh-tw.md b/1-Introduction/1-intro-to-ML/translations/assignment.zh-tw.md deleted file mode 100644 index fa913b28..00000000 --- a/1-Introduction/1-intro-to-ML/translations/assignment.zh-tw.md +++ /dev/null @@ -1,9 +0,0 @@ -# å•Ÿå‹•å’Œé‹čĄŒ - -## čĒĒ明 - -åœ¨é€™å€‹ä¸čŠ•åˆ†įš„äŊœæĨ­ä¸­īŧŒäŊ æ‡‰čŠ˛æēĢįŋ’一下 PythonīŧŒå°‡ Python į’°åĸƒčƒŊå¤ é‹čĄŒčĩˇäž†īŧŒä¸Ļ且可äģĨ運行 notebooks。 - -å­¸įŋ’這個 [Python å­¸įŋ’čˇ¯åž‘](https://docs.microsoft.com/learn/paths/python-language/?WT.mc_id=academic-77952-leestott)īŧŒį„ļ垌通過這äē›äģ‹į´šæ€§įš„čĻ–é ģ將äŊ įš„įŗģįĩąį’°åĸƒč¨­įŊŽåĨŊīŧš - -https://www.youtube.com/playlist?list=PLlrxD0HtieHhS8VzuMCfQD4uJ9yne1mE6 diff --git a/1-Introduction/2-history-of-ML/README.md b/1-Introduction/2-history-of-ML/README.md deleted file mode 100644 index 48e519e1..00000000 --- a/1-Introduction/2-history-of-ML/README.md +++ /dev/null @@ -1,150 +0,0 @@ -# History of machine learning - -![Summary of History of machine learning in a sketchnote](../../sketchnotes/ml-history.png) -> Sketchnote by [Tomomi Imura](https://www.twitter.com/girlie_mac) - -## [Pre-lecture quiz](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/3/) - ---- - -[![ML for beginners - History of Machine Learning](https://img.youtube.com/vi/N6wxM4wZ7V0/0.jpg)](https://youtu.be/N6wxM4wZ7V0 "ML for beginners - History of Machine Learning") - -> đŸŽĨ Click the image above for a short video working through this lesson. - -In this lesson, we will walk through the major milestones in the history of machine learning and artificial intelligence. - -The history of artificial intelligence (AI) as a field is intertwined with the history of machine learning, as the algorithms and computational advances that underpin ML fed into the development of AI. It is useful to remember that, while these fields as distinct areas of inquiry began to crystallize in the 1950s, important [algorithmic, statistical, mathematical, computational and technical discoveries](https://wikipedia.org/wiki/Timeline_of_machine_learning) predated and overlapped this era. In fact, people have been thinking about these questions for [hundreds of years](https://wikipedia.org/wiki/History_of_artificial_intelligence): this article discusses the historical intellectual underpinnings of the idea of a 'thinking machine.' - ---- -## Notable discoveries - -- 1763, 1812 [Bayes Theorem](https://wikipedia.org/wiki/Bayes%27_theorem) and its predecessors. This theorem and its applications underlie inference, describing the probability of an event occurring based on prior knowledge. -- 1805 [Least Square Theory](https://wikipedia.org/wiki/Least_squares) by French mathematician Adrien-Marie Legendre. This theory, which you will learn about in our Regression unit, helps in data fitting. -- 1913 [Markov Chains](https://wikipedia.org/wiki/Markov_chain), named after Russian mathematician Andrey Markov, is used to describe a sequence of possible events based on a previous state. -- 1957 [Perceptron](https://wikipedia.org/wiki/Perceptron) is a type of linear classifier invented by American psychologist Frank Rosenblatt that underlies advances in deep learning. - ---- - -- 1967 [Nearest Neighbor](https://wikipedia.org/wiki/Nearest_neighbor) is an algorithm originally designed to map routes. In an ML context it is used to detect patterns. -- 1970 [Backpropagation](https://wikipedia.org/wiki/Backpropagation) is used to train [feedforward neural networks](https://wikipedia.org/wiki/Feedforward_neural_network). -- 1982 [Recurrent Neural Networks](https://wikipedia.org/wiki/Recurrent_neural_network) are artificial neural networks derived from feedforward neural networks that create temporal graphs. - -✅ Do a little research. What other dates stand out as pivotal in the history of ML and AI? - ---- -## 1950: Machines that think - -Alan Turing, a truly remarkable person who was voted [by the public in 2019](https://wikipedia.org/wiki/Icons:_The_Greatest_Person_of_the_20th_Century) as the greatest scientist of the 20th century, is credited as helping to lay the foundation for the concept of a 'machine that can think.' He grappled with naysayers and his own need for empirical evidence of this concept in part by creating the [Turing Test](https://www.bbc.com/news/technology-18475646), which you will explore in our NLP lessons. - ---- -## 1956: Dartmouth Summer Research Project - -"The Dartmouth Summer Research Project on artificial intelligence was a seminal event for artificial intelligence as a field," and it was here that the term 'artificial intelligence' was coined ([source](https://250.dartmouth.edu/highlights/artificial-intelligence-ai-coined-dartmouth)). - -> Every aspect of learning or any other feature of intelligence can in principle be so precisely described that a machine can be made to simulate it. - ---- - -The lead researcher, mathematics professor John McCarthy, hoped "to proceed on the basis of the conjecture that every aspect of learning or any other feature of intelligence can in principle be so precisely described that a machine can be made to simulate it." The participants included another luminary in the field, Marvin Minsky. - -The workshop is credited with having initiated and encouraged several discussions including "the rise of symbolic methods, systems focussed on limited domains (early expert systems), and deductive systems versus inductive systems." ([source](https://wikipedia.org/wiki/Dartmouth_workshop)). - ---- -## 1956 - 1974: "The golden years" - -From the 1950s through the mid '70s, optimism ran high in the hope that AI could solve many problems. In 1967, Marvin Minsky stated confidently that "Within a generation ... the problem of creating 'artificial intelligence' will substantially be solved." (Minsky, Marvin (1967), Computation: Finite and Infinite Machines, Englewood Cliffs, N.J.: Prentice-Hall) - -natural language processing research flourished, search was refined and made more powerful, and the concept of 'micro-worlds' was created, where simple tasks were completed using plain language instructions. - ---- - -Research was well funded by government agencies, advances were made in computation and algorithms, and prototypes of intelligent machines were built. Some of these machines include: - -* [Shakey the robot](https://wikipedia.org/wiki/Shakey_the_robot), who could maneuver and decide how to perform tasks 'intelligently'. - - ![Shakey, an intelligent robot](images/shakey.jpg) - > Shakey in 1972 - ---- - -* Eliza, an early 'chatterbot', could converse with people and act as a primitive 'therapist'. You'll learn more about Eliza in the NLP lessons. - - ![Eliza, a bot](images/eliza.png) - > A version of Eliza, a chatbot - ---- - -* "Blocks world" was an example of a micro-world where blocks could be stacked and sorted, and experiments in teaching machines to make decisions could be tested. Advances built with libraries such as [SHRDLU](https://wikipedia.org/wiki/SHRDLU) helped propel language processing forward. - - [![blocks world with SHRDLU](https://img.youtube.com/vi/QAJz4YKUwqw/0.jpg)](https://www.youtube.com/watch?v=QAJz4YKUwqw "blocks world with SHRDLU") - - > đŸŽĨ Click the image above for a video: Blocks world with SHRDLU - ---- -## 1974 - 1980: "AI Winter" - -By the mid 1970s, it had become apparent that the complexity of making 'intelligent machines' had been understated and that its promise, given the available compute power, had been overblown. Funding dried up and confidence in the field slowed. Some issues that impacted confidence included: ---- -- **Limitations**. Compute power was too limited. -- **Combinatorial explosion**. The amount of parameters needed to be trained grew exponentially as more was asked of computers, without a parallel evolution of compute power and capability. -- **Paucity of data**. There was a paucity of data that hindered the process of testing, developing, and refining algorithms. -- **Are we asking the right questions?**. The very questions that were being asked began to be questioned. Researchers began to field criticism about their approaches: - - Turing tests came into question by means, among other ideas, of the 'chinese room theory' which posited that, "programming a digital computer may make it appear to understand language but could not produce real understanding." ([source](https://plato.stanford.edu/entries/chinese-room/)) - - The ethics of introducing artificial intelligences such as the "therapist" ELIZA into society was challenged. - ---- - -At the same time, various AI schools of thought began to form. A dichotomy was established between ["scruffy" vs. "neat AI"](https://wikipedia.org/wiki/Neats_and_scruffies) practices. _Scruffy_ labs tweaked programs for hours until they had the desired results. _Neat_ labs "focused on logic and formal problem solving". ELIZA and SHRDLU were well-known _scruffy_ systems. In the 1980s, as demand emerged to make ML systems reproducible, the _neat_ approach gradually took the forefront as its results are more explainable. - ---- -## 1980s Expert systems - -As the field grew, its benefit to business became clearer, and in the 1980s so did the proliferation of 'expert systems'. "Expert systems were among the first truly successful forms of artificial intelligence (AI) software." ([source](https://wikipedia.org/wiki/Expert_system)). - -This type of system is actually _hybrid_, consisting partially of a rules engine defining business requirements, and an inference engine that leveraged the rules system to deduce new facts. - -This era also saw increasing attention paid to neural networks. - ---- -## 1987 - 1993: AI 'Chill' - -The proliferation of specialized expert systems hardware had the unfortunate effect of becoming too specialized. The rise of personal computers also competed with these large, specialized, centralized systems. The democratization of computing had begun, and it eventually paved the way for the modern explosion of big data. - ---- -## 1993 - 2011 - -This epoch saw a new era for ML and AI to be able to solve some of the problems that had been caused earlier by the lack of data and compute power. The amount of data began to rapidly increase and become more widely available, for better and for worse, especially with the advent of the smartphone around 2007. Compute power expanded exponentially, and algorithms evolved alongside. The field began to gain maturity as the freewheeling days of the past began to crystallize into a true discipline. - ---- -## Now - -Today machine learning and AI touch almost every part of our lives. This era calls for careful understanding of the risks and potentials effects of these algorithms on human lives. As Microsoft's Brad Smith has stated, "Information technology raises issues that go to the heart of fundamental human-rights protections like privacy and freedom of expression. These issues heighten responsibility for tech companies that create these products. In our view, they also call for thoughtful government regulation and for the development of norms around acceptable uses" ([source](https://www.technologyreview.com/2019/12/18/102365/the-future-of-ais-impact-on-society/)). - ---- - -It remains to be seen what the future holds, but it is important to understand these computer systems and the software and algorithms that they run. We hope that this curriculum will help you to gain a better understanding so that you can decide for yourself. - -[![The history of deep learning](https://img.youtube.com/vi/mTtDfKgLm54/0.jpg)](https://www.youtube.com/watch?v=mTtDfKgLm54 "The history of deep learning") -> đŸŽĨ Click the image above for a video: Yann LeCun discusses the history of deep learning in this lecture - ---- -## 🚀Challenge - -Dig into one of these historical moments and learn more about the people behind them. There are fascinating characters, and no scientific discovery was ever created in a cultural vacuum. What do you discover? - -## [Post-lecture quiz](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/4/) - ---- -## Review & Self Study - -Here are items to watch and listen to: - -[This podcast where Amy Boyd discusses the evolution of AI](http://runasradio.com/Shows/Show/739) - -[![The history of AI by Amy Boyd](https://img.youtube.com/vi/EJt3_bFYKss/0.jpg)](https://www.youtube.com/watch?v=EJt3_bFYKss "The history of AI by Amy Boyd") - ---- - -## Assignment - -[Create a timeline](assignment.md) diff --git a/1-Introduction/2-history-of-ML/assignment.md b/1-Introduction/2-history-of-ML/assignment.md deleted file mode 100644 index a12e85a7..00000000 --- a/1-Introduction/2-history-of-ML/assignment.md +++ /dev/null @@ -1,11 +0,0 @@ -# Create a timeline - -## Instructions - -Using [this repo](https://github.com/Digital-Humanities-Toolkit/timeline-builder), create a timeline of some aspect of the history of algorithms, mathematics, statistics, AI, or ML, or a combination of these. You can focus on one person, one idea, or a long timespan of thought. Make sure to add multimedia elements. - -## Rubric - -| Criteria | Exemplary | Adequate | Needs Improvement | -| -------- | ------------------------------------------------- | --------------------------------------- | ---------------------------------------------------------------- | -| | A deployed timeline is presented as a GitHub page | The code is incomplete and not deployed | The timeline is incomplete, not well researched and not deployed | diff --git a/1-Introduction/2-history-of-ML/images/eliza.png b/1-Introduction/2-history-of-ML/images/eliza.png deleted file mode 100644 index 04f14146..00000000 Binary files a/1-Introduction/2-history-of-ML/images/eliza.png and /dev/null differ diff --git a/1-Introduction/2-history-of-ML/images/shakey.jpg b/1-Introduction/2-history-of-ML/images/shakey.jpg deleted file mode 100644 index 53ce4b35..00000000 Binary files a/1-Introduction/2-history-of-ML/images/shakey.jpg and /dev/null differ diff --git a/1-Introduction/2-history-of-ML/lesson-2.pdf b/1-Introduction/2-history-of-ML/lesson-2.pdf deleted file mode 100644 index 21997a3d..00000000 Binary files a/1-Introduction/2-history-of-ML/lesson-2.pdf and /dev/null differ diff --git a/1-Introduction/2-history-of-ML/translations/README.es.md b/1-Introduction/2-history-of-ML/translations/README.es.md deleted file mode 100755 index 116cc7e4..00000000 --- a/1-Introduction/2-history-of-ML/translations/README.es.md +++ /dev/null @@ -1,117 +0,0 @@ -# Historia del machine learning - -![Resumen de la historia del machine learning en un boceto](../../sketchnotes/ml-history.png) -> Boceto por [Tomomi Imura](https://www.twitter.com/girlie_mac) - -## [Cuestionario previo a la conferencia](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/3?loc=es) - -En esta lecciÃŗn, analizaremos los principales hitos en la historia del machine learning y la inteligencia artificial. - -La historia de la inteligencia artificial (AI) como campo estÃĄ entrelazada con la historia del machine learning, ya que los algoritmos y avances computacionales que sustentan el ML ayudaron al desarrollo de la inteligencia artificial. Es Ãētil recordar que, si bien estos campos comenzaron a cristalizar en la dÊcada de 1950 como ÃĄreas distintas de investigaciÃŗn, importantes [descubrimientos algorítmicos, estadísticos, matemÃĄticos, computacionales y tÊcnicos](https://wikipedia.org/wiki/Timeline_of_machine_learning) fueron predecesores y contemporÃĄneos a esta era. De hecho, las personas han estado pensando en estas preguntas durante [cientos de aÃąos](https://wikipedia.org/wiki/History_of_artificial_intelligence): este artículo analiza los fundamentos intelectuales histÃŗricos de la idea de una 'mÃĄquina pensante.' - -## Descubrimientos notables - -- 1763, 1812 [Teorema de Bayes](https://es.wikipedia.org/wiki/Teorema_de_Bayes) y sus predecesores. Este teorema y sus aplicaciones son la base de la inferencia, describiendo la probabilidad de que ocurra un evento basado en el conocimiento previo. -- 1805 [Teoría de mínimos cuadrados](https://es.wikipedia.org/wiki/M%C3%ADnimos_cuadrados) por el matemÃĄtico francÊs Adrien-Marie Legendre. Esta teoría, sobre la que aprenderemos en nuestra unidad de RegresiÃŗn, ayuda al ajustar los modelos a los datos. -- 1913 [Cadenas de Markov](https://es.wikipedia.org/wiki/Cadena_de_M%C3%A1rkov) el nombre del matemÃĄtico ruso Andrey Markov es utilizado para describir una secuencia de posibles eventos basados en su estado anterior. -- 1957 [Perceptron](https://wikipedia.org/wiki/Perceptron) es un tipo de clasificador lineal inventado por el psicÃŗlogo Frank Rosenblatt que subyace a los avances en el deep learning. -- 1967 [Nearest Neighbor (Vecino mÃĄs cercano)](https://es.wikipedia.org/wiki/K_vecinos_m%C3%A1s_pr%C3%B3ximos) es un algoritmo diseÃąado originalmente para trazar rutas. En un contexto de ML, se utiliza para detectar patrones. -- 1970 [RetropropagaciÃŗn](https://es.wikipedia.org/wiki/Propagaci%C3%B3n_hacia_atr%C3%A1s): es usada para entrenar [redes neuronales prealimentadas](https://es.wikipedia.org/wiki/Red_neuronal_prealimentada). -- 1982 [Redes neuronales recurrentes](https://es.wikipedia.org/wiki/Red_neuronal_recurrente) son redes neuronales artificiales derivadas de redes neuronales prealimentadas que crean grafos temporales. - -✅ Investigue un poco. ÂŋQuÊ otras fechas se destacan como fundamentales en la historia del machine learning (ML) y la inteligencia artificial (AI)? -## 1950: MÃĄquinas que piensan - -Alan Turing, una persona verdaderamente notable que fue votada [por el pÃēblico en 2019](https://wikipedia.org/wiki/Icons:_The_Greatest_Person_of_the_20th_Century) como el científico mÃĄs grande del siglo XX, a quien se le atribuye haber ayudado a sentar las bases del concepto de una 'mÃĄquina que puede pensar.' LidiÃŗ con los detractores y con su propia necesidad de evidencia empírica de este concepto en parte mediante la creaciÃŗn de la [prueba de Turing](https://www.bbc.com/news/technology-18475646), que explorarÃĄs en nuestras lecciones de procesamiento de lenguaje natural (NLP, por sus siglas en inglÊs). - -## 1956: Dartmouth Summer Research Project - -"The Dartmouth Summer Research Project sobre inteligencia artificial fue un evento fundamental para la inteligencia artificial como campo" y fue aquí donde se acuÃąÃŗ el tÊrmino 'inteligencia artificial' ([fuente](https://250.dartmouth.edu/highlights/artificial-intelligence-ai-coined-dartmouth)). - - -> Todos los aspectos del aprendizaje y cualquier otra característica de la inteligencia pueden, en principio, describirse con tanta precisiÃŗn que se puede hacer una mÃĄquina para simularlos. - -El investigador principal, el profesor de matemÃĄticas John McCarthy, esperaba "proceder sobre las bases de la conjetura de que cada aspecto del aprendizaje o cualquier otra característica de la inteligencia pueden, en principio, describirse con tanta precisiÃŗn que se puede hacer una mÃĄquina para simularlos." Los participantes, incluyeron otro gran experto en el campo, Marvin Minsky. - -El taller tiene el mÊrito de haber iniciado y alentado varias discusiones que incluyen "el surgimiento de mÊtodos simbÃŗlicos, sistemas en dominios limitados (primeros sistemas expertos), y sistemas deductivos contra sistemas inductivos." ([fuente](https://es.wikipedia.org/wiki/Conferencia_de_Dartmouth)). - -## 1956 - 1974: "Los aÃąos dorados" - -Desde la dÊcada de 1950, hasta mediados de la de 1970, el optimismo se elevÃŗ con la esperanza de que la AI pudiera resolver muchos problemas. En 1967, Marvin Minsky declarÃŗ con seguridad que "dentro de una generaciÃŗn ... el problema de crear 'inteligencia artificial' estarÃĄ resuelto en gran medida." (Minsky, Marvin (1967), Computation: Finite and Infinite Machines, Englewood Cliffs, N.J.: Prentice-Hall) - -La investigaciÃŗn del procesamiento del lenguaje natural floreciÃŗ, la bÃēsqueda se refinÃŗ y se hizo mÃĄs poderosa, y el concepto de 'micro-mundos' fue creado, donde se completaban tareas simples utilizando instrucciones en lenguaje sencillo. - -La investigaciÃŗn estuvo bien financiada por agencias gubernamentales, se realizaron avances en computaciÃŗn y algoritmos, y se construyeron prototipos de mÃĄquinas inteligentes. Algunas de esta mÃĄquinas incluyen: - -* [Shakey la robot](https://wikipedia.org/wiki/Shakey_the_robot), que podría maniobrar y decidir cÃŗmo realizar las tareas de forma 'inteligente'. - - ![Shakey, un robot inteligente](images/shakey.jpg) - > Shakey en 1972 - -* Eliza, unas de las primeras 'chatterbot', podía conversar con las personas y actuar como un 'terapeuta' primitivo. AprenderÃĄ mÃĄs sobre Eliza en las lecciones de NLP. - - ![Eliza, un bot](images/eliza.png) - > Una versiÃŗn de Eliza, un chatbot - -* "Blocks world" era un ejemplo de micro-world donde los bloques se podían apilar y ordenar, y se podían probar experimentos en mÃĄquinas de enseÃąanza para tomar decisiones. Los avances creados con librerías como [SHRDLU](https://wikipedia.org/wiki/SHRDLU) ayudaron a inpulsar el procesamiento del lenguaje natural. - - [![blocks world con SHRDLU](https://img.youtube.com/vi/QAJz4YKUwqw/0.jpg)](https://www.youtube.com/watch?v=QAJz4YKUwqw "blocks world con SHRDLU") - - > đŸŽĨ Haga clic en la imagen de arriba para ver un video: Blocks world con SHRDLU - -## 1974 - 1980: "Invierno de la AI" - -A mediados de la dÊcada de 1970, se hizo evidente que la complejidad de la fabricaciÃŗn de 'mÃĄquinas inteligentes' se había subestimado y que su promesa, dado la potencia computacional disponible, había sido exagerada. La financiaciÃŗn se agotÃŗ y la confianza en el campo se ralentizÃŗ. Algunos problemas que impactaron la confianza incluyeron: - -- **Limitaciones**. La potencia computacional era demasiado limitada. -- **ExplosiÃŗn combinatoria**. La cantidad de parÃĄmetros necesitados para entrenar creciÃŗ exponencialmente a medida que se pedía mÃĄs a las computadoras sin una evoluciÃŗn paralela de la potencia y la capacidad de cÃŗmputo. -- **Escasez de datos**. Hubo una escasez de datos que obstaculizÃŗ el proceso de pruebas, desarrollo y refinamiento de algoritmos. -- **ÂŋEstamos haciendo las preguntas correctas?**. Las mismas preguntas que se estaban formulando comenzaron a cuestionarse. Los investigadores comenzaron a criticar sus mÊtodos: - - Las pruebas de Turing se cuestionaron por medio, entre otras ideas, de la 'teoría de la habitaciÃŗn china' que postulaba que "programar una computadora digital puede hacerse que parezca que entiende el lenguaje, pero no puede producir una comprensiÃŗn real" ([fuente](https://plato.stanford.edu/entries/chinese-room/)) - - Se cuestionÃŗ la Êtica de introducir inteligencias artificiales como la "terapeuta" Eliza en la sociedad. - -Al mismo tiempo, comenzaron a formarse varias escuelas de pensamiento de AI. Se estableciÃŗ una dicotomía entre las prÃĄcticas ["scruffy" vs. "neat AI"](https://wikipedia.org/wiki/Neats_and_scruffies). _Scruffy_ labs modificÃŗ los programas durante horas hasta que obtuvieron los objetivos deseados. _Neat_ labs "centrados en la lÃŗgica y la resoluciÃŗn de problemas formales". ELIZA y SHRDLU eran sistemas _scruffy_ muy conocidos. En la dÊcada de 1980, cuando surgiÃŗ la demanda para hacer que los sistemas de aprendizaje fueran reproducibles, el enfoque _neat_ gradualmente tomÃŗ la vanguardia a medida que sus resultados eran mÃĄs explicables. - -## Systemas expertos de la dÊcada de 1980 - -A medida que el campo creciÃŗ, su beneficio para las empresas se hizo mÃĄs claro, y en la dÊcada de 1980 tambiÊn lo hizo la proliferaciÃŗn de 'sistemas expertos'. "Los sistemas expertos estuvieron entre las primeras formas verdaderamente exitosas de software de inteligencia artificial (IA)." ([fuente](https://wikipedia.org/wiki/Expert_system)). - -Este tipo de sistemas es en realidad _híbrido_, que consta parcialmente de un motor de reglas que define los requisitos comerciales, y un motor de inferencia que aprovechÃŗ el sistema de reglas para deducir nuevos hechos. - -En esta era tambiÊn se prestÃŗ mayor atenciÃŗn a las redes neuronales. - -## 1987 - 1993: AI 'Chill' - -La proliferaciÃŗn de hardware de sistemas expertos especializados tuvo el desafortunado efecto de volverse demasiado especializado. El auge de las computadoras personales tambiÊn compitiÃŗ con estos grandes sistemas centralizados especializados. La democratizaciÃŗn de la informÃĄtica había comenzado, y finalmente, allanÃŗ el camino para la explosiÃŗn moderna del big data. - -## 1993 - 2011 - -Esta Êpoca viÃŗ una nueva era para el ML y la IA para poder resolver problemas que anteriormente provenían de la falta de datos y de poder de cÃŗmputo. La cantidad de datos comenzÃŗ a aumentar rÃĄpidamente y a estar mÃĄs disponible, para bien o para mal, especialmente con la llegada del smartphone alrededor del 2007. El poder computacional se expandiÃŗ exponencialmente y los algoritmos evolucionaron al mismo tiempo. El campo comenzÃŗ a ganar madurez a medida que los días libres del pasado comenzaron a cristalizar en una verdadera disciplina. - -## Ahora - -Hoy en día, machine learning y la inteligencia artificial tocan casi todos los aspectos de nuestras vidas. Esta era requiere de una comprensiÃŗn cuidadosa de los riesgos y los efectos potenciales de estos algoritmos en las vidas humanas. Como ha dicho Brad Smith de Microsoft, "La tecnología de la informaciÃŗn plantea problemas que van al corazÃŗn de las protecciones fundamentales de los derechos humanos, como la privacidad y la libertad de expresiÃŗn. Esos problemas aumentan las responsabilidades de las empresas de tecnología que crean estos productos. En nuestra opiniÃŗn, tambiÊn exige regulaciÃŗn gubernamental reflexiva y el desarrollo de normas sobre usos aceptables" ([fuente](https://www.technologyreview.com/2019/12/18/102365/the-future-of-ais-impact-on-society/)). - -Queda por ver quÊ depara el futuro, pero es importante entender estos sistemas informÃĄticos y el software y los algoritmos que ejecutan. Esperamos que este plan de estudios le ayude a comprender mejor para que pueda decidir por si mismo. - -[![La historia del deep learning](https://img.youtube.com/vi/mTtDfKgLm54/0.jpg)](https://www.youtube.com/watch?v=mTtDfKgLm54 "The history of deep learning") -> đŸŽĨ Haga clic en la imagen de arriba para ver un video: Yann LeCun analiza la historia del deep learning en esta conferencia - ---- -## 🚀Desafío - -SumÊrjase dentro de unos de estos momentos histÃŗricos y aprenda mÃĄs sobre las personas detrÃĄs de ellos. Hay personajes fascinantes y nunca ocurriÃŗ ningÃēn descubrimiento científico en un vacío cultural. ÂŋQuÊ descubres? - -## [Cuestionario posterior a la lecciÃŗn](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/4?loc=es) - -## RevisiÃŗn y autoestudio - -Aquí hay elementos para ver y escuchar: - -[Este podcast donde Amy Boyd habla sobre la evoluciÃŗn de la IA](http://runasradio.com/Shows/Show/739) - -[![La historia de la IA por Amy Boyd](https://img.youtube.com/vi/EJt3_bFYKss/0.jpg)](https://www.youtube.com/watch?v=EJt3_bFYKss "La historia de la IA por Amy Boyd") - -## Tarea - -[Crea un timeline](assignment.md) diff --git a/1-Introduction/2-history-of-ML/translations/README.fr.md b/1-Introduction/2-history-of-ML/translations/README.fr.md deleted file mode 100644 index d9ecad4f..00000000 --- a/1-Introduction/2-history-of-ML/translations/README.fr.md +++ /dev/null @@ -1,117 +0,0 @@ -# Histoire du Machine Learning (apprentissage automatique) - -![RÊsumÊ de l'histoire du machine learning dans un sketchnote](../../../sketchnotes/ml-history.png) -> Sketchnote de [Tomomi Imura](https://www.twitter.com/girlie_mac) - -## [Quizz prÊalable](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/3?loc=fr) - -Dans cette leçon, nous allons parcourir les principales Êtapes de l'histoire du machine learning et de l'intelligence artificielle. - -L'histoire de l'intelligence artificielle, l'IA, en tant que domaine est Êtroitement liÊe à l'histoire du machine learning, car les algorithmes et les avancÊes informatiques qui sous-tendent le ML alimentent le dÊveloppement de l'IA. Bien que ces domaines en tant que domaines de recherches distincts ont commencÊ à se cristalliser dans les annÊes 1950, il est important de rappeler que les [dÊcouvertes algorithmiques, statistiques, mathÊmatiques, informatiques et techniques](https://wikipedia.org/wiki/Timeline_of_machine_learning) ont prÊcÊdÊ et chevauchait cette Êpoque. En fait, le monde rÊflÊchit à ces questions depuis [des centaines d'annÊes](https://fr.wikipedia.org/wiki/Histoire_de_l%27intelligence_artificielle) : cet article traite des fondements intellectuels historiques de l'idÊe d'une ÂĢ machine qui pense Âģ. - -## DÊcouvertes notables - -- 1763, 1812 [thÊorème de Bayes](https://wikipedia.org/wiki/Bayes%27_theorem) et ses prÊdÊcesseurs. Ce thÊorème et ses applications sous-tendent l'infÊrence, dÊcrivant la probabilitÊ qu'un ÊvÊnement se produise sur la base de connaissances antÊrieures. -- 1805 [ThÊorie des moindres carrÊs](https://wikipedia.org/wiki/Least_squares) par le mathÊmaticien français Adrien-Marie Legendre. Cette thÊorie, que vous dÊcouvrirez dans notre unitÊ RÊgression, aide à l'ajustement des donnÊes. -- 1913 [ChaÃŽnes de Markov](https://wikipedia.org/wiki/Markov_chain) du nom du mathÊmaticien russe Andrey Markov sont utilisÊes pour dÊcrire une sÊquence d'ÊvÊnements possibles basÊe sur un Êtat antÊrieur. -- 1957 [Perceptron](https://wikipedia.org/wiki/Perceptron) est un type de classificateur linÊaire inventÊ par le psychologue amÊricain Frank Rosenblatt qui sous-tend les progrès de l'apprentissage en profondeur. -- 1967 [Nearest Neighbor](https://wikipedia.org/wiki/Nearest_neighbor) est un algorithme conçu à l'origine pour cartographier les itinÊraires. Dans un contexte ML, il est utilisÊ pour dÊtecter des modèles. -- 1970 [Backpropagation](https://wikipedia.org/wiki/Backpropagation) est utilisÊ pour former des [rÊseaux de neurones feedforward (propagation avant)](https://fr.wikipedia.org/wiki/R%C3%A9seau_de_neurones_%C3%A0_propagation_avant). -- 1982 [RÊseaux de neurones rÊcurrents](https://wikipedia.org/wiki/Recurrent_neural_network) sont des rÊseaux de neurones artificiels dÊrivÊs de rÊseaux de neurones à rÊaction qui crÊent des graphes temporels. - -✅ Faites une petite recherche. Quelles autres dates sont marquantes dans l'histoire du ML et de l'IA ? - -## 1950 : Des machines qui pensent - -Alan Turing, une personne vraiment remarquable qui a ÊtÊ Êlue [par le public en 2019](https://wikipedia.org/wiki/Icons:_The_Greatest_Person_of_the_20th_Century) comme le plus grand scientifique du 20e siècle, est reconnu pour avoir aidÊ à jeter les bases du concept d'une "machine qui peut penser". Il a luttÊ avec ses opposants et son propre besoin de preuves empiriques de sa thÊorie en crÊant le [Test de Turing] (https://www.bbc.com/news/technology-18475646), que vous explorerez dans nos leçons de NLP (TALN en français). - -## 1956 : Projet de recherche d'ÊtÊ à Dartmouth - -ÂĢ Le projet de recherche d'ÊtÊ de Dartmouth sur l'intelligence artificielle a ÊtÊ un ÊvÊnement fondateur pour l'intelligence artificielle en tant que domaine Âģ, et c'est ici que le terme ÂĢ intelligence artificielle Âģ a ÊtÊ inventÊ ([source](https://250.dartmouth.edu/highlights/artificial-intelligence-ai-coined-dartmouth)). - -> Chaque aspect de l'apprentissage ou toute autre caractÊristique de l'intelligence peut en principe ÃĒtre dÊcrit si prÊcisÊment qu'une machine peut ÃĒtre conçue pour les simuler. - -Le chercheur en tÃĒte, le professeur de mathÊmatiques John McCarthy, espÊrait ÂĢ procÊder sur la base de la conjecture selon laquelle chaque aspect de l'apprentissage ou toute autre caractÊristique de l'intelligence peut en principe ÃĒtre dÊcrit avec une telle prÊcision qu'une machine peut ÃĒtre conçue pour les simuler Âģ. Les participants comprenaient une autre sommitÊ dans le domaine, Marvin Minsky. - -L'atelier est crÊditÊ d'avoir initiÊ et encouragÊ plusieurs discussions, notamment ÂĢ l'essor des mÊthodes symboliques, des systèmes spÊcialisÊs sur des domaines limitÊs (premiers systèmes experts) et des systèmes dÊductifs par rapport aux systèmes inductifs Âģ. ([source](https://fr.wikipedia.org/wiki/Conf%C3%A9rence_de_Dartmouth)). - -## 1956 - 1974 : "Les annÊes d'or" - -Des annÊes 50 au milieu des annÊes 70, l'optimisme Êtait au rendez-vous en espÊrant que l'IA puisse rÊsoudre de nombreux problèmes. En 1967, Marvin Minsky a dÊclarÊ avec assurance que ÂĢ Dans une gÊnÊration... le problème de la crÊation d'"intelligence artificielle" sera substantiellement rÊsolu. Âģ (Minsky, Marvin (1967), Computation: Finite and Infinite Machines, Englewood Cliffs, N.J.: Prentice-Hall) - -La recherche sur le Natural Language Processing (traitement du langage naturel en français) a prospÊrÊ, la recherche a ÊtÊ affinÊe et rendue plus puissante, et le concept de ÂĢ micro-mondes Âģ a ÊtÊ crÊÊ, oÚ des tÃĸches simples ont ÊtÊ effectuÊes en utilisant des instructions en langue naturelle. - -La recherche a ÊtÊ bien financÊe par les agences gouvernementales, des progrès ont ÊtÊ rÊalisÊs dans le calcul et les algorithmes, et des prototypes de machines intelligentes ont ÊtÊ construits. Certaines de ces machines incluent : - -* [Shakey le robot](https://fr.wikipedia.org/wiki/Shakey_le_robot), qui pouvait manœuvrer et dÊcider comment effectuer des tÃĸches ÂĢ intelligemment Âģ. - - ![Shakey, un robot intelligent](../images/shakey.jpg) - > Shaky en 1972 - -* Eliza, une des premières ÂĢ chatbot Âģ, pouvait converser avec les gens et agir comme une ÂĢ thÊrapeute Âģ primitive. Vous en apprendrez plus sur Eliza dans les leçons de NLP. - - ![Eliza, un bot](../images/eliza.png) - > Une version d'Eliza, un chatbot - -* Le ÂĢ monde des blocs Âģ Êtait un exemple de micro-monde oÚ les blocs pouvaient ÃĒtre empilÊs et triÊs, et oÚ des expÊriences d'apprentissages sur des machines, dans le but qu'elles prennent des dÊcisions, pouvaient ÃĒtre testÊes. Les avancÊes rÊalisÊes avec des bibliothèques telles que [SHRDLU](https://fr.wikipedia.org/wiki/SHRDLU) ont contribuÊ à faire avancer le natural language processing. - - [![Monde de blocs avec SHRDLU](https://img.youtube.com/vi/QAJz4YKUwqw/0.jpg)](https://www.youtube.com/watch?v=QAJz4YKUwqw "Monde de blocs avec SHRDLU" ) - - > đŸŽĨ Cliquez sur l'image ci-dessus pour une vidÊo : Blocks world with SHRDLU - -## 1974 - 1980 : ÂĢ l'hiver de l'IA Âģ - -Au milieu des annÊes 1970, il Êtait devenu Êvident que la complexitÊ de la fabrication de ÂĢ machines intelligentes Âģ avait ÊtÊ sous-estimÊe et que sa promesse, compte tenu de la puissance de calcul disponible, avait ÊtÊ exagÊrÊe. Les financements se sont taris et la confiance dans le domaine s'est ralentie. Parmi les problèmes qui ont eu un impact sur la confiance, citons : - -- **Restrictions**. La puissance de calcul Êtait trop limitÊe. -- **Explosion combinatoire**. Le nombre de paramètres à former augmentait de façon exponentielle à mesure que l'on en demandait davantage aux ordinateurs, sans Êvolution parallèle de la puissance et de la capacitÊ de calcul. -- **PÊnurie de donnÊes**. Il y avait un manque de donnÊes qui a entravÊ le processus de test, de dÊveloppement et de raffinement des algorithmes. -- **Posions-nous les bonnes questions ?**. Les questions mÃĒmes, qui Êtaient posÊes, ont commencÊ à ÃĒtre remises en question. Les chercheurs ont commencÊ à Êmettre des critiques sur leurs approches : - - Les tests de Turing ont ÊtÊ remis en question au moyen, entre autres, de la ÂĢ thÊorie de la chambre chinoise Âģ qui postulait que ÂĢ la programmation d'un ordinateur numÊrique peut faire croire qu'il comprend le langage mais ne peut pas produire une comprÊhension rÊelle Âģ. ([source](https://plato.stanford.edu/entries/chinese-room/)) - - L'Êthique de l'introduction d'intelligences artificielles telles que la "thÊrapeute" ELIZA dans la sociÊtÊ a ÊtÊ remise en cause. - -Dans le mÃĒme temps, diverses Êcoles de pensÊe sur l'IA ont commencÊ à se former. Une dichotomie a ÊtÊ Êtablie entre les pratiques IA ["scruffy" et "neat"](https://wikipedia.org/wiki/Neats_and_scruffies). Les laboratoires _Scruffy_ peaufinaient leurs programmes pendant des heures jusqu'à ce qu'ils obtiennent les rÊsultats souhaitÊs. Les laboratoires _Neat_ "se concentraient sur la logique et la rÊsolution formelle de problèmes". ELIZA et SHRDLU Êtaient des systèmes _scruffy_ bien connus. Dans les annÊes 1980, alors qu'Êmergeait la demande de rendre les systèmes ML reproductibles, l'approche _neat_ a progressivement pris le devant de la scène car ses rÊsultats sont plus explicables. - -## 1980 : Systèmes experts - -Au fur et à mesure que le domaine s'est dÊveloppÊ, ses avantages pour les entreprises sont devenus plus clairs, particulièrement via les ÂĢ systèmes experts Âģ dans les annÊes 1980. "Les systèmes experts ont ÊtÊ parmi les premières formes vraiment rÊussies de logiciels d'intelligence artificielle (IA)." ([source](https://fr.wikipedia.org/wiki/Syst%C3%A8me_expert)). - -Ce type de système est en fait _hybride_, composÊ en partie d'un moteur de règles dÊfinissant les exigences mÊtier et d'un moteur d'infÊrence qui exploite le système de règles pour dÊduire de nouveaux faits. - -Cette Êpoque a Êgalement vu une attention croissante accordÊe aux rÊseaux de neurones. - -## 1987 - 1993 : IA ÂĢ Chill Âģ - -La prolifÊration du matÊriel spÊcialisÊ des systèmes experts a eu pour effet malheureux de devenir trop spÊcialisÊe. L'essor des ordinateurs personnels a Êgalement concurrencÊ ces grands systèmes spÊcialisÊs et centralisÊs. La dÊmocratisation de l'informatique a commencÊ et a finalement ouvert la voie à l'explosion des mÊgadonnÊes. - -## 1993 - 2011 - -Cette Êpoque a vu naÃŽtre une nouvelle ère pour le ML et l'IA afin de rÊsoudre certains des problèmes qui n'avaient pu l'ÃĒtre plus tôt par le manque de donnÊes et de puissance de calcul. La quantitÊ de donnÊes a commencÊ à augmenter rapidement et à devenir plus largement disponibles, pour le meilleur et pour le pire, en particulier avec l'avènement du smartphone vers 2007. La puissance de calcul a augmentÊ de façon exponentielle et les algorithmes ont ÊvoluÊ parallèlement. Le domaine a commencÊ à gagner en maturitÊ alors que l'ingÊniositÊ a commencÊ à se cristalliser en une vÊritable discipline. - -## À prÊsent - -Aujourd'hui, le machine learning et l'IA touchent presque tous les aspects de notre vie. Cette ère nÊcessite une comprÊhension approfondie des risques et des effets potentiels de ces algorithmes sur les vies humaines. Comme l'a dÊclarÊ Brad Smith de Microsoft, ÂĢ les technologies de l'information soulèvent des problèmes qui vont au cœur des protections fondamentales des droits de l'homme comme la vie privÊe et la libertÊ d'expression. Ces problèmes accroissent la responsabilitÊ des entreprises technologiques qui crÊent ces produits. À notre avis, ils appellent Êgalement à une rÊglementation gouvernementale rÊflÊchie et au dÊveloppement de normes autour des utilisations acceptables" ([source](https://www.technologyreview.com/2019/12/18/102365/the-future-of-ais-impact-on-society/)). - -Reste à savoir ce que l'avenir nous rÊserve, mais il est important de comprendre ces systèmes informatiques ainsi que les logiciels et algorithmes qu'ils exÊcutent. Nous espÊrons que ce programme vous aidera à mieux les comprendre afin que vous puissiez dÊcider par vous-mÃĒme. - -[![L'histoire du Deep Learning](https://img.youtube.com/vi/mTtDfKgLm54/0.jpg)](https://www.youtube.com/watch?v=mTtDfKgLm54 "L'histoire du Deep Learning") -> đŸŽĨ Cliquez sur l'image ci-dessus pour une vidÊo : Yann LeCun discute de l'histoire du deep learning dans cette confÊrence - ---- -## 🚀Challenge - -Plongez dans l'un de ces moments historiques et apprenez-en plus sur les personnes derrière ceux-ci. Il y a des personnalitÊs fascinantes, et aucune dÊcouverte scientifique n'a jamais ÊtÊ crÊÊe avec un vide culturel. Que dÊcouvrez-vous ? - -## [Quiz de validation des connaissances](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/4?loc=fr) - -## RÊvision et auto-apprentissage - -Voici quelques articles à regarder et à Êcouter : - -[Ce podcast oÚ Amy Boyd discute de l'Êvolution de l'IA](http://runasradio.com/Shows/Show/739) - -[![L'histoire de l'IA par Amy Boyd](https://img.youtube.com/vi/EJt3_bFYKss/0.jpg)](https://www.youtube.com/watch?v=EJt3_bFYKss "L'histoire de l'IA par Amy Boyd") - -## Devoir - -[CrÊer une frise chronologique](assignment.fr.md) diff --git a/1-Introduction/2-history-of-ML/translations/README.id.md b/1-Introduction/2-history-of-ML/translations/README.id.md deleted file mode 100644 index 351dd17d..00000000 --- a/1-Introduction/2-history-of-ML/translations/README.id.md +++ /dev/null @@ -1,116 +0,0 @@ -# Sejarah Machine Learning - -![Ringkasan dari Sejarah Machine Learning dalam sebuah catatan sketsa](../../../sketchnotes/ml-history.png) -> Catatan sketsa oleh [Tomomi Imura](https://www.twitter.com/girlie_mac) - -## [Quiz Pra-Pelajaran](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/3/) - -Dalam pelajaran ini, kita akan membahas tonggak utama dalam sejarah Machine Learning dan Artificial Intelligence. - -Sejarah Artifical Intelligence, AI, sebagai bidang terkait dengan sejarah Machine Learning, karena algoritma dan kemajuan komputasi yang mendukung ML dimasukkan ke dalam pengembangan AI. Penting untuk diingat bahwa, meski bidang-bidang ini sebagai bidang-bidang penelitian yang berbeda mulai terbentuk pada 1950-an, [algoritmik, statistik, matematik, komputasi dan penemuan teknis](https://wikipedia.org/wiki/Timeline_of_machine_learning) penting sudah ada sebelumnya, dan saling tumpang tindih di era ini. Faktanya, orang-orang telah memikirkan pertanyaan-pertanyaan ini selama [ratusan tahun](https://wikipedia.org/wiki/History_of_artificial_intelligence): artikel ini membahas dasar-dasar intelektual historis dari gagasan 'mesin yang berpikir'. - -## Penemuan penting - -- 1763, 1812 [Bayes Theorem](https://wikipedia.org/wiki/Bayes%27_theorem) dan para pendahulu. Teorema ini dan penerapannya mendasari inferensi, mendeskripsikan kemungkinan suatu peristiwa terjadi berdasarkan pengetahuan sebelumnya. -- 1805 [Least Square Theory](https://wikipedia.org/wiki/Least_squares) oleh matematikawan Perancis Adrien-Marie Legendre. Teori ini yang akan kamu pelajari di unit Regresi, ini membantu dalam *data fitting*. -- 1913 [Markov Chains](https://wikipedia.org/wiki/Markov_chain) dinamai dengan nama matematikawan Rusia, Andrey Markov, digunakan untuk mendeskripsikan sebuah urutan dari kejadian-kejadian yang mungkin terjadi berdasarkan kondisi sebelumnya. -- 1957 [Perceptron](https://wikipedia.org/wiki/Perceptron) adalah sebuah tipe dari *linear classifier* yang ditemukan oleh psikolog Amerika, Frank Rosenblatt, yang mendasari kemajuan dalam *Deep Learning*. -- 1967 [Nearest Neighbor](https://wikipedia.org/wiki/Nearest_neighbor) adalah sebuah algoritma yang pada awalnya didesain untuk memetakan rute. Dalam konteks ML, ini digunakan untuk mendeteksi berbagai pola. -- 1970 [Backpropagation](https://wikipedia.org/wiki/Backpropagation) digunakan untuk melatih [feedforward neural networks](https://wikipedia.org/wiki/Feedforward_neural_network). -- 1982 [Recurrent Neural Networks](https://wikipedia.org/wiki/Recurrent_neural_network) adalah *artificial neural networks* yang berasal dari *feedforward neural networks* yang membuat grafik sementara. - -✅ Lakukan sebuah riset kecil. Tanggal berapa lagi yang merupakan tanggal penting dalam sejarah ML dan AI? -## 1950: Mesin yang berpikir - -Alan Turing, merupakan orang luar biasa yang terpilih oleh [publik di tahun 2019](https://wikipedia.org/wiki/Icons:_The_Greatest_Person_of_the_20th_Century) sebagai ilmuwan terhebat di abad 20, diberikan penghargaan karena membantu membuat fondasi dari sebuah konsep 'mesin yang bisa berpikir', Dia berjuang menghadapi orang-orang yang menentangnya dan keperluannya sendiri untuk bukti empiris dari konsep ini dengan membuat [Turing Test](https://www.bbc.com/news/technology-18475646), yang mana akan kamu jelajahi di pelajaran NLP kami. - -## 1956: Proyek Riset Musim Panas Dartmouth - -"Proyek Riset Musim Panas Dartmouth pada *artificial intelligence* merupakan sebuah acara penemuan untuk *artificial intelligence* sebagai sebuah bidang," dan dari sinilah istilah '*artificial intelligence*' diciptakan ([sumber](https://250.dartmouth.edu/highlights/artificial-intelligence-ai-coined-dartmouth)). - -> Setiap aspek pembelajaran atau fitur kecerdasan lainnya pada prinsipnya dapat dideskripsikan dengan sangat tepat sehingga sebuah mesin dapat dibuat untuk mensimulasikannya. - -Ketua peneliti, profesor matematika John McCarthy, berharap "untuk meneruskan dasar dari dugaan bahwa setiap aspek pembelajaran atau fitur kecerdasan lainnya pada prinsipnya dapat dideskripsikan dengan sangat tepat sehingga mesin dapat dibuat untuk mensimulasikannya." Marvin Minsky, seorang tokoh terkenal di bidang ini juga termasuk sebagai peserta penelitian. - -Workshop ini dipuji karena telah memprakarsai dan mendorong beberapa diskusi termasuk "munculnya metode simbolik, sistem yang berfokus pada domain terbatas (sistem pakar awal), dan sistem deduktif versus sistem induktif." ([sumber](https://wikipedia.org/wiki/Dartmouth_workshop)). - -## 1956 - 1974: "Tahun-tahun Emas" - -Dari tahun 1950-an hingga pertengahan 70-an, optimisme memuncak dengan harapan bahwa AI dapat memecahkan banyak masalah. Pada tahun 1967, Marvin Minsky dengan yakin menyatakan bahwa "Dalam satu generasi ... masalah menciptakan '*artificial intelligence*' akan terpecahkan secara substansial." (Minsky, Marvin (1967), Computation: Finite and Infinite Machines, Englewood Cliffs, N.J.: Prentice-Hall) - -Penelitian *natural language processing* berkembang, pencarian disempurnakan dan dibuat lebih *powerful*, dan konsep '*micro-worlds*' diciptakan, di mana tugas-tugas sederhana diselesaikan menggunakan instruksi bahasa sederhana. - -Penelitian didanai dengan baik oleh lembaga pemerintah, banyak kemajuan dibuat dalam komputasi dan algoritma, dan prototipe mesin cerdas dibangun. Beberapa mesin tersebut antara lain: - -* [Shakey the robot](https://wikipedia.org/wiki/Shakey_the_robot), yang bisa bermanuver dan memutuskan bagaimana melakukan tugas-tugas secara 'cerdas'. - - ![Shakey, an intelligent robot](../images/shakey.jpg) - > Shakey pada 1972 - -* Eliza, sebuah 'chatterbot' awal, dapat mengobrol dengan orang-orang dan bertindak sebagai 'terapis' primitif. Kamu akan belajar lebih banyak tentang Eliza dalam pelajaran NLP. - - ![Eliza, a bot](../images/eliza.png) - > Sebuah versi dari Eliza, sebuah *chatbot* - -* "Blocks world" adalah contoh sebuah *micro-world* dimana balok dapat ditumpuk dan diurutkan, dan pengujian eksperimen mesin pengajaran untuk membuat keputusan dapat dilakukan. Kemajuan yang dibuat dengan *library-library* seperti [SHRDLU](https://wikipedia.org/wiki/SHRDLU) membantu mendorong kemajuan pemrosesan bahasa. - - [![blocks world dengan SHRDLU](https://img.youtube.com/vi/QAJz4YKUwqw/0.jpg)](https://www.youtube.com/watch?v=QAJz4YKUwqw "blocks world dengan SHRDLU") - - > đŸŽĨ Klik gambar diatas untuk menonton video: Blocks world with SHRDLU - -## 1974 - 1980: "Musim Dingin AI" - -Pada pertengahan 1970-an, semakin jelas bahwa kompleksitas pembuatan 'mesin cerdas' telah diremehkan dan janjinya, mengingat kekuatan komputasi yang tersedia, telah dilebih-lebihkan. Pendanaan telah habis dan kepercayaan dalam bidang ini menurun. Beberapa masalah yang memengaruhi kepercayaan diri termasuk: - -- **Keterbatasan**. Kekuatan komputasi terlalu terbatas. -- **Ledakan kombinatorial**. Jumlah parameter yang perlu dilatih bertambah secara eksponensial karena lebih banyak hal yang diminta dari komputer, tanpa evolusi paralel dari kekuatan dan kemampuan komputasi. -- **Kekurangan data**. Adanya kekurangan data yang menghalangi proses pengujian, pengembangan, dan penyempurnaan algoritma. -- **Apakah kita menanyakan pertanyaan yang tepat?**. Pertanyaan-pertanyaan yang diajukan pun mulai dipertanyakan kembali. Para peneliti mulai melontarkan kritik tentang pendekatan mereka - - Tes Turing mulai dipertanyakan, di antara ide-ide lain, dari 'teori ruang Cina' yang mengemukakan bahwa, "memprogram komputer digital mungkin membuatnya tampak memahami bahasa tetapi tidak dapat menghasilkan pemahaman yang sebenarnya." ([sumber](https://plato.stanford.edu/entries/chinese-room/)) - - Tantangan etika ketika memperkenalkan kecerdasan buatan seperti si "terapis" ELIZA ke dalam masyarakat. - -Pada saat yang sama, berbagai aliran pemikiran AI mulai terbentuk. Sebuah dikotomi didirikan antara praktik ["scruffy" vs. "neat AI"](https://wikipedia.org/wiki/Neats_and_scruffies). Lab _Scruffy_ mengubah program selama berjam-jam sampai mendapat hasil yang diinginkan. Lab _Neat_ "berfokus pada logika dan penyelesaian masalah formal". ELIZA dan SHRDLU adalah sistem _scruffy_ yang terkenal. Pada tahun 1980-an, karena perkembangan permintaan untuk membuat sistem ML yang dapat direproduksi, pendekatan _neat_ secara bertahap menjadi yang terdepan karena hasilnya lebih dapat dijelaskan. - -## 1980s Sistem Pakar - -Seiring berkembangnya bidang ini, manfaatnya bagi bisnis menjadi lebih jelas, dan begitu pula dengan menjamurnya 'sistem pakar' pada tahun 1980-an. "Sistem pakar adalah salah satu bentuk perangkat lunak artificial intelligence (AI) pertama yang benar-benar sukses." ([sumber](https://wikipedia.org/wiki/Expert_system)). - -Tipe sistem ini sebenarnya adalah _hybrid_, sebagian terdiri dari mesin aturan yang mendefinisikan kebutuhan bisnis, dan mesin inferensi yang memanfaatkan sistem aturan untuk menyimpulkan fakta baru. - -Pada era ini juga terlihat adanya peningkatan perhatian pada jaringan saraf. - -## 1987 - 1993: AI 'Chill' - -Perkembangan perangkat keras sistem pakar terspesialisasi memiliki efek yang tidak menguntungkan karena menjadi terlalu terspesialiasasi. Munculnya komputer pribadi juga bersaing dengan sistem yang besar, terspesialisasi, dan terpusat ini. Demokratisasi komputasi telah dimulai, dan pada akhirnya membuka jalan untuk ledakan modern dari *big data*. - -## 1993 - 2011 - -Pada zaman ini memperlihatkan era baru bagi ML dan AI untuk dapat menyelesaikan beberapa masalah yang sebelumnya disebabkan oleh kurangnya data dan daya komputasi. Jumlah data mulai meningkat dengan cepat dan tersedia secara luas, terlepas dari baik dan buruknya, terutama dengan munculnya *smartphone* sekitar tahun 2007. Daya komputasi berkembang secara eksponensial, dan algoritma juga berkembang saat itu. Bidang ini mulai mengalami kedewasaan karena hari-hari yang tidak beraturan di masa lalu mulai terbentuk menjadi disiplin yang sebenarnya. - -## Sekarang - -Saat ini, *machine learning* dan AI hampir ada di setiap bagian dari kehidupan kita. Era ini menuntut pemahaman yang cermat tentang risiko dan efek potensi dari berbagai algoritma yang ada pada kehidupan manusia. Seperti yang telah dinyatakan oleh Brad Smith dari Microsoft, "Teknologi informasi mengangkat isu-isu yang menjadi inti dari perlindungan hak asasi manusia yang mendasar seperti privasi dan kebebasan berekspresi. Masalah-masalah ini meningkatkan tanggung jawab bagi perusahaan teknologi yang menciptakan produk-produk ini. Dalam pandangan kami, mereka juga menyerukan peraturan pemerintah yang bijaksana dan untuk pengembangan norma-norma seputar penggunaan yang wajar" ([sumber](https://www.technologyreview.com/2019/12/18/102365/the-future-of-ais-impact-on-society/)). - -Kita masih belum tahu apa yang akan terjadi di masa depan, tetapi penting untuk memahami sistem komputer dan perangkat lunak serta algoritma yang dijalankannya. Kami berharap kurikulum ini akan membantu kamu untuk mendapatkan pemahaman yang lebih baik sehingga kamu dapat memutuskan sendiri. - -[![Sejarah Deep Learning](https://img.youtube.com/vi/mTtDfKgLm54/0.jpg)](https://www.youtube.com/watch?v=mTtDfKgLm54 "Sejarah Deep Learning") -> đŸŽĨ Klik gambar diatas untuk menonton video: Yann LeCun mendiskusikan sejarah dari Deep Learning dalam pelajaran ini - ---- -## 🚀Tantangan - -Gali salah satu momen bersejarah ini dan pelajari lebih lanjut tentang orang-orang di baliknya. Ada karakter yang menarik, dan tidak ada penemuan ilmiah yang pernah dibuat dalam kekosongan budaya. Apa yang kamu temukan? - -## [Quiz Pasca-Pelajaran](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/4/) - -## Ulasan & Belajar Mandiri - -Berikut adalah item untuk ditonton dan didengarkan: - -[Podcast dimana Amy Boyd mendiskusikan evolusi dari AI](http://runasradio.com/Shows/Show/739) - -[![Sejarah AI oleh Amy Boyd](https://img.youtube.com/vi/EJt3_bFYKss/0.jpg)](https://www.youtube.com/watch?v=EJt3_bFYKss "Sejarah AI oleh Amy Boyd") - -## Tugas - -[Membuat sebuah *timeline*](assignment.id.md) diff --git a/1-Introduction/2-history-of-ML/translations/README.it.md b/1-Introduction/2-history-of-ML/translations/README.it.md deleted file mode 100644 index f95b542c..00000000 --- a/1-Introduction/2-history-of-ML/translations/README.it.md +++ /dev/null @@ -1,118 +0,0 @@ -# Storia di machine learning - -![Riepilogo della storia di machine learning in uno sketchnote](../../../sketchnotes/ml-history.png) -> Sketchnote di [Tomomi Imura](https://www.twitter.com/girlie_mac) - -## [Quiz pre-lezione](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/3/?loc=it) - -In questa lezione, si camminerà attraverso le principali pietre miliari nella storia di machine learning e dell'intelligenza artificiale. - -La storia dell'intelligenza artificiale, AI, come campo è intrecciata con la storia di machine learning, poichÊ gli algoritmi e i progressi computazionali alla base di machine learning hanno contribuito allo sviluppo dell'intelligenza artificiale. È utile ricordare che, mentre questi campi come distinte aree di indagine hanno cominciato a cristallizzarsi negli anni '50, importanti [scoperte algoritmiche, statistiche, matematiche, computazionali e tecniche](https://wikipedia.org/wiki/Timeline_of_machine_learning) hanno preceduto e si sono sovrapposte a questa era. In effetti, le persone hanno riflettuto su queste domande per [centinaia di anni](https://wikipedia.org/wiki/History_of_artificial_intelligence); questo articolo discute le basi intellettuali storiche dell'idea di una "macchina pensante". - -## Scoperte rilevanti - -- 1763, 1812 [Teorema di Bayes](https://it.wikipedia.org/wiki/Teorema_di_Bayes) e suoi predecessori. Questo teorema e le sue applicazioni sono alla base dell'inferenza, descrivendo la probabilità che un evento si verifichi in base alla conoscenza precedente. -- 1805 [Metodo dei Minimi Quadrati](https://it.wikipedia.org/wiki/Metodo_dei_minimi_quadrati) del matematico francese Adrien-Marie Legendre. Questa teoria, che verrà trattata nell'unità Regressione, aiuta nell'adattamento dei dati. -- 1913 [Processo Markoviano](https://it.wikipedia.org/wiki/Processo_markoviano) dal nome del matematico russo Andrey Markov è usato per descrivere una sequenza di possibili eventi basati su uno stato precedente. -- 1957 [Percettrone](https://it.wikipedia.org/wiki/Percettrone) è un tipo di classificatore lineare inventato dallo psicologo americano Frank Rosenblatt che sta alla base dei progressi nel deep learning. -- 1967 [Nearest Neighbor](https://wikipedia.org/wiki/Nearest_neighbor) è un algoritmo originariamente progettato per mappare i percorsi. In un contesto ML viene utilizzato per rilevare i modelli. -- 1970 [La Retropropagazione dell'Errore](https://it.wikipedia.org/wiki/Retropropagazione_dell'errore) viene utilizzata per addestrare [le reti neurali feed-forward](https://it.wikipedia.org/wiki/Rete_neurale_feed-forward). -- Le [Reti Neurali Ricorrenti](https://it.wikipedia.org/wiki/Rete_neurale_ricorrente) del 1982 sono reti neurali artificiali derivate da reti neurali feedforward che creano grafici temporali. - -✅ Fare una piccola ricerca. Quali altre date si distinguono come fondamentali nella storia del machine learning e dell'intelligenza artificiale? -## 1950: Macchine che pensano - -Alan Turing, una persona davvero notevole che è stata votata [dal pubblico nel 2019](https://wikipedia.org/wiki/Icons:_The_Greatest_Person_of_the_20th_Century) come il piÚ grande scienziato del XX secolo, è accreditato per aver contribuito a gettare le basi per il concetto di "macchina in grado di pensare". Ha affrontato gli oppositori e il suo stesso bisogno di prove empiriche di questo concetto in parte creando il [Test di Turing](https://www.bbc.com/news/technology-18475646), che verrà esplorato nelle lezioni di NLP (elaborazione del linguaggio naturale). - -## 1956: Progetto di Ricerca Estivo Dartmouth - -"Il Dartmouth Summer Research Project sull'intelligenza artificiale è stato un evento seminale per l'intelligenza artificiale come campo", qui è stato coniato il termine "intelligenza artificiale" ([fonte](https://250.dartmouth.edu/highlights/artificial-intelligence-ai-coined-dartmouth)). - -> In linea di principio, ogni aspetto dell'apprendimento o qualsiasi altra caratteristica dell'intelligenza puÃ˛ essere descritto in modo cosÃŦ preciso che si puÃ˛ costruire una macchina per simularlo. - -Il ricercatore capo, il professore di matematica John McCarthy, sperava "di procedere sulla base della congettura che ogni aspetto dell'apprendimento o qualsiasi altra caratteristica dell'intelligenza possa in linea di principio essere descritta in modo cosÃŦ preciso che si possa costruire una macchina per simularlo". I partecipanti includevano un altro luminare nel campo, Marvin Minsky. - -Il workshop è accreditato di aver avviato e incoraggiato diverse discussioni tra cui "l'ascesa di metodi simbolici, sistemi focalizzati su domini limitati (primi sistemi esperti) e sistemi deduttivi contro sistemi induttivi". ([fonte](https://wikipedia.org/wiki/Dartmouth_workshop)). - -## 1956 - 1974: "Gli anni d'oro" - -Dagli anni '50 fino alla metà degli anni '70, l'ottimismo era alto nella speranza che l'AI potesse risolvere molti problemi. Nel 1967, Marvin Minsky dichiarÃ˛ con sicurezza che "Entro una generazione... il problema della creazione di 'intelligenza artificiale' sarà sostanzialmente risolto". (Minsky, Marvin (1967), Computation: Finite and Infinite Machines, Englewood Cliffs, N.J.: Prentice-Hall) - -La ricerca sull'elaborazione del linguaggio naturale è fiorita, la ricerca è stata perfezionata e resa piÚ potente ed è stato creato il concetto di "micro-mondi", in cui compiti semplici sono stati completati utilizzando istruzioni in linguaggio semplice. - -La ricerca è stata ben finanziata dalle agenzie governative, sono stati fatti progressi nel calcolo e negli algoritmi e sono stati costruiti prototipi di macchine intelligenti. Alcune di queste macchine includono: - -* [Shakey il robot](https://wikipedia.org/wiki/Shakey_the_robot), che poteva manovrare e decidere come eseguire i compiti "intelligentemente". - - ![Shakey, un robot intelligente](../images/shakey.jpg) - > Shakey nel 1972 - -* Eliza, una delle prime "chatterbot", poteva conversare con le persone e agire come una "terapeuta" primitiva. Si Imparerà di piÚ su Eliza nelle lezioni di NLP. - - ![Eliza, un bot](../images/eliza.png) - > Una versione di Eliza, un chatbot - -* Il "mondo dei blocchi" era un esempio di un micromondo in cui i blocchi potevano essere impilati e ordinati e si potevano testare esperimenti su macchine per insegnare a prendere decisioni. I progressi realizzati con librerie come [SHRDLU](https://it.wikipedia.org/wiki/SHRDLU) hanno contribuito a far progredire l'elaborazione del linguaggio. - - [![Il mondo dei blocchi con SHRDLU](https://img.youtube.com/vi/QAJz4YKUwqw/0.jpg)](https://www.youtube.com/watch?v=QAJz4YKUwqw "Il mondo dei blocchi con SHRDLU") - - > đŸŽĨ Fare clic sull'immagine sopra per un video: Blocks world con SHRDLU - -## 1974 - 1980: "L'inverno dell'AI" - -Verso la metà degli anni '70, era diventato evidente che la complessità della creazione di "macchine intelligenti" era stata sottovalutata e che la sua promessa, data la potenza di calcolo disponibile, era stata esagerata. I finanziamenti si sono prosciugati e la fiducia nel settore è rallentata. Alcuni problemi che hanno influito sulla fiducia includono: - -- **Limitazioni**. La potenza di calcolo era troppo limitata. -- **Esplosione combinatoria**. La quantità di parametri necessari per essere addestrati è cresciuta in modo esponenziale man mano che veniva chiesto di piÚ ai computer, senza un'evoluzione parallela della potenza e delle capacità di calcolo. -- **Scarsità di dati**. C'era una scarsità di dati che ostacolava il processo di test, sviluppo e perfezionamento degli algoritmi. -- **Stiamo facendo le domande giuste?**. Le stesse domande che venivano poste cominciarono ad essere messe in discussione. I ricercatori hanno iniziato a criticare i loro approcci: - - I test di Turing furono messi in discussione attraverso, tra le altre idee, la "teoria della stanza cinese" che postulava che "la programmazione di un computer digitale puÃ˛ far sembrare che capisca il linguaggio ma non potrebbe produrre una vera comprensione". ([fonte](https://plato.stanford.edu/entries/chinese-room/)) - - L'etica dell'introduzione di intelligenze artificiali come la "terapeuta" ELIZA nella società è stata messa in discussione. - -Allo stesso tempo, iniziarono a formarsi varie scuole di pensiero sull'AI. È stata stabilita una dicotomia tra pratiche ["scruffy" contro "neat AI"](https://wikipedia.org/wiki/Neats_and_scruffies). I laboratori _scruffy_ ottimizzavano i programmi per ore fino a quando non ottenevano i risultati desiderati. I laboratori _Neat_ "si focalizzavano sulla logica e sulla risoluzione formale dei problemi". ELIZA e SHRDLU erano ben noti _sistemi scruffy_. Negli anni '80, quando è emersa la richiesta di rendere riproducibili i sistemi ML, l'_approccio neat_ ha gradualmente preso il sopravvento in quanto i suoi risultati sono piÚ spiegabili. - -## Sistemi esperti degli anni '80 - -Man mano che il settore cresceva, i suoi vantaggi per le imprese diventavano piÚ chiari e negli anni '80 lo stesso accadeva con la proliferazione di "sistemi esperti". "I sistemi esperti sono stati tra le prime forme di software di intelligenza artificiale (AI) di vero successo". ([fonte](https://wikipedia.org/wiki/Expert_system)). - -Questo tipo di sistema è in realtà _ibrido_, costituito in parte da un motore di regole che definisce i requisiti aziendali e un motore di inferenza che sfrutta il sistema di regole per dedurre nuovi fatti. - -Questa era ha visto anche una crescente attenzione rivolta alle reti neurali. - -## 1987 - 1993: AI 'Chill' - -La proliferazione di hardware specializzato per sistemi esperti ha avuto lo sfortunato effetto di diventare troppo specializzato. L'ascesa dei personal computer ha anche gareggiato con questi grandi sistemi centralizzati specializzati. La democratizzazione dell'informatica era iniziata e alla fine ha spianato la strada alla moderna esplosione dei big data. - -## 1993 - 2011 - -Questa epoca ha visto una nuova era per ML e AI per essere in grado di risolvere alcuni dei problemi che erano stati causati in precedenza dalla mancanza di dati e potenza di calcolo. La quantità di dati ha iniziato ad aumentare rapidamente e a diventare piÚ ampiamente disponibile, nel bene e nel male, soprattutto con l'avvento degli smartphone intorno al 2007. La potenza di calcolo si è ampliata in modo esponenziale e gli algoritmi si sono evoluti di pari passo. Il campo ha iniziato a maturare quando i giorni a ruota libera del passato hanno iniziato a cristallizzarsi in una vera disciplina. - -## Adesso - -Oggi, machine learning e intelligenza artificiale toccano quasi ogni parte della nostra vita. Questa era richiede un'attenta comprensione dei rischi e dei potenziali effetti di questi algoritmi sulle vite umane. Come ha affermato Brad Smith di Microsoft, "La tecnologia dell'informazione solleva questioni che vanno al cuore delle protezioni fondamentali dei diritti umani come la privacy e la libertà di espressione. Questi problemi aumentano la responsabilità delle aziende tecnologiche che creano questi prodotti. A nostro avviso, richiedono anche un'attenta regolamentazione del governo e lo sviluppo di norme sugli usi accettabili" ([fonte](https://www.technologyreview.com/2019/12/18/102365/the-future-of-ais-impact-on-society/)). - -Resta da vedere cosa riserva il futuro, ma è importante capire questi sistemi informatici e il software e gli algoritmi che eseguono. Ci si augura che questo programma di studi aiuti ad acquisire una migliore comprensione in modo che si possa decidere in autonomia. - -[![La storia del deeplearningLa](https://img.youtube.com/vi/mTtDfKgLm54/0.jpg)](https://www.youtube.com/watch?v=mTtDfKgLm54 " storia del deep learning") -> đŸŽĨ Fare clic sull'immagine sopra per un video: Yann LeCun discute la storia del deep learning in questa lezione - ---- - -## 🚀 Sfida - -Approfondire uno di questi momenti storici e scoprire - di piÚ sulle persone che stanno dietro ad essi. Ci sono personaggi affascinanti e nessuna scoperta scientifica è mai stata creata in un vuoto culturale. Cosa si è scoperto? - -## [Quiz post-lezione](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/4/?loc=it) - -## Revisione e Auto Apprendimento - -Ecco gli elementi da guardare e ascoltare: - -[Questo podcast in cui Amy Boyd discute l'evoluzione dell'AI](http://runasradio.com/Shows/Show/739) - -[![La storia dell'AI di Amy Boyd](https://img.youtube.com/vi/EJt3_bFYKss/0.jpg)](https://www.youtube.com/watch?v=EJt3_bFYKss "La storia dell'AI di Amy Boyd") - -## Compito - -[Creare una sequenza temporale](assignment.it.md) diff --git a/1-Introduction/2-history-of-ML/translations/README.ja.md b/1-Introduction/2-history-of-ML/translations/README.ja.md deleted file mode 100644 index 780b1f85..00000000 --- a/1-Introduction/2-history-of-ML/translations/README.ja.md +++ /dev/null @@ -1,114 +0,0 @@ -# 抟æĸ°å­Ļįŋ’ãŽæ­´å˛ - -![抟æĸ°å­Ļįŋ’ãŽæ­´å˛ã‚’ãžã¨ã‚ãŸã‚šã‚ąãƒƒãƒ](../../../sketchnotes/ml-history.png) -> [Tomomi Imura](https://www.twitter.com/girlie_mac)ãĢã‚ˆã‚‹ã‚šã‚ąãƒƒãƒ - -## [Pre-lecture quiz](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/3?loc=ja) - -こぎ授æĨ­ã§ã¯ã€æŠŸæĸ°å­Ļįŋ’とäēēåˇĨįŸĨčƒŊãŽæ­´å˛ãĢおけるä¸ģčĻãĒå‡ēæĨäē‹ã‚’į´šäģ‹ã—ぞす。 - -äēēåˇĨįŸĨčƒŊīŧˆAIīŧ‰ãŽæ­´å˛ã¯ã€æŠŸæĸ°å­Ļįŋ’ãŽæ­´å˛ã¨å¯†æŽĨãĢé–ĸäŋ‚しãĻいぞす。ãĒぜãĒらば、抟æĸ°å­Ļįŋ’を支えるã‚ĸãƒĢゴãƒĒã‚ēãƒ ã¨č¨ˆįŽ—ãŽé€˛æ­ŠãŒã€AIぎį™ēåą•ãĢつãĒがãŖたからです。これらぎ分野は、1950åš´äģŖãĢ明įĸēãĢãĒり始めぞしたが、重čĻãĒ[ã‚ĸãƒĢゴãƒĒã‚ēム、įĩąč¨ˆã€æ•°å­Ļã€č¨ˆįŽ—ã€æŠ€čĄ“įš„ãĒį™ēčĻ‹](https://wikipedia.org/wiki/Timeline_of_machine_learning)は、こぎ時äģŖよりも前ãĢ、そしãĻ同時ãĢčĄŒã‚ã‚ŒãĻいたことをčĻšãˆãĻおくとよいでしょう。原際、äēē々は[äŊ•į™žåš´ã‚‚](https://wikipedia.org/wiki/History_of_artificial_intelligence)ã“ãŽå•éĄŒãĢついãĻč€ƒãˆãĻきぞした。īŧˆã“ãŽč¨˜äē‹ã§ã¯ã€ã€Œč€ƒãˆã‚‹æŠŸæĸ°ã€ã¨ã„うã‚ĸイデã‚ĸãŽæ­´å˛įš„ãĒįŸĨįš„åŸēį›¤ãĢついãĻčĒŦ明されãĻいぞす。īŧ‰ - - -## æŗ¨į›Žã™ãšãį™ēčĻ‹ -- 1763嚴、1812åš´ [ベイã‚ēぎ厚į†](https://wikipedia.org/wiki/Bayes%27_theorem)とそぎ前čēĢぎį™ēčĻ‹ã€‚あるäē‹čąĄãŒčĩˇã“ã‚‹įĸēįŽ‡ã‚’、äē‹å‰ãŽįŸĨ識ãĢåŸēãĨいãĻ記čŋ°ã™ã‚‹æŽ¨čĢ–ぎåŸēį¤Žã¨ãĒる厚į†ã¨ããŽåŋœį”¨ã€‚ -- 1805åš´ フナãƒŗ゚ぎ数å­Ļ者ã‚ĸドãƒĒã‚ĸãƒŗīŧãƒžãƒĒãƒŧãƒģãƒŦジェãƒŗドãƒĢãĢよる[最小äēŒäš—į†čĢ–](https://wikipedia.org/wiki/Least_squares)。こぎį†čĢ–は、デãƒŧã‚ŋぎフã‚Ŗッテã‚ŖãƒŗグãĢåŊšįĢ‹ã¤ã€‚ -- 1913åš´ ãƒ­ã‚ˇã‚ĸぎ数å­Ļ者ã‚ĸãƒŗドãƒŦイãƒģマãƒĢã‚ŗフãĢãĄãĒんで名äģ˜ã‘られた[マãƒĢã‚ŗフé€Ŗ鎖](https://wikipedia.org/wiki/Markov_chain)は、äģĨ前ぎįŠļ態ãĢåŸēãĨいãĻčĩˇã“りうる一é€Ŗぎäē‹čąĄã‚’č¨˜čŋ°ã™ã‚‹ãŸã‚ãĢäŊŋį”¨ã•ã‚Œã‚‹ã€‚ -- 1957åš´ [パãƒŧã‚ģプトロãƒŗ](https://wikipedia.org/wiki/Perceptron)は、ã‚ĸãƒĄãƒĒã‚Ģぎåŋƒį†å­Ļč€…ãƒ•ãƒŠãƒŗクãƒģロãƒŧã‚ŧãƒŗブナットがį™ē明したįˇšåŊĸåˆ†éĄžå™¨ãŽä¸€į¨Žã§ã‚ã‚Šã€æˇąåą¤å­Ļįŋ’ぎåŸēį›¤ã¨ãĒãŖãĻいる。 -- 1967 [最小čŋ‘傍æŗ•](https://wikipedia.org/wiki/Nearest_neighbor)は、元々はįĩŒčˇ¯æŽĸį´ĸぎためãĢč€ƒæĄˆã•ã‚ŒãŸã‚ĸãƒĢゴãƒĒã‚ēム。MLではパã‚ŋãƒŧãƒŗぎ検å‡ēãĢį”¨ã„られる。 -- 1970åš´ [ãƒãƒƒã‚¯ãƒ—ãƒ­ãƒ‘ã‚˛ãƒŧã‚ˇãƒ§ãƒŗ](https://wikipedia.org/wiki/Backpropagation)をį”¨ã„ãĻ[フã‚ŖãƒŧドフりワãƒŧドãƒģニãƒĨãƒŧナãƒĢネットワãƒŧクīŧˆé †äŧæ’­åž‹ãƒ‹ãƒĨãƒŧナãƒĢネットワãƒŧクīŧ‰](https://wikipedia.org/wiki/Feedforward_neural_network)をå­Ļįŋ’する。 -- 1982åš´ [回帰型ニãƒĨãƒŧナãƒĢネットワãƒŧク](https://wikipedia.org/wiki/Recurrent_neural_network) は、フã‚ŖãƒŧドフりワãƒŧドãƒģニãƒĨãƒŧナãƒĢネットワãƒŧクから洞į”Ÿã—たäēēåˇĨįš„ãĒニãƒĨãƒŧナãƒĢネットワãƒŧクで、時間įš„ãĒグナフをäŊœæˆã—ぞす。 - -✅ 少しčĒŋずãĻãŋãĻください。MLとAIãŽæ­´å˛ãŽä¸­ã§é‡čĻãĒæ—Ĩäģ˜ã¯äģ–ãĢありぞすかīŧŸ - -## 1950: æ€č€ƒã™ã‚‹æŠŸæĸ° -ã‚ĸナãƒŗãƒģチãƒĨãƒŧãƒĒãƒŗグは、[2019åš´ãĢ世間から](https://wikipedia.org/wiki/Icons:_The_Greatest_Person_of_the_20th_Century)20世į´€æœ€å¤§ãŽį§‘å­Ļč€…ã¨ã—ãĻ投įĨ¨ã•ã‚ŒãŸã€įœŸãĢå„Ēれたäēēį‰Šã§ã€ã€Œč€ƒãˆã‚‹ã“とができる抟æĸ°ã€ã¨ã„うæĻ‚åŋĩぎåŸēį¤Žã‚’į¯‰ããŽãĢč˛ĸįŒŽã—たとされãĻいぞす。åŊŧは、åĻ厚įš„ãĒ意čĻ‹ã‚„、こぎæĻ‚åŋĩぎ原č¨ŧįš„ãĒč¨ŧ拠をåŋ…čĻã¨ã™ã‚‹č‡Ē分č‡ĒčēĢと、こぎ先č‡Ēį„ļ言čĒžå‡Ļį†ãŽæŽˆæĨ­ã§č§ĻれることとãĒる[チãƒĨãƒŧãƒĒãƒŗグãƒģテ゚ト](https://www.bbc.com/news/technology-18475646)をäŊœæˆã™ã‚‹ã“とでæˆĻいぞした。 - -## 1956: ダãƒŧトマ゚ãƒģã‚ĩマãƒŧãƒģãƒĒã‚ĩãƒŧチãƒģプロジェクト -ダãƒŧトマ゚ãƒģã‚ĩマãƒŧãƒģãƒĒã‚ĩãƒŧチãƒģプロジェクトは、分野としãĻぎäēēåˇĨįŸĨčƒŊãĢとãŖãĻ重čĻãĒå‡ēæĨäē‹ã§ã‚り、ここで「äēēåˇĨįŸĨčƒŊã€ã¨ã„ã†č¨€č‘‰ãŒäŊœã‚‰ã‚Œãžã—たīŧˆ[å‡ē典](https://250.dartmouth.edu/highlights/artificial-intelligence-ai-coined-dartmouth)īŧ‰ - -> å­Ļįŋ’やそぎäģ–ぎįŸĨčƒŊぎあらゆる側éĸは、原į†įš„ãĢ非常ãĢæ­ŖįĸēãĢ記čŋ°ã™ã‚‹ã“ã¨ãŒã§ãã‚‹ãŽã§ã€ãã‚Œã‚’ã‚ˇãƒŸãƒĨãƒŦãƒŧトする抟æĸ°ã‚’äŊœã‚‹ã“とができる。 - -ä¸ģäģģį ”įŠļč€…ã§ã‚ã‚‹æ•°å­Ļぎジョãƒŗãƒģマッã‚Ģãƒŧã‚ˇãƒŧ教授は、「å­Ļįŋ’ぎあらゆる側éĸやįŸĨčƒŊぎそぎäģ–ぎį‰šåž´ã¯ã€åŽŸį†įš„ãĢ非常ãĢæ­ŖįĸēãĢ記čŋ°ã™ã‚‹ã“ã¨ãŒã§ãã‚‹ãŽã§ã€ãã‚Œã‚’ã‚ˇãƒŸãƒĨãƒŦãƒŧトする抟æĸ°ã‚’äŊœã‚‹ã“とができるという推æ¸ŦãĢåŸēãĨいãĻé€˛ã‚ãĻã„ããŸã„ã€ã¨č€ƒãˆãĻã„ãžã—ãŸã€‚å‚åŠ č€…ãŽä¸­ãĢã¯ã€ã“ãŽåˆ†é‡ŽãŽč‘—åäēēであるマãƒŧビãƒŗãƒģミãƒŗã‚šã‚­ãƒŧもいぞした。 - -こぎワãƒŧã‚¯ã‚ˇãƒ§ãƒƒãƒ—ã§ã¯ã€ã€Œč¨˜åˇįš„手æŗ•ãŽå°é ­ã€é™åŽšã•ã‚ŒãŸé ˜åŸŸãĢį„Ļį‚šã‚’åŊ“ãĻãŸã‚ˇã‚šãƒ†ãƒ īŧˆåˆæœŸãŽã‚¨ã‚­ã‚šãƒ‘ãƒŧãƒˆã‚ˇã‚šãƒ†ãƒ īŧ‰ã€æŧ”įššįš„ã‚ˇã‚šãƒ†ãƒ ã¨å¸°į´įš„ã‚ˇã‚šãƒ†ãƒ ãŽæ¯”čŧƒã€ãĒãŠãŽč­°čĢ–が開始され、äŋƒé€˛ã•ã‚ŒãŸã¨čŠ•äžĄã•ã‚ŒãĻいぞす。īŧˆ[å‡ē典](https://wikipedia.org/wiki/Dartmouth_workshop)īŧ‰ - -## 1956 - 1974: éģ„金期 - -1950åš´äģŖから70åš´äģŖ半ばぞでは、AIがさぞざぞãĒå•éĄŒã‚’č§ŖæąēしãĻくれるぎではãĒいかというæĨŊčĻŗįš„ãĒčĻ‹æ–šãŒåēƒãŒãŖãĻいぞした。1967嚴、マãƒŧビãƒŗãƒģミãƒŗã‚šã‚­ãƒŧは「一世äģŖãŽã†ãĄãĢ...『äēēåˇĨįŸĨčƒŊ』をäŊœã‚‹ã¨ã„ã†å•éĄŒã¯åŽŸčŗĒįš„ãĢč§Ŗæąēされるだろう」とč‡ĒäŋĄã‚’持ãŖãĻčŋ°ãšãĻいる。(Minsky, Marvin (1967), Computation: Finite and Infinite Machines, Englewood Cliffs, N.J.: Prentice-Hall) - -č‡Ēį„ļ言čĒžå‡Ļį†ãŽį ”įŠļがį››ã‚“ãĢãĒり、検į´ĸが洗įˇ´ã•ã‚ŒãĻよりåŧˇåŠ›ãĢãĒり、åšŗ易ãĒ言čĒžãĢよる指į¤ēでį°Ąå˜ãĒäŊœæĨ­ã‚’こãĒす「マイクロワãƒŧãƒĢド」というæĻ‚åŋĩがį”Ÿãžã‚ŒãŸã€‚ - -į ”įŠļはæ”ŋåēœæŠŸé–ĸからæŊ¤æ˛ĸãĒčŗ‡é‡‘ãŒæäž›ã•ã‚Œã€č¨ˆįŽ—とã‚ĸãƒĢゴãƒĒã‚ēãƒ ãŒé€˛æ­Šã—ã€įŸĨįš„抟æĸ°ãŽãƒ—ロトã‚ŋイプがäŊœã‚‰ã‚ŒãŸã€‚そぎ中ãĢはæŦĄãŽã‚ˆã†ãĒもぎがある。 - -* į§ģ動したり、ã‚ŋã‚šã‚¯ã‚’åŽŸčĄŒã™ã‚‹æ–šæŗ•ã‚’「įŸĨįš„ãĢ」æąē厚することができるロボット[「Shakey」](https://wikipedia.org/wiki/Shakey_the_robot) - - ![įŸĨįš„ãĒロボットであるShakey](../images/shakey.jpg) - > 1972ぎShakey - -* 初期ぎ「おしゃずりロボット」であるElizaは、äēēとäŧščŠąã™ã‚‹ã“とができ、原始įš„ãĒ「ã‚ģナピ゚ト」ぎåŊšå‰˛ã‚’果たした。エãƒĒã‚ļãĢついãĻは、NLPぎãƒŦッ゚ãƒŗでčŠŗしくčĒŦ明しぞす。 - - ![BotであるEliza](../images/eliza.png) - > チãƒŖットボットEliza - -* 「Blocks world」は、ブロックをįŠãŋ上げたりä¸Ļずæ›ŋえたりするマイクロワãƒŧãƒĢドぎ一䞋で、抟æĸ°ãĢ判断力をčēĢãĢã¤ã‘ã•ã›ã‚‹åŽŸé¨“ã‚’čĄŒãŖた。[SHRDLU](https://wikipedia.org/wiki/SHRDLU)をはじめとするナイブナãƒĒãŽé€˛æ­Šã¯ã€č¨€čĒžå‡Ļį†ãŽį™ēåą•ãĢ大きくč˛ĸįŒŽã—た。 - - [![SHRDLUをį”¨ã„たblocks world](https://img.youtube.com/vi/QAJz4YKUwqw/0.jpg)](https://www.youtube.com/watch?v=QAJz4YKUwqw "SHRDLUをį”¨ã„たblocks world") - - > đŸŽĨ 上ぎį”ģ像をクãƒĒックすると動į”ģがčĻ‹ã‚‰ã‚Œãžã™īŧš"SHRDLUをį”¨ã„たblocks world" - -## 1974 - 1980: AIぎå†Ŧ - -1970åš´äģŖ半ばãĢãĒると、「įŸĨįš„ãĒ抟æĸ°ã€ã‚’äŊœã‚‹ã“ã¨ãŽč¤‡é›‘ã•ãŒéŽå°čŠ•äžĄã•ã‚ŒãĻいたことや、刊į”¨å¯čƒŊãĒ計įŽ—čƒŊåŠ›ã‚’č€ƒæ…Žã™ã‚‹ã¨ã€ããŽå°†æĨæ€§ãŒéŽå¤§čŠ•äžĄã•ã‚ŒãĻいたことが明らかãĢãĒりぞした。čŗ‡é‡‘が枯渇し、こぎ分野へぎäŋĄé ŧがäŊŽä¸‹ã—た。äŋĄé ŧ性ãĢåŊąéŸŋã‚’ä¸ŽãˆãŸå•éĄŒãĢはäģĨ下ぎようãĒもぎがある。: - -- **限į•Œ**. 計įŽ—čƒŊ力ぎ限į•Œ -- **įĩ„ãŋ合わせぎįˆ†į™ē**. å­Ļįŋ’ãĢåŋ…čĻãĒãƒ‘ãƒŠãƒĄãƒŧã‚ŋぎ量は、ã‚ŗãƒŗピãƒĨãƒŧã‚ŋãĢčĻæą‚されることが多くãĒるãĢつれãĻ指数é–ĸ数įš„ãĢåĸ—加しぞしたが、ã‚ŗãƒŗピãƒĨãƒŧã‚ŋぎ性čƒŊやčƒŊ力はä¸ĻčĄŒã—ãĻé€˛åŒ–ã—ãžã›ã‚“ã§ã—ãŸã€‚ -- **デãƒŧã‚ŋぎ少ãĒさ**. デãƒŧã‚ŋが不čļŗしãĻいたため、ã‚ĸãƒĢゴãƒĒã‚ēムぎテ゚ト、開į™ēã€æ”šč‰¯ãŽãƒ—ãƒ­ã‚ģ゚がåĻ¨ã’られた。 -- **æ­ŖしいčŗĒ問をしãĻいるぎかおうか**. 問いかけãĻいたčŗĒ問そぎもぎがį–‘問čĻ–され始めた。į ”įŠļč€…ãŸãĄã¯ã€č‡Ēåˆ†ãŸãĄãŽã‚ĸプロãƒŧチãĢ扚判įš„ãĒ意čĻ‹ã‚’持つようãĢãĒãŖた。 - - チãƒĨãƒŧãƒĒãƒŗグテ゚トは、「ã‚ŗãƒŗピãƒĨãƒŧã‚ŋをプログナミãƒŗã‚°ã™ã‚‹ã“ã¨ã§ã€č¨€čĒžã‚’į†č§ŖしãĻいるようãĢčĻ‹ã›ã‹ã‘ることはできるが、æœŦåŊ“ぎ意å‘ŗでぎį†č§ŖはできãĒい」とする「チãƒŖイニãƒŧã‚ēãƒĢãƒŧムį†čĢ–」ãĒおãĢよãŖãĻ、į–‘問čĻ–されるようãĢãĒãŖた。([å‡ē典](https://plato.stanford.edu/entries/chinese-room/)) - - ã‚ģナピ゚トとしãĻELIZAぎようãĒäēēåˇĨįŸĨčƒŊをį¤žäŧšãĢ導å…Ĩすることぎå€Ģį†æ€§ãŒå•ã‚ã‚ŒãŸã€‚ -それと同時ãĢ、さぞざぞãĒAIぎæĩæ´žãŒåŊĸ成され始めぞした。一つは、["Scruffy"と "Neat AI"](https://wikipedia.org/wiki/Neats_and_scruffies)というäēŒåˆ†æŗ•ã§ã‚る。ScruffyãĒį ”įŠļ厤では、į›Žįš„ぎįĩæžœãŒåž—られるぞでäŊ•æ™‚間もプログナムをいじãŖãĻいた一斚、neatãĒį ”įŠļ厤では、čĢ–į†ã¨åŊĸåŧįš„ãĒå•éĄŒč§Ŗæąēを重čĻ–する。ELIZAやSHRDLUãĒおが有名ãĒScruffyã§ã‚ã‚‹ã‚ˇã‚šãƒ†ãƒ ã§ã‚ã‚‹ã€‚1980åš´äģŖãĢå…ĨãŖãĻ、MLã‚ˇã‚šãƒ†ãƒ ãŽå†įžæ€§ãŒæą‚められるようãĢãĒると、įĩæžœãŒčĒŦ明可čƒŊであることから、æŦĄįŦŦãĢneatãĒã‚ĸプロãƒŧチがä¸ģæĩãĢãĒãŖãĻいきぞした。 - -## 1980s エキ゚パãƒŧãƒˆã‚ˇã‚šãƒ†ãƒ  - -分野がį™ēåą•ã™ã‚‹ãĢつれ、ビジネ゚へぎč˛ĸįŒŽãŒæ˜ŽįĸēãĢãĒり、1980åš´äģŖãĢは「エキ゚パãƒŧãƒˆã‚ˇã‚šãƒ†ãƒ ã€ãŒæ™ŽåŠã—ãžã—ãŸã€‚ã€Œã‚¨ã‚­ã‚šãƒ‘ãƒŧãƒˆã‚ˇã‚šãƒ†ãƒ ã¯ã€äēēåˇĨįŸĨčƒŊīŧˆAIīŧ‰ã‚Ŋフトã‚Ļェã‚ĸぎ中で最初ãĢįœŸãĢ成功したåŊĸæ…‹ãŽä¸€ã¤ã§ã‚ã‚‹ã€‚ã€ã¨č¨€ã‚ã‚ŒãĻいぞす。īŧˆ[å‡ē典](https://wikipedia.org/wiki/Expert_system)īŧ‰ - -こぎã‚ŋã‚¤ãƒ—ãŽã‚ˇã‚šãƒ†ãƒ ã¯ã€ãƒ“ã‚¸ãƒã‚ščĻäģļを厚įžŠã™ã‚‹ãƒĢãƒŧãƒĢエãƒŗジãƒŗと、ãƒĢãƒŧãƒĢã‚ˇã‚šãƒ†ãƒ ã‚’æ´ģį”¨ã—ãĻ新たãĒäē‹åŽŸã‚’推čĢ–する推čĢ–エãƒŗジãƒŗで構成されるハイブãƒĒッド型です。 - -ぞた、こぎ時äģŖはニãƒĨãƒŧナãƒĢネットワãƒŧクãĢもæŗ¨į›ŽãŒé›†ãžãŖた。 - -## 1987 - 1993: AIãŽå†ˇãˆčžŧãŋ - -専門分野ãĢį‰šåŒ–したエキ゚パãƒŧãƒˆã‚ˇã‚šãƒ†ãƒ ãŽãƒãƒŧドã‚Ļェã‚ĸが晎及したことで、専門性がéĢ˜ããĒりすぎãĻしぞうという掋åŋĩãĒįĩæžœãĢãĒりぞした。ぞた、パãƒŧã‚ŊナãƒĢã‚ŗãƒŗピãƒĨãƒŧã‚ŋぎ台頭は、これらぎ大čĻæ¨Ąã§å°‚é–€įš„ãĒ中夎集樊įš„ã‚ˇã‚šãƒ†ãƒ ã¨įĢļ合した。ã‚ŗãƒŗピãƒĨãƒŧテã‚Ŗãƒŗグぎ民ä¸ģ化が始ぞり、最įĩ‚įš„ãĢはįžäģŖぎįˆ†į™ēįš„ãĒビッグデãƒŧã‚ŋへぎ道が開かれぞした。 - -## 1993 - 2011 - -こぎ期間では、それäģĨ前ãĢデãƒŧã‚ŋã¨č¨ˆįŽ—čƒŊ力ぎ不čļŗãĢよãŖãĻåŧ•ãčĩˇã“されãĻã„ãŸå•éĄŒã‚’ã€MLやAIがč§ŖæąēできるようãĢãĒãŖãĻいた。į‰šãĢ2007åš´é ƒãĢ゚マãƒŧトフりãƒŗがį™ģå ´ã—ãŸã“ã¨ã§ã€č‰¯ãã‚‚æ‚Ēくもデãƒŧã‚ŋ量がæ€Ĩ速ãĢåĸ—加し、åēƒãåˆŠį”¨ã•ã‚Œã‚‹ã‚ˆã†ãĢãĒã‚Šãžã—ãŸã€‚č¨ˆįŽ—抟ぎ性čƒŊもéŖ›čēįš„ãĢ向上し、ã‚ĸãƒĢゴãƒĒã‚ēムもそれãĢ合わせãĻé€˛åŒ–ã—ãĻいきぞした。過åŽģぎč‡Ēį”ąåĨ”攞ãĒ時äģŖから、įœŸãŽå­Ļ問としãĻぎįĩæ™ļ化が始ぞり、こぎ分野は成į†Ÿã—ãĻいきぞした。 - -## įžåœ¨ - -įžåœ¨ã€æŠŸæĸ°å­Ļįŋ’ã‚„AIは、į§ãŸãĄãŽį”Ÿæ´ģぎãģãŧすずãĻぎ部分ãĢé–ĸわãŖãĻいぞす。こぎようãĒ時äģŖãĢは、これらぎã‚ĸãƒĢゴãƒĒã‚ēムがäēē間ぎį”Ÿæ´ģãĢ及ãŧすãƒĒ゚クやæŊœåœ¨įš„ãĒåŊąéŸŋをæŗ¨æ„æˇąãį†č§Ŗã™ã‚‹ã“ã¨ãŒæą‚ã‚ã‚‰ã‚Œãžã™ã€‚ãƒžã‚¤ã‚¯ãƒ­ã‚Ŋフトぎブナッドãƒģã‚šãƒŸã‚šã¯ã€ã€Œæƒ…å ąæŠ€čĄ“ã¯ã€ãƒ—ãƒŠã‚¤ãƒã‚ˇãƒŧã‚„čĄ¨įžãŽč‡Ēį”ąã¨ã„ãŖたåŸēæœŦįš„ãĒäēē樊äŋč­ˇãŽæ ¸åŋƒãĢčŋĢã‚‹å•éĄŒã‚’æčĩˇã—ãžã™ã€‚æƒ…å ąæŠ€čĄ“ã¯ã€ãƒ—ãƒŠã‚¤ãƒã‚ˇãƒŧã‚„čĄ¨įžãŽč‡Ēį”ąã¨ã„ãŖたåŸēæœŦįš„ãĒäēē樊äŋč­ˇãŽæ šåššãĢé–ĸã‚ã‚‹å•éĄŒã‚’æčĩˇã—ぞす。我々ぎčĻ‹č§Ŗã§ã¯ã€ã“ã‚Œã‚‰ãŽå•éĄŒã¯ã€æ”ŋåēœãĢã‚ˆã‚‹æ€æ…Žæˇąã„čĻåˆļã¨ã€č¨ąåŽšã•ã‚Œã‚‹äŊŋį”¨æ–šæŗ•ãĢé–ĸするčĻį¯„ぎį­–厚をåŋ…čĻã¨ã—ãĻいぞす。」とčŋ°ãšãĻいぞす。īŧˆ[å‡ē典](https://www.technologyreview.com/2019/12/18/102365/the-future-of-ais-impact-on-society/)īŧ‰ - -æœĒæĨがおうãĒるかはぞだわかりぞせんが、これらぎã‚ŗãƒŗピãƒĨãƒŧã‚ŋã‚ˇã‚šãƒ†ãƒ ã¨ã€ãã‚Œã‚’å‹•ã‹ã™ã‚Ŋフトã‚Ļェã‚ĸやã‚ĸãƒĢゴãƒĒã‚ēムをį†č§Ŗすることは重čĻã§ã™ã€‚こぎã‚ĢãƒĒキãƒĨナムがč‡ĒčēĢで判断するãĢã‚ãŸã‚Šã€ã‚ˆã‚Šč‰¯ã„į†č§Ŗを劊けるもぎãĢãĒると嚸いです。 - -[![デã‚Ŗãƒŧプナãƒŧニãƒŗã‚°ãŽæ­´å˛](https://img.youtube.com/vi/mTtDfKgLm54/0.jpg)](https://www.youtube.com/watch?v=mTtDfKgLm54 "デã‚Ŗãƒŧプナãƒŧニãƒŗã‚°ãŽæ­´å˛") -> đŸŽĨ 上ぎį”ģ像をクãƒĒックすると動į”ģがčĻ‹ã‚‰ã‚Œãžã™īŧšã“ぎãƒŦクチãƒŖãƒŧではYann LeCunがデã‚Ŗãƒŧプナãƒŧニãƒŗã‚°ãŽæ­´å˛ãĢついãĻč­°čĢ–しãĻいぞす。 - ---- -## 🚀Challenge - -ã“ã‚Œã‚‰ãŽæ­´å˛įš„įžŦ間ぎ1つを掘り下げãĻã€ããŽčƒŒåžŒãĢいるäēē々ãĢついãĻå­Ļãŗぞしょう。魅力įš„ãĒäēē々がいぞすし、文化įš„ãĢįŠēį™ŊぎįŠļ態でį§‘å­Ļįš„į™ēčĻ‹ãŒãĒされたことはありぞせん。おういãŖたことがčĻ‹ã¤ã‹ã‚‹ã§ã—ょうかīŧŸ - -## [Post-lecture quiz](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/4?loc=ja) - -## 振りčŋ”りとč‡Ēįŋ’ - -čĻ–č´ã™ã‚‹ãšãæ•™æã¯äģĨ下ãĢãĒりぞす: - -[Amy BoydがAIãŽé€˛åŒ–ãĢついãĻčŋ°ãšãĻいるポッドキãƒŖ゚ト](http://runasradio.com/Shows/Show/739) - -[![Amy BoydãĢよるAIãŽæ­´å˛](https://img.youtube.com/vi/EJt3_bFYKss/0.jpg)](https://www.youtube.com/watch?v=EJt3_bFYKss "Amy BoydãĢよるAIãŽæ­´å˛") - -## čĒ˛éĄŒ - -[åš´čĄ¨ã‚’äŊœæˆã™ã‚‹](./assignment.ja.md) diff --git a/1-Introduction/2-history-of-ML/translations/README.ko.md b/1-Introduction/2-history-of-ML/translations/README.ko.md deleted file mode 100644 index cf0a1dae..00000000 --- a/1-Introduction/2-history-of-ML/translations/README.ko.md +++ /dev/null @@ -1,118 +0,0 @@ -# 머ė‹ ëŸŦ닝ė˜ ė—­ė‚Ŧ - -![Summary of History of machine learning in a sketchnote](../../../sketchnotes/ml-history.png) -> Sketchnote by [Tomomi Imura](https://www.twitter.com/girlie_mac) - -## [강ė˜ ė „ 퀴ėĻˆ](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/3/) - -ė´ 강ė˜ė—ė„œ, 머ė‹ ëŸŦ닝ęŗŧ ė¸ęŗĩ ė§€ëŠĨė˜ ė—­ė‚Ŧė—ė„œ ėŖŧėš” 마ėŧėŠ¤í†¤ė„ ė‚´íŽ´ëŗ´ë ¤ 합니다. - -ė¸ęŗĩ ė§€ëŠĨ, AIė˜ ė—­ė‚Ŧ는 머ė‹ ëŸŦ닝ė˜ ė—­ė‚Ŧė™€ ė„œëĄœ ė—Žė—Ŧ ėžˆėœŧ늰, MLė„ 받ėŗėŖŧ는 ė•Œęŗ ëĻŦėĻ˜ęŗŧ ęŗ„ė‚° 기ėˆ ė´ AIė˜ 개발ė— 기ė—Ŧ했ėŠĩ니다. 독특한 탐ęĩŦ ė˜ė—­ėœŧ로 ė´ëŸ° ëļ„ė•ŧ는 1950년ė— ęĩŦė˛´ė ėœŧ로 ė‹œėž‘í–ˆė§€ë§Œ, ė¤‘ėš”í•œ [algorithmical, statistical, mathematical, computational and technical discoveries](https://wikipedia.org/wiki/Timeline_of_machine_learning)로 ė´ ė‹œëŒ€ëĨŧ ė˜¤ë˛„랊했다ęŗ  ėƒę°í•˜ëŠ” 게 ėœ ėšŠí•Šë‹ˆë‹¤. ė‹¤ė œëĄœ, ė‚Ŧ람들ė€ [hundreds of years](https://wikipedia.org/wiki/History_of_artificial_intelligence)동ė•ˆ ė´ ė§ˆëŦ¸ė„ ėƒę°í•´ė™”ėŠĩ니다: ė´ ė•„티클ė€ 'thinking machine'ëŧ는 개념ė˜ ė—­ė‚Ŧė  ė§€ė  토대ė— 대하ė—Ŧ ė´ė•ŧ기 합니다. - -## ėŖŧëĒŠí•  발ę˛Ŧ - -- 1763, 1812 [Bayes Theorem](https://wikipedia.org/wiki/Bayes%27_theorem)ęŗŧ ė „ėž„ėž. ė´ ė •ëĻŦė™€ ė ėšŠė€ ė‚Ŧė „ė§€ė‹ 기반ėœŧ로 ė´ë˛¤íŠ¸ę°€ 발ėƒí•  확ëĨ ė„ ė„¤ëĒ…í•  ėļ”률ė˜ 기ė´ˆę°€ 됩니다. -- 1805 [Least Square Theory](https://wikipedia.org/wiki/Least_squares) by 프랑ėŠ¤ ėˆ˜í•™ėž Adrien-Marie Legendre. Regression 단ėœ„ė—ė„œ ë°°ėš¸ ė´ ė´ëĄ ė€, 데ė´í„° í”ŧ팅ė— 도ė›€ė´ 됩니다. -- 1913 ëŸŦė‹œė•„ ėˆ˜í•™ėž Andrey Markovė˜ ė´ëĻ„ė—ė„œ ėœ ëž˜ëœ [Markov Chains](https://wikipedia.org/wiki/Markov_chain)는 ė´ė „ ėƒíƒœëĨŧ 기반ėœŧ로 가ëŠĨ한 ė´ë˛¤íŠ¸ė˜ ė‹œí€€ėŠ¤ëĨŧ ė„¤ëĒ…하는 데 ė‚ŦėšŠëŠë‹ˆë‹¤. -- 1957 [Perceptron](https://wikipedia.org/wiki/Perceptron)ė€ 미ęĩ­ ė‹ŦëĻŦ학ėž Frank Rosenblattė´ 개발한 linear classifierė˜ 한 타ėž…ėœŧ로 ë”ĨëŸŦ닝 발ė „ė„ 뒷받ėšŠë‹ˆë‹¤. -- 1967 [Nearest Neighbor](https://wikipedia.org/wiki/Nearest_neighbor)는 ė›ëž˜ ę˛Ŋ로ëĨŧ ë§ĩ핑하기 ėœ„í•œ ė•Œęŗ ëĻŦėĻ˜ėž…니다. ML contextė—ė„œ 패턴ė„ 감ė§€í•  때 ė‚ŦėšŠí•Šë‹ˆë‹¤. -- 1970 [Backpropagation](https://wikipedia.org/wiki/Backpropagation)ė€ [feedforward neural networks](https://wikipedia.org/wiki/Feedforward_neural_network)ëĨŧ 학ėŠĩ할 때 ė‚ŦėšŠí•Šë‹ˆë‹¤. -- 1982 [Recurrent Neural Networks](https://wikipedia.org/wiki/Recurrent_neural_network)는 ė‹œę°„ 그래프ëĨŧ ėƒė„ąí•˜ëŠ” feedforward neural networksė—ė„œ 파ėƒí•œ ė¸ęŗĩ ė‹ ę˛Ŋ망ėž…니다. - -✅ ėĄ°ę¸ˆ ėĄ°ė‚Ŧ해ëŗ´ė„¸ėš”. MLęŗŧ AIė˜ ė—­ė‚Ŧė—ė„œ ė¤‘ėš”í•œ 다ëĨ¸ 날ė§œëŠ” ė–¸ė œė¸ę°€ėš”? - -## 1950: ėƒę°í•˜ëŠ” 기ęŗ„ - -20ė„¸ę¸°ė˜ ėĩœęŗ  ęŗŧ학ėžëĄœ [by the public in 2019](https://wikipedia.org/wiki/Icons:_The_Greatest_Person_of_the_20th_Century)ė— ė„ íƒëœ, Alan Turingė€, 'machine that can think.'ëŧ는 개념ė˜ 기반ė„ ęĩŦėļ•í•˜ëŠ” 데ė— 기ė—Ŧ한 것ėœŧ로 평가되ęŗ  ėžˆėŠĩ니다. -NLP 강ė˜ė—ė„œ ė‚´í•„ [Turing Test](https://www.bbc.com/news/technology-18475646)ëĨŧ 만들ė–´ė„œ ëļ€ëļ„ė ėœŧ로 ė´ 개념ė— 대한 ę˛Ŋ험ė ė¸ 반대하는 ė‚Ŧ람들ęŗŧ 대ëĻŊ했ėŠĩ니다. - -## 1956: Dartmouth ė—ŦëĻ„ ė—°ęĩŦ 프로ė íŠ¸ - -"The Dartmouth Summer Research Project on artificial intelligence was a seminal event for artificial intelligence as a field," ([source](https://250.dartmouth.edu/highlights/artificial-intelligence-ai-coined-dartmouth))ė—ė„œ "ė¸ęŗĩ ė§€ëŠĨ"ė´ëŧ는 ėšŠė–´ę°€ 만들ė–´ėĄŒėŠĩ니다. - -> 학ėŠĩė˜ ëĒ¨ë“  ė¸ĄëŠ´ė´ë‚˜ ė§€ëŠĨė˜ 다ëĨ¸ 기ëŠĨė€ ė›ėš™ė ėœŧ로 ė •í™•í•˜ę˛Œ ė„œėˆ í•  ėˆ˜ ėžˆė–´ė„œ ė´ëĨŧ 따ëŧ 할 기ęŗ„ëĨŧ 만들 ėˆ˜ ėžˆėŠĩ니다. - -ėˆ˜ė„ ė—°ęĩŦė›ė¸, ėˆ˜í•™ ęĩėˆ˜ John McCarthy는, "to proceed on the basis of the conjecture that every aspect of learning or any other feature of intelligence can in principle be so precisely described that a machine can be made to simulate it."ė´ëŧęŗ  íŦ망했ėŠĩ니다. ė°¸ę°€í•œ ė‚Ŧ람들 ė¤‘ė—ė„œëŠ” Marvin Minsky도 ėžˆė—ˆėŠĩ니다. - -ė´ ė›ŒíŦėˆė€ "the rise of symbolic methods, systems focussed on limited domains (early expert systems), and deductive systems versus inductive systems." ([source](https://wikipedia.org/wiki/Dartmouth_workshop))ė„ íŦ함해ė„œ ė—ŦëŸŦ 토론ė„ ė‹œėž‘하ęŗ  ėžĨ려한 것ėœŧ로 평가됩니다. - -## 1956 - 1974: "The golden years" - -1950년대ëļ€í„° 70년대 ė¤‘ėˆœęšŒė§€ AI로 많ė€ ëŦ¸ė œëĨŧ 해결할 ėˆ˜ ėžˆë‹¤ęŗ  ë¯ŋė€ 낙관ėŖŧė˜ę°€ ėģ¤ėĄŒėŠĩ니다. 1967년 Marvin Minsky는 "Within a generation ... the problem of creating 'artificial intelligence' will substantially be solved." (Minsky, Marvin (1967), Computation: Finite and Infinite Machines, Englewood Cliffs, N.J.: Prentice-Hall)ė´ëŧęŗ  ėžė‹ ėžˆę˛Œ 말했ėŠĩ니다. - -natural language processing ė—°ęĩŦ가 발ė „하ęŗ , 검ėƒ‰ė´ 개ė„ ë˜ė–´ 더 강ë Ĩ해ėĄŒėœŧ늰, 단ėˆœí•œ ė–¸ė–´ ė§€ėš¨ėœŧ로 간단한 ėž‘ė—…ė„ ė™„ëŖŒí•˜ëŠ” 'micro-worlds'ëŧ는 개념ė´ ėƒę˛ŧėŠĩ니다. - -ė •ëļ€ ė§€ė›ė„ 받ėœŧ늰 ė—°ęĩŦ했ėœŧ늰, ęŗ„ė‚°ęŗŧ ė•Œęŗ ëĻŦėĻ˜ė´ 발ė „하늴ė„œ, ė§€ëŠĨė  기ęŗ„ė˜ 프로토 타ėž…ė´ 만들ė–´ėĄŒėŠĩ니다. ė´ëŸ° 기ęŗ„ ė¤‘ė— ėŧëļ€ëŠ” ė•„래ė™€ 같ėŠĩ니다: - -* [Shakey the robot](https://wikipedia.org/wiki/Shakey_the_robot), 'ė§€ëŠĨė 'ėœŧ로 ėž‘ė—…하는 방법ė„ ėĄ°ėĸ…하ęŗ  결ė •í•  ėˆ˜ ėžˆėŠĩ니다. - - ![Shakey, an intelligent robot](../images/shakey.jpg) - > Shakey in 1972 - -* ė´ˆę¸° 'chatterbot'ė¸, Eliza는, ė‚Ŧ람들ęŗŧ ė´ė•ŧ기하ęŗ  ė›ė‹œė  'ėš˜ëŖŒė‚Ŧ' ė—­í• ė„ 할 ėˆ˜ ėžˆė—ˆėŠĩ니다. NLP 강ė˜ė—ė„œ Elizaė— 대하ė—Ŧ ėžė„¸ížˆ ė•Œė•„ë´…ė‹œë‹¤. - - ![Eliza, a bot](../images/eliza.png) - > A version of Eliza, a chatbot - -* "Blocks world"는 블록ė„ ėŒ“ęŗ  ëļ„ëĨ˜í•  ėˆ˜ ėžˆëŠ” 마ė´íŦ로-ė›”ë“œė˜ ė˜ˆė‹œė´ëŠ°, 결ė •í•˜ëŠ” 기ęŗ„ëĨŧ 가ëĨ´ėš  ė‹¤í—˜ė„ 테ėŠ¤íŠ¸í•  ėˆ˜ ėžˆė—ˆėŠĩ니다. [SHRDLU](https://wikipedia.org/wiki/SHRDLU)ė™€ 같ė€ ëŧė´ë¸ŒëŸŦëĻŦ로 만들ė–´ė§„ 발ëĒ…ė€ language processingëĨŧ 발ė „ė‹œí‚¤ëŠ” 데 도ė›€ė´ 되ė—ˆėŠĩ니다. - - [![blocks world with SHRDLU](https://img.youtube.com/vi/QAJz4YKUwqw/0.jpg)](https://www.youtube.com/watch?v=QAJz4YKUwqw "blocks world with SHRDLU") - - > đŸŽĨ ė˜ėƒė„ ëŗ´ë ¤ëŠ´ ė´ë¯¸ė§€ 클ëĻ­: Blocks world with SHRDLU - -## 1974 - 1980: "AI Winter" - -1970년 ė¤‘ėˆœė—, 'ė¸ęŗĩ 기ęŗ„'ëĨŧ 만드는 ëŗĩėžĄë„ę°€ ęŗŧė†Œ 평가되면ė„œ, ėŖŧė–´ė§„ ėģ´í“¨í„° 파ė›ŒëĨŧ ęŗ ë ¤í•´ëŗ´ë‹ˆ, ꡸ ė•Ŋė†ė€ ęŗŧėžĨ된 것ė´ ëļ„ëĒ…í•´ėĄŒėŠĩ니다. ėžę¸ˆė´ ęŗ ę°ˆë˜ęŗ  현ėžĨė— 대한 ėžė‹ ę°ë„ 느려ėĄŒėŠĩ니다. ė‹ ëĸ°ė— ė˜í–Ĩė„ ė¤€ ė´ėŠˆëŠ” ė•„래ė— ėžˆėŠĩ니다: - -- **ė œí•œ**. ėģ´í“¨í„° ė„ąëŠĨė´ 너ëŦ´ ė œí•œë˜ė—ˆėŠĩ니다. -- **결합 파ė—´**. 훈련ė— 필ėš”í•œ 파ëŧ미터ė˜ ė–‘ė´ ėģ´í“¨í„° ė„ąëŠĨ, 기ëŠĨęŗŧ ëŗ„ę°œëĄœ ėģ´í“¨í„°ė˜ ėš”ė˛­ė— 따ëŧ 늘ė–´ë‚ŦėŠĩ니다. -- **데ė´í„° ëļ€ėĄą**. ė•Œęŗ ëĻŦėĻ˜ė„ 테ėŠ¤íŠ¸, 개발, ꡸ëĻŦęŗ  개ė„ í•  ėˆ˜ ė—†ę˛Œ 데ė´í„°ę°€ ëļ€ėĄąí–ˆėŠĩ니다. -- **ė˜Ŧ바ëĨ¸ ė§ˆëŦ¸ė¸ę°€ėš”?**. ė§ˆëŦ¸ë°›ė€ ꡸ ė§ˆëŦ¸ė— 바로 ëŦŧė—ˆėŠĩ니다. ė—°ęĩŦė›ë“¤ė€ ꡸ ė ‘ęˇŧ ë°Šė‹ė— 비판했ėŠĩ니다: - - 튜링 테ėŠ¤íŠ¸ëŠ” "programming a digital computer may make it appear to understand language but could not produce real understanding." ([source](https://plato.stanford.edu/entries/chinese-room/))하다ęŗ  가ė •í•œ, 'chinese room theory'ė˜ 다ëĨ¸ ė•„ė´ë””ė–´ė— ė˜í•´ ė˜ëŦ¸ė´ ėƒę˛ŧėŠĩ니다. - - "ėš˜ëŖŒė‚Ŧ" ELIZAė™€ 같ė€ ė¸ęŗĩ ė§€ëŠĨė„ ė‚Ŧ회ė— 도ėž…하늰 ėœ¤ëĻŦė— 도ė „í–ˆėŠĩ니다. - -동 ė‹œę°„대ė—, 다ė–‘í•œ AI 학ęĩę°€ 형ė„ąë˜ę¸° ė‹œėž‘í–ˆėŠĩ니다. ["scruffy" vs. "neat AI"](https://wikipedia.org/wiki/Neats_and_scruffies) ė‚Ŧė´ė— ė´ëļ„법ė´ 확ëĻŊ되ė—ˆėŠĩ니다. _Scruffy_ ė—°ęĩŦė‹¤ė€ ė›í•˜ëŠ” 결ęŗŧëĨŧ ė–ģė„ 때까ė§€ ëĒ‡ ė‹œę°„ 동ė•ˆ 프로그램ė„ 트ėœ…í–ˆėŠĩ니다. _Neat_ ė—°ęĩŦė‹¤ė€ ë…ŧëĻŦė™€ ęŗĩė‹ė  ëŦ¸ė œëĨŧ 해결하는 데ė— ė´ˆė ė„ 맞ėļ”ė—ˆėŠĩ니다. ELIZAė™€ SHRDLU는 ėž˜ ė•Œë ¤ė§„ _scruffy_ ė‹œėŠ¤í…œėž…니다. 1980년대ė—, ML ė‹œėŠ¤í…œė„ ėžŦ현할 ėˆ˜ ėžˆė–´ė•ŧ 된다는 ėš”ęĩŦė‚Ŧ항ė´ ėƒę˛ŧęŗ , _neat_ ë°Šė‹ė´ 더 결ęŗŧëĨŧ ė„¤ëĒ…í•  ėˆ˜ ėžˆė–´ė„œ ė ė°¨ ė„ ë‘ëĨŧ ė°¨ė§€í–ˆėŠĩ니다. - -## 1980s ė „ëŦ¸ę°€ ė‹œėŠ¤í…œ - -ė´ ëļ„ė•ŧ가 ė„ąėžĨ하며, 비ėĻˆë‹ˆėŠ¤ė— 대한 ė´ė ė´ ëĒ…확해ėĄŒęŗ , 1980년대ė— 'ė „ëŦ¸ę°€ ė‹œėŠ¤í…œ'ė´ 확ė‚°ë˜ė—ˆėŠĩ니다. "Expert systems were among the first truly successful forms of artificial intelligence (AI) software." ([source](https://wikipedia.org/wiki/Expert_system)). - -ė´ ė‹œėŠ¤í…œė˜ 타ėž…ė€, ė‹¤ė œëĄœ 비ėĻˆë‹ˆėŠ¤ ėš”ęĩŦė‚Ŧ항ė„ ė •ė˜í•˜ëŠ” ëŖ° ė—”ė§„ęŗŧ ėƒˆëĄœėš´ ė‚Ŧė‹¤ ėļ”ëĄ í•˜ëŠ” ëŖ° ė‹œėŠ¤í…œė„ 활ėšŠí•œ ėļ”률 ė—”ė§„ėœŧ로 ëļ€ëļ„ė  ęĩŦė„ąëœ _hybrid_ ėž…니다. - -ė´ëŸ° ė‹œëŒ€ė—ë„ neural networksė— 대한 관ė‹Ŧė´ 늘ė–´ë‚ŦėŠĩ니다. - -## 1987 - 1993: AI 'Chill' - -ė „ëŦ¸í™”된 ė „ëŦ¸ę°€ ė‹œėŠ¤í…œ 하드ė›¨ė–´ė˜ 확ė‚°ė€ 너ëŦ´ë‚˜ë„ ęŗ ė°¨ė›ë˜ëŠ” ëļˆėš´í•œ 결ęŗŧëĨŧ 가ė ¸ė™”ėŠĩ니다. 개ė¸ėšŠ ėģ´í“¨í„°ė˜ ëļ€ėƒė€ íŦęŗ , ė „ëŦ¸í™”된, ė¤‘ė•™í™” ė‹œėŠ¤í…œęŗŧ ę˛ŊėŸí–ˆėŠĩ니다. ėģ´í“¨íŒ…ė˜ ë¯ŧėŖŧ화가 ė‹œėž‘되ė—ˆęŗ , 결ęĩ­ 현대ė˜ 빅 데ė´í„° 폭발ė„ ėœ„í•œ 길ė„ ė—´ė—ˆėŠĩ니다. - -## 1993 - 2011 - -ė´ ė‹œëŒ€ė—ëŠ” MLęŗŧ AI가 ęŗŧęą° 데ė´í„°ė™€ ėģ´í“¨í„° 파ė›Œ ëļ€ėĄąėœŧ로 ė¸í•´ 발ėƒí–ˆë˜ ëŦ¸ė œ ė¤‘ ėŧëļ€ 해결할 ėˆ˜ ėžˆëŠ” ėƒˆëĄœėš´ ė‹œëŒ€ę°€ ė—´ë ¸ėŠĩ니다. 데ė´í„°ė˜ ė–‘ė€ 급격히 늘ė–´ë‚˜ę¸° ė‹œėž‘í–ˆęŗ , 2007년ė— ėŠ¤ë§ˆíŠ¸í°ė´ 나ė˜¤ëŠ´ė„œ ėĸ‹ë“  나ė˜ë“  더 넓게 ė‚ŦėšŠí•  ėˆ˜ ėžˆę˛Œ 되ė—ˆėŠĩ니다. ėģ´í“¨í„° 파ė›ŒëŠ” íŦ게 확ėžĨ되ė—ˆęŗ , ė•Œęŗ ëĻŦėĻ˜ë„ 함ęģ˜ 발ė „í–ˆėŠĩ니다. ęŗŧęą° ėžėœ ëĄ­ë˜ ė‹œëŒ€ė—ė„œ ė§„ė •í•œ 규ėœ¨ëĄœ ė´ ëļ„ė•ŧ는 ė„ąėˆ™í•´ė§€ę¸° ė‹œėž‘í–ˆėŠĩ니다. - -## 현ėžŦ - -ė˜¤ëŠ˜ 날, 머ė‹ ëŸŦ닝ęŗŧ AI는 ė¸ėƒė˜ 대ëļ€ëļ„ė— ė˜í–Ĩė„ 미ėšŠë‹ˆë‹¤. ė´ ė‹œëŒ€ė—ëŠ” ė´ëŸŦ한 ė•Œęŗ ëĻŦėĻ˜ė´ ė¸ę°„ė˜ ė¸ėƒė— 미ėš˜ëŠ” ėœ„í—˜ęŗŧ ėž ėžŦė ė¸ ė˜í–Ĩė— 대한 ėŖŧė˜ęšŠė€ ė´í•´ë„ę°€ ėš”ęĩŦ됩니다. Microsoftė˜ Brad Smith가 ė–¸ę¸‰í•Šë‹ˆë‹¤ "Information technology raises issues that go to the heart of fundamental human-rights protections like privacy and freedom of expression. These issues heighten responsibility for tech companies that create these products. In our view, they also call for thoughtful government regulation and for the development of norms around acceptable uses" ([source](https://www.technologyreview.com/2019/12/18/102365/the-future-of-ais-impact-on-society/)). - -ë¯¸ëž˜ę°€ ė–´ë–ģ게 ëŗ€í• ė§€ ė•Œ ėˆ˜ ė—†ė§€ë§Œ, ėģ´í“¨í„° ė‹œėŠ¤í…œęŗŧ ė´ëĨŧ ė‹¤í–‰í•˜ëŠ” ė†Œí”„트ė›¨ė–´ė™€ ė•Œęŗ ëĻŦėĻ˜ė„ ė´í•´í•˜ëŠ” 것ė€ ė¤‘ėš”핊니다. ė´ ėģ¤ëĻŦ큘ëŸŧėœŧ로 더 ėž˜ ė´í•´í•˜ęŗ  ėŠ¤ėŠ¤ëĄœ 결ė •í•  ėˆ˜ ėžˆę˛Œ 되기ëĨŧ 바랍니다. - -[![The history of deep learning](https://img.youtube.com/vi/mTtDfKgLm54/0.jpg)](https://www.youtube.com/watch?v=mTtDfKgLm54 "The history of deep learning") -> đŸŽĨ ė˜ėƒ ëŗ´ë ¤ëŠ´ ėœ„ ė´ë¯¸ė§€ 클ëĻ­: Yann LeCunė´ 강ė˜ė—ė„œ ë”ĨëŸŦ닝ė˜ ė—­ė‚ŦëĨŧ ė´ė•ŧ기 합니다. - ---- -## 🚀 도ė „ - -ė—­ė‚Ŧė ė¸ ėˆœę°„ė— ė‚Ŧ람들 뒤ė—ė„œ 한 가ė§€ëĨŧ ė§‘ė¤‘ė ėœŧ로 파ęŗ  ėžˆëŠ” ėžëĨŧ ėžė„¸ížˆ ė•Œė•„ëŗ´ė„¸ėš”. 매ë ĨėžˆëŠ” ėēëĻ­í„°ę°€ ėžˆėœŧ늰, ëŦ¸í™”ę°€ ė‚Ŧëŧė§„ ęŗŗė—ė„œëŠ” ęŗŧ학ė ė¸ 발ę˛Ŧė„ 하ė§€ ëĒģ합니다. 당ė‹ ė€ ė–´ë–¤ 발ę˛Ŧė„ 해ëŗ´ė•˜ë‚˜ėš”? - -## [강ė˜ 후 퀴ėĻˆ](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/4/) - -## 검토 & ėžę¸°ėŖŧ도 학ėŠĩ - -ëŗ´ęŗ  들ė„ ėˆ˜ ėžˆëŠ” 항ëĒŠė€ ė•„래ė™€ 같ėŠĩ니다: - -[This podcast where Amy Boyd discusses the evolution of AI](http://runasradio.com/Shows/Show/739) - -[![The history of AI by Amy Boyd](https://img.youtube.com/vi/EJt3_bFYKss/0.jpg)](https://www.youtube.com/watch?v=EJt3_bFYKss "The history of AI by Amy Boyd") - -## ęŗŧė œ - -[Create a timeline](../assignment.md) diff --git a/1-Introduction/2-history-of-ML/translations/README.pt-br.md b/1-Introduction/2-history-of-ML/translations/README.pt-br.md deleted file mode 100644 index 815c8722..00000000 --- a/1-Introduction/2-history-of-ML/translations/README.pt-br.md +++ /dev/null @@ -1,118 +0,0 @@ -# HistÃŗria do machine learning - -![Resumo da histÃŗria do machine learning no sketchnote](../../../sketchnotes/ml-history.png) -> Sketchnote por [Tomomi Imura](https://www.twitter.com/girlie_mac) - -## [Teste prÊ-aula](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/3?loc=ptbr) - -Nesta liçÃŖo, veremos os principais marcos da histÃŗria do machine learning e da artificial intelligence. - -A histÃŗria da inteligÃĒncia artificial, IA, como um campo estÃĄ entrelaçada com a histÃŗria do machine learning, pois os algoritmos e os avanços computacionais por trÃĄs do machine learning contribuíram para o desenvolvimento da inteligÃĒncia artificial. É Ãētil lembrar que, embora esses campos como ÃĄreas distintas de investigaçÃŖo tenham começado a se cristalizar na dÊcada de 1950, importantes [descobertas algorítmicas, estatísticas, matemÃĄticas, computacionais e tÊcnicas](https://wikipedia.org/wiki/Timeline_of_machine_learning) -precederam e se sobrepuseram com esta Êpoca. Na verdade, as pessoas tÃĒm refletido sobre essas questÃĩes por [centenas de anos](https://wikipedia.org/wiki/History_of_artificial_intelligence): este artigo discute a base intelectual histÃŗrica da ideia de uma 'mÃĄquina pensante'. - -## Descobertas notÃĄveis - -- 1763, 1812 [Teorema de Bayes](https://wikipedia.org/wiki/Bayes%27_theorem) e seus predecessores. Este teorema e suas aplicaçÃĩes fundamentam a inferÃĒncia, descrevendo a probabilidade de um evento ocorrer com base em conhecimento prÊvio. -- 1805 [Teoria dos Mínimos Quadrados](https://wikipedia.org/wiki/Least_squares) pelo matemÃĄtico francÃĒs Adrien-Marie Legendre. Esta teoria, que vocÃĒ aprenderÃĄ em nossa unidade de regressÃŖo, ajuda no ajuste de dados. -- 1913 [Cadeias de Markov](https://wikipedia.org/wiki/Markov_chain) com o nome do matemÃĄtico russo Andrey Markov Ê usado para descrever uma sequÃĒncia de eventos possíveis com base em um estado anterior. -- 1957 [Perceptron](https://wikipedia.org/wiki/Perceptron) Ê um tipo de classificador linear inventado pelo psicÃŗlogo americano Frank Rosenblatt que fundamenta os avanços no aprendizado profundo. -- 1967 [Vizinho mais prÃŗximo](https://wikipedia.org/wiki/Nearest_neighbor) Ê um algoritmo originalmente projetado para mapear rotas. Em um contexto de ML, ele Ê usado para detectar padrÃĩes. -- 1970 [Backpropagation](https://wikipedia.org/wiki/Backpropagation) Ê usado para treinar [redes neurais feedforward](https://wikipedia.org/wiki/Feedforward_neural_network). -- 1982 [Redes Neurais Recorrentes](https://wikipedia.org/wiki/Recurrent_neural_network) sÃŖo redes neurais artificiais derivadas de redes neurais feedforward que criam grÃĄficos temporais. - -✅ Faça uma pequena pesquisa. Que outras datas se destacam como fundamentais na histÃŗria do ML e da AI? - -## 1950: MÃĄquinas que pensam - -Alan Turing, uma pessoa verdadeiramente notÃĄvel que foi eleita [pelo pÃēblico em 2019](https://wikipedia.org/wiki/Icons:_The_Greatest_Person_of_the_20th_Century) como o maior cientista do sÊculo 20, Ê creditado por ajudar a lançar as bases para o conceito de uma 'mÃĄquina que pode pensar'. Ele lutou contra os pessimistas e sua prÃŗpria necessidade de evidÃĒncias empíricas desse conceito, em parte criando o [Teste de Turing](https://www.bbc.com/news/technology-18475646), que vocÃĒ explorarÃĄ em nossas liçÃĩes de NPL. - -## 1956: Projeto de Pesquisa de VerÃŖo de Dartmouth - -"O Projeto de Pesquisa de VerÃŖo de Dartmouth sobre inteligÃĒncia artificial foi um evento seminal para a inteligÃĒncia artificial como um campo", e foi aqui que o termo 'inteligÃĒncia artificial (AI)' foi cunhado ([fonte](https://250.dartmouth.edu/highlights/artificial-intelligence-ai-coined-dartmouth)). - -> Cada aspecto da aprendizagem ou qualquer outra característica da inteligÃĒncia pode, em princípio, ser descrito com tanta precisÃŖo que uma mÃĄquina pode ser feita para simulÃĄ-lo. - -O pesquisador principal, professor de matemÃĄtica John McCarthy, esperava "proceder com base na conjectura de que cada aspecto do aprendizado ou qualquer outra característica da inteligÃĒncia pode, em princípio, ser descrito de forma tÃŖo precisa que uma mÃĄquina pode ser feita para simulÃĄ-lo". Os participantes incluíram outro luminar da ÃĄrea, Marvin Minsky. - -O workshop Ê creditado por ter iniciado e encorajado vÃĄrias discussÃĩes, incluindo "o surgimento de mÊtodos simbÃŗlicos, sistemas focados em domínios limitados (primeiros sistemas especialistas) e sistemas dedutivos versus sistemas indutivos." ([fonte](https://wikipedia.org/wiki/Dartmouth_workshop)). - -## 1956 - 1974: "Os anos dourados" - -Dos anos 1950 atÊ meados dos anos 1970, o otimismo era alto na esperança de que a IA pudesse resolver muitos problemas. Em 1967, Marvin Minsky afirmou com segurança que "dentro de uma geraçÃŖo ... o problema de criar 'inteligÃĒncia artificial' serÃĄ substancialmente resolvido." (Minsky, Marvin (1967), Computation: Finite and Infinite Machines, Englewood Cliffs, N.J.: Prentice-Hall) - -A pesquisa em processamento de linguagem natural floresceu, a pesquisa foi refinada e tornada mais poderosa, e o conceito de "micro-mundos" foi criado, no qual tarefas simples sÃŖo concluídas usando instruçÃĩes de linguagem simples. - -A pesquisa foi bem financiada por agÃĒncias governamentais, avanços foram feitos em computaçÃŖo e algoritmos e protÃŗtipos de mÃĄquinas inteligentes foram construídos. Algumas dessas mÃĄquinas incluem: - -* [Shakey o robô](https://wikipedia.org/wiki/Shakey_the_robot), quem poderia manobrar e decidir como realizar as tarefas de forma 'inteligente'. - - ![Shakey, o robô inteligente](../images/shakey.jpg) - > Shakey em 1972 - -* Eliza, um dos primeiros 'chatterbot', podia conversar com as pessoas e agir como uma 'terapeuta' primitiva. VocÃĒ aprenderÃĄ mais sobre Eliza nas liçÃĩes de NPL. - - ![Eliza, a bot](../images/eliza.png) - > Uma versÃŖo de Eliza, um chatbot - -* O "mundo dos blocos" era um exemplo de micro-mundo onde os blocos podiam ser empilhados e classificados, e experimentos em mÃĄquinas de ensino para tomar decisÃĩes podiam ser testados. Avanços construídos com bibliotecas como [SHRDLU](https://wikipedia.org/wiki/SHRDLU) ajudaram a impulsionar o processamento de linguagem. - - [![mundo dos blocos com SHRDLU](https://img.youtube.com/vi/QAJz4YKUwqw/0.jpg)](https://www.youtube.com/watch?v=QAJz4YKUwqw "mundo dos blocos com SHRDLU") - - > đŸŽĨ Clique na imagem acima para ver um vídeo: Mundo dos blocos com SHRDLU - -## 1974 - 1980: "O inverno da AI" - -Em meados da dÊcada de 1970, ficou claro que a complexidade de criar 'mÃĄquinas inteligentes' havia sido subestimada e que sua promessa, dado o poder de computaçÃŖo disponível, havia sido exagerada. O financiamento secou e a confiança no setor desacelerou. Alguns problemas que afetaram a confiança incluem: - -- **LimitaçÃĩes**. O poder de computaçÃŖo era muito limitado. -- **ExplosÃŖo combinatÃŗria**. A quantidade de parÃĸmetros que precisavam ser treinados cresceu exponencialmente à medida que mais computadores eram exigidos, sem uma evoluçÃŖo paralela no poder e nas capacidades de computaçÃŖo. -- **Falta de dados**. Havia uma escassez de dados que dificultou o processo de teste, desenvolvimento e refinamento dos algoritmos. -- **Estamos fazendo as perguntas certas?**. As prÃŗprias perguntas que estavam sendo feitas começaram a ser questionadas. Os pesquisadores começaram a criticar suas abordagens: - - Os testes de Turing foram desafiados atravÊs, entre outras ideias, da 'teoria da sala chinesa' que postulava que "programar um computador digital pode fazer com que pareça compreender a linguagem, mas nÃŖo pode produzir uma compreensÃŖo verdadeira". ([fonte](https://plato.stanford.edu/entries/chinese-room/)) - - A Êtica da introduçÃŖo de inteligÃĒncias artificiais como o "terapeuta" de ELIZA na sociedade tem sido questionada. - -Ao mesmo tempo, vÃĄrias escolas de pensamento de IA começaram a se formar. Uma dicotomia foi estabelecida entre as prÃĄticas ["scruffy" versus "neat AI"](https://wikipedia.org/wiki/Neats_and_scruffies). O laboratÃŗrio do _Scruffy_ otimizou os programas por horas atÊ obter os resultados desejados. O laboratÃŗrio do _Neat_ "focava na soluçÃŖo de problemas lÃŗgicos e formais". ELIZA e SHRDLU eram sistemas desalinhados bem conhecidos. Na dÊcada de 1980, quando surgiu a demanda para tornar os sistemas de ML reproduzíveis, a abordagem _neat_ gradualmente assumiu o controle, à medida que seus resultados eram mais explicÃĄveis. - -## Sistemas especialistas de 1980 - -À medida que o campo cresceu, seus benefícios para os negÃŗcios tornaram-se mais claros e, na dÊcada de 1980, o mesmo aconteceu com a proliferaçÃŖo de 'sistemas especialistas'. "Os sistemas especialistas estavam entre as primeiras formas verdadeiramente bem-sucedidas de software de inteligÃĒncia artificial (AI)." ([fonte](https://wikipedia.org/wiki/Expert_system)). - -Na verdade, esse tipo de sistema Ê _híbrido_, consistindo parcialmente em um mecanismo de regras que define os requisitos de negÃŗcios e um mecanismo de inferÃĒncia que potencializa o sistema de regras para deduzir novos fatos. - -Essa era tambÊm viu uma crescente atençÃŖo dada às redes neurais. - -## 1987 - 1993: AI 'Chill' - -A proliferaçÃŖo de hardware de sistemas especialistas especializados teve o infeliz efeito de se tornar muito especializado. A ascensÃŖo dos computadores pessoais tambÊm competiu com esses sistemas grandes, especializados e centralizados. A democratizaçÃŖo da computaçÃŖo havia começado e, por fim, pavimentou o caminho para a explosÃŖo moderna de big data. - -## 1993 - 2011 - -Essa Êpoca viu uma nova era para o ML e a AI serem capazes de resolver alguns dos problemas que eram causados anteriormente pela falta de dados e capacidade de computaçÃŖo. A quantidade de dados começou a aumentar rapidamente e se tornar mais amplamente disponível, para melhor e para pior, especialmente com o advento do smartphone por volta de 2007. O poder de computaçÃŖo se expandiu exponencialmente e os algoritmos evoluíram junto. O campo começou a ganhar maturidade à medida que os dias livres do passado começaram a se cristalizar em uma verdadeira disciplina. - -## Agora - -Hoje, o machine learning e a inteligÃĒncia artificial afetam quase todas as partes de nossa vida. Esta era requer uma compreensÃŖo cuidadosa dos riscos e efeitos potenciais desses algoritmos em vidas humanas. Como disse Brad Smith, da Microsoft, "a tecnologia da informaçÃŖo levanta questÃĩes que vÃŖo ao cerne das proteçÃĩes fundamentais dos direitos humanos, como privacidade e liberdade de expressÃŖo. Essas questÃĩes aumentam a responsabilidade das empresas de tecnologia que criam esses produtos. Observe, elas tambÊm exigem um governo cuidadoso regulamentaçÃŖo e o desenvolvimento de padrÃĩes sobre usos aceitÃĄveis​​" ([fonte](https://www.technologyreview.com/2019/12/18/102365/the-future-of-ais-impact-on-society/)). - -Resta saber o que o futuro reserva, mas Ê importante entender esses sistemas de computador e o software e algoritmos que eles executam. Esperamos que este curso lhe ajude a obter um melhor entendimento para que vocÃĒ possa decidir por si mesmo. - -[![A histÃŗria do deep learning](https://img.youtube.com/vi/mTtDfKgLm54/0.jpg)](https://www.youtube.com/watch?v=mTtDfKgLm54 "A histÃŗria do deep learning") -> đŸŽĨ Clique na imagem acima para ver um vídeo: Yann LeCun discute a histÃŗria do deep learning nesta palestra - ---- -## 🚀Desafio - -Explore um desses momentos histÃŗricos e aprenda mais sobre as pessoas por trÃĄs deles. Existem personagens fascinantes e nenhuma descoberta científica foi criada em um vÃĄcuo cultural. O que vocÃĒ descobriu? - -## [QuestionÃĄrio pÃŗs-aula](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/4?loc=ptbr) - -## RevisÃŖo e Autoestudo - -Aqui estÃŖo os itens para assistir e ouvir: - -[Este podcast em que Amy Boyd discute a evoluçÃŖo da AI](http://runasradio.com/Shows/Show/739) - -[![A histÃŗria da AI ​​por Amy Boyd](https://img.youtube.com/vi/EJt3_bFYKss/0.jpg)](https://www.youtube.com/watch?v=EJt3_bFYKss "A histÃŗria da AI ​​por Amy Boyd") - -## Tarefa - -[Crie uma linha do tempo](assignment.pt-br.md) diff --git a/1-Introduction/2-history-of-ML/translations/README.ru.md b/1-Introduction/2-history-of-ML/translations/README.ru.md deleted file mode 100644 index 013cf9cb..00000000 --- a/1-Introduction/2-history-of-ML/translations/README.ru.md +++ /dev/null @@ -1,146 +0,0 @@ -# ИŅŅ‚ĐžŅ€Đ¸Ņ ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐŗĐž ОйŅƒŅ‡ĐĩĐŊиŅ - -![КŅ€Đ°Ņ‚ĐēĐžĐĩ иСĐģĐžĐļĐĩĐŊиĐĩ иŅŅ‚ĐžŅ€Đ¸Đ¸ ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐŗĐž ОйŅƒŅ‡ĐĩĐŊиŅ в СаĐŧĐĩŅ‚ĐēĐĩ](../../../sketchnotes/ml-history.png) -> ЗаĐŧĐĩŅ‚ĐēĐ° [ĐĸĐžĐŧĐžĐŧи ИĐŧŅƒŅ€Đ°](https://www.twitter.com/girlie_mac) - -## [ĐĸĐĩŅŅ‚ ĐŋĐĩŅ€ĐĩĐ´ ĐģĐĩĐēŅ†Đ¸ĐĩĐš](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/3/) - ---- - -На ŅŅ‚ĐžĐŧ ŅƒŅ€ĐžĐēĐĩ ĐŧŅ‹ Ņ€Đ°ŅŅĐŧĐžŅ‚Ņ€Đ¸Đŧ ĐžŅĐŊОвĐŊŅ‹Đĩ вĐĩŅ…и в иŅŅ‚ĐžŅ€Đ¸Đ¸ ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐŗĐž ОйŅƒŅ‡ĐĩĐŊиŅ и иŅĐēŅƒŅŅŅ‚вĐĩĐŊĐŊĐžĐŗĐž иĐŊŅ‚ĐĩĐģĐģĐĩĐēŅ‚Đ°. - -ИŅŅ‚ĐžŅ€Đ¸Ņ иŅĐēŅƒŅŅŅ‚вĐĩĐŊĐŊĐžĐŗĐž иĐŊŅ‚ĐĩĐģĐģĐĩĐēŅ‚Đ° (ИИ) ĐēĐ°Đē ОйĐģĐ°ŅŅ‚и ĐŋĐĩŅ€ĐĩĐŋĐģĐĩŅ‚Đ°ĐĩŅ‚ŅŅ Ņ иŅŅ‚ĐžŅ€Đ¸ĐĩĐš ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐŗĐž ОйŅƒŅ‡ĐĩĐŊиŅ (machine learning, ML), ĐŋĐžŅĐēĐžĐģŅŒĐēŅƒ Đ°ĐģĐŗĐžŅ€Đ¸Ņ‚ĐŧŅ‹ и вŅ‹Ņ‡Đ¸ŅĐģиŅ‚ĐĩĐģŅŒĐŊŅ‹Đĩ Đ´ĐžŅŅ‚иĐļĐĩĐŊиŅ, ĐģĐĩĐļĐ°Ņ‰Đ¸Đĩ в ĐžŅĐŊОвĐĩ ML, ŅĐŋĐžŅĐžĐąŅŅ‚вОваĐģи Ņ€Đ°ĐˇĐ˛Đ¸Ņ‚иŅŽ ИИ. ПоĐģĐĩСĐŊĐž ĐŋĐžĐŧĐŊиŅ‚ŅŒ, Ņ‡Ņ‚Đž, Ņ…ĐžŅ‚Ņ ŅŅ‚и ОйĐģĐ°ŅŅ‚и ĐēĐ°Đē ĐŊĐ°Ņ‡Đ°Đģи вŅ‹Đ´ĐĩĐģŅŅ‚ŅŒŅŅ в ĐžŅ‚Đ´ĐĩĐģŅŒĐŊŅ‹Đĩ в 1950-Ņ… ĐŗОдаŅ…, ваĐļĐŊŅ‹Đĩ [Đ°ĐģĐŗĐžŅ€Đ¸Ņ‚ĐŧиŅ‡ĐĩŅĐēиĐĩ, ŅŅ‚Đ°Ņ‚иŅŅ‚иŅ‡ĐĩŅĐēиĐĩ, ĐŧĐ°Ņ‚ĐĩĐŧĐ°Ņ‚иŅ‡ĐĩŅĐēиĐĩ, вŅ‹Ņ‡Đ¸ŅĐģиŅ‚ĐĩĐģŅŒĐŊŅ‹Đĩ и Ņ‚ĐĩŅ…ĐŊиŅ‡ĐĩŅĐēиĐĩ ĐžŅ‚ĐēŅ€Ņ‹Ņ‚иŅ](https://wikipedia.org/wiki/Timeline_of_machine_learning) ĐŋŅ€ĐĩĐ´ŅˆĐĩŅŅ‚вОваĐģи и ĐŋŅ€ĐžĐ¸ŅŅ…ОдиĐģи в ŅŅ‚Ņƒ ŅĐŋĐžŅ…Ņƒ. На ŅĐ°ĐŧĐžĐŧ Đ´ĐĩĐģĐĩ, ĐģŅŽĐ´Đ¸ Đ´ŅƒĐŧĐ°Đģи Ой ŅŅ‚иŅ… вОĐŋŅ€ĐžŅĐ°Ņ… в Ņ‚ĐĩŅ‡ĐĩĐŊиĐĩ [ŅĐžŅ‚ĐĩĐŊ ĐģĐĩŅ‚](https://ru.wikipedia.org/wiki/%D0%98%D1%81%D1%82%D0%BE%D1%80%D0%B8%D1%8F_%D0%B8%D1%81%D0%BA%D1%83%D1%81%D1%81%D1%82%D0%B2%D0%B5%D0%BD%D0%BD%D0%BE%D0%B3%D0%BE_%D0%B8%D0%BD%D1%82%D0%B5%D0%BB%D0%BB%D0%B5%D0%BA%D1%82%D0%B0): в ŅŅ‚ОК ŅŅ‚Đ°Ņ‚ŅŒĐĩ Ņ€Đ°ŅŅĐŧĐ°Ņ‚Ņ€Đ¸Đ˛Đ°ŅŽŅ‚ŅŅ иŅŅ‚ĐžŅ€Đ¸Ņ‡ĐĩŅĐēиĐĩ иĐŊŅ‚ĐĩĐģĐģĐĩĐēŅ‚ŅƒĐ°ĐģŅŒĐŊŅ‹Đĩ ĐžŅĐŊОвŅ‹ идĐĩи "ĐŧŅ‹ŅĐģŅŅ‰ĐĩĐš ĐŧĐ°ŅˆĐ¸ĐŊŅ‹". - ---- -## ЗаĐŧĐĩŅ‚ĐŊŅ‹Đĩ ĐžŅ‚ĐēŅ€Ņ‹Ņ‚иŅ - -- 1763, 1812 [ĐĸĐĩĐžŅ€ĐĩĐŧĐ° БайĐĩŅĐ°](https://ru.wikipedia.org/wiki/%D0%A2%D0%B5%D0%BE%D1%80%D0%B5%D0%BC%D0%B0_%D0%91%D0%B0%D0%B9%D0%B5%D1%81%D0%B0) и ĐĩĐĩ ĐŋŅ€ĐĩĐ´ŅˆĐĩŅŅ‚вĐĩĐŊĐŊиĐēи. Đ­Ņ‚Đ° Ņ‚ĐĩĐžŅ€ĐĩĐŧĐ° и ĐĩĐĩ ĐŋŅ€Đ¸ĐģĐžĐļĐĩĐŊиŅ ĐģĐĩĐļĐ°Ņ‚ в ĐžŅĐŊОвĐĩ вŅ‹Đ˛ĐžĐ´Đ°, ĐžĐŋиŅŅ‹Đ˛Đ°ŅŽŅ‰ĐĩĐŗĐž вĐĩŅ€ĐžŅŅ‚ĐŊĐžŅŅ‚ŅŒ ŅĐžĐąŅ‹Ņ‚иŅ, ĐŋŅ€ĐžĐ¸ŅŅ…ОдŅŅ‰ĐĩĐŗĐž ĐŊĐ° ĐžŅĐŊОвĐĩ ĐŋŅ€ĐĩдваŅ€Đ¸Ņ‚ĐĩĐģŅŒĐŊŅ‹Ņ… СĐŊĐ°ĐŊиК. -- 1805 [ĐĸĐĩĐžŅ€Đ¸Ņ ĐŊаиĐŧĐĩĐŊŅŒŅˆĐ¸Ņ… ĐēвадŅ€Đ°Ņ‚Ов](https://ru.wikipedia.org/wiki/%D0%9C%D0%B5%D1%82%D0%BE%D0%B4_%D0%BD%D0%B0%D0%B8%D0%BC%D0%B5%D0%BD%D1%8C%D1%88%D0%B8%D1%85_%D0%BA%D0%B2%D0%B0%D0%B4%D1%80%D0%B0%D1%82%D0%BE%D0%B2) Ņ„Ņ€Đ°ĐŊŅ†ŅƒĐˇŅĐēĐžĐŗĐž ĐŧĐ°Ņ‚ĐĩĐŧĐ°Ņ‚иĐēĐ° АдŅ€Đ¸ĐĩĐŊĐ°-МаŅ€Đ¸ ЛĐĩĐļĐ°ĐŊĐ´Ņ€Đ°. Đ­Ņ‚Đ° Ņ‚ĐĩĐžŅ€Đ¸Ņ, Đž ĐēĐžŅ‚ĐžŅ€ĐžĐš вŅ‹ ŅƒĐˇĐŊĐ°ĐĩŅ‚Đĩ в ĐŊĐ°ŅˆĐĩĐŧ ĐąĐģĐžĐēĐĩ Ņ€ĐĩĐŗŅ€ĐĩŅŅĐ¸Đ¸, ĐŋĐžĐŧĐžĐŗĐ°ĐĩŅ‚ в Đ°ĐŋĐŋŅ€ĐžĐēŅĐ¸ĐŧĐ°Ņ†Đ¸Đ¸ Đ´Đ°ĐŊĐŊŅ‹Ņ…. -- 1913 [ĐĻĐĩĐŋи МаŅ€ĐēОва](https://ru.wikipedia.org/wiki/%D0%A6%D0%B5%D0%BF%D1%8C_%D0%9C%D0%B0%D1%80%D0%BA%D0%BE%D0%B2%D0%B0), ĐŊаСваĐŊĐŊŅ‹Đš в Ņ‡ĐĩŅŅ‚ŅŒ Ņ€ŅƒŅŅĐēĐžĐŗĐž ĐŧĐ°Ņ‚ĐĩĐŧĐ°Ņ‚иĐēĐ° АĐŊĐ´Ņ€ĐĩŅ МаŅ€ĐēОва, иŅĐŋĐžĐģŅŒĐˇŅƒĐĩŅ‚ŅŅ Đ´ĐģŅ ĐžĐŋиŅĐ°ĐŊиŅ ĐŋĐžŅĐģĐĩдОваŅ‚ĐĩĐģŅŒĐŊĐžŅŅ‚и вОСĐŧĐžĐļĐŊŅ‹Ņ… ŅĐžĐąŅ‹Ņ‚иК ĐŊĐ° ĐžŅĐŊОвĐĩ ĐŋŅ€ĐĩĐ´Ņ‹Đ´ŅƒŅ‰ĐĩĐŗĐž ŅĐžŅŅ‚ĐžŅĐŊиŅ. -- 1957 [ПĐĩŅ€ŅĐĩĐŋŅ‚Ņ€ĐžĐŊ](https://ru.wikipedia.org/wiki/%D0%9F%D0%B5%D1%80%D1%86%D0%B5%D0%BF%D1%82%D1%80%D0%BE%D0%BD) - ŅŅ‚Đž Ņ‚иĐŋ ĐģиĐŊĐĩĐšĐŊĐžĐŗĐž ĐēĐģĐ°ŅŅĐ¸Ņ„иĐēĐ°Ņ‚ĐžŅ€Đ°, иСОйŅ€ĐĩŅ‚ĐĩĐŊĐŊŅ‹Đš Đ°ĐŧĐĩŅ€Đ¸ĐēĐ°ĐŊŅĐēиĐŧ ĐŋŅĐ¸Ņ…ĐžĐģĐžĐŗĐžĐŧ ФŅ€ŅĐŊĐēĐžĐŧ РОСĐĩĐŊĐąĐģĐ°Ņ‚Ņ‚ĐžĐŧ, ĐēĐžŅ‚ĐžŅ€Ņ‹Đš ĐģĐĩĐļиŅ‚ в ĐžŅĐŊОвĐĩ Đ´ĐžŅŅ‚иĐļĐĩĐŊиК в ОйĐģĐ°ŅŅ‚и ĐŗĐģŅƒĐąĐžĐēĐžĐŗĐž ОйŅƒŅ‡ĐĩĐŊиŅ. - ---- - -- 1967 [МĐĩŅ‚Од ĐąĐģиĐļĐ°ĐšŅˆĐĩĐŗĐž ŅĐžŅĐĩĐ´Đ°](https://ru.wikipedia.org/wiki/%D0%91%D0%BB%D0%B8%D0%B6%D0%B0%D0%B9%D1%88%D0%B8%D0%B9_%D1%81%D0%BE%D1%81%D0%B5%D0%B4) - ŅŅ‚Đž Đ°ĐģĐŗĐžŅ€Đ¸Ņ‚Đŧ, иСĐŊĐ°Ņ‡Đ°ĐģŅŒĐŊĐž Ņ€Đ°ĐˇŅ€Đ°ĐąĐžŅ‚Đ°ĐŊĐŊŅ‹Đš Đ´ĐģŅ ĐžŅ‚ОйŅ€Đ°ĐļĐĩĐŊиŅ ĐŧĐ°Ņ€ŅˆŅ€ŅƒŅ‚Ов. В ĐēĐžĐŊŅ‚ĐĩĐēŅŅ‚Đĩ ML ĐžĐŊ иŅĐŋĐžĐģŅŒĐˇŅƒĐĩŅ‚ŅŅ Đ´ĐģŅ ОйĐŊĐ°Ņ€ŅƒĐļĐĩĐŊиŅ СаĐēĐžĐŊĐžĐŧĐĩŅ€ĐŊĐžŅŅ‚ĐĩĐš. -- 1970 [ОбŅ€Đ°Ņ‚ĐŊĐžĐĩ Ņ€Đ°ŅĐŋŅ€ĐžŅŅ‚Ņ€Đ°ĐŊĐĩĐŊиĐĩ ĐžŅˆĐ¸ĐąĐēи](https://ru.wikipedia.org/wiki/%D0%9C%D0%B5%D1%82%D0%BE%D0%B4_%D0%BE%D0%B1%D1%80%D0%B0%D1%82%D0%BD%D0%BE%D0%B3%D0%BE_%D1%80%D0%B0%D1%81%D0%BF%D1%80%D0%BE%D1%81%D1%82%D1%80%D0%B0%D0%BD%D0%B5%D0%BD%D0%B8%D1%8F_%D0%BE%D1%88%D0%B8%D0%B1%D0%BA%D0%B8) иŅĐŋĐžĐģŅŒĐˇŅƒĐĩŅ‚ŅŅ Đ´ĐģŅ ОйŅƒŅ‡ĐĩĐŊиŅ [ĐŊĐĩĐšŅ€ĐžĐŊĐŊŅ‹Ņ… ŅĐĩŅ‚ĐĩĐš Ņ ĐŋŅ€ŅĐŧОК ŅĐ˛ŅĐˇŅŒŅŽ](https://ru.wikipedia.org/wiki/%D0%9D%D0%B5%D0%B9%D1%80%D0%BE%D0%BD%D0%BD%D0%B0%D1%8F_%D1%81%D0%B5%D1%82%D1%8C_%D1%81_%D0%BF%D1%80%D1%8F%D0%BC%D0%BE%D0%B9_%D1%81%D0%B2%D1%8F%D0%B7%D1%8C%D1%8E). -- 1982 [Đ ĐĩĐēŅƒŅ€Ņ€ĐĩĐŊŅ‚ĐŊŅ‹Đĩ ĐŊĐĩĐšŅ€ĐžĐŊĐŊŅ‹Đĩ ŅĐĩŅ‚и](https://ru.wikipedia.org/wiki/%D0%A0%D0%B5%D0%BA%D1%83%D1%80%D1%80%D0%B5%D0%BD%D1%82%D0%BD%D0%B0%D1%8F_%D0%BD%D0%B5%D0%B9%D1%80%D0%BE%D0%BD%D0%BD%D0%B0%D1%8F_%D1%81%D0%B5%D1%82%D1%8C) ŅĐ˛ĐģŅŅŽŅ‚ŅŅ иŅĐēŅƒŅŅŅ‚вĐĩĐŊĐŊŅ‹Đŧи ĐŊĐĩĐšŅ€ĐžĐŊĐŊŅ‹Đŧи ŅĐĩŅ‚ŅĐŧи, ĐŋĐžĐģŅƒŅ‡ĐĩĐŊĐŊŅ‹Đŧи иС ĐŊĐĩĐšŅ€ĐžĐŊĐŊŅ‹Ņ… ŅĐĩŅ‚ĐĩĐš ĐŋŅ€ŅĐŧОК ŅĐ˛ŅĐˇĐ¸, ĐēĐžŅ‚ĐžŅ€Ņ‹Đĩ ŅĐžĐˇĐ´Đ°ŅŽŅ‚ вŅ€ĐĩĐŧĐĩĐŊĐŊŅ‹Đĩ ĐŗŅ€Đ°Ņ„иĐēи. - -✅ ПŅ€ĐžĐ˛ĐĩдиŅ‚Đĩ ĐŊĐĩйОĐģŅŒŅˆĐžĐĩ иŅŅĐģĐĩдОваĐŊиĐĩ. КаĐēиĐĩ ĐĩŅ‰Đĩ Đ´Đ°Ņ‚Ņ‹ ŅĐ˛ĐģŅŅŽŅ‚ŅŅ ĐēĐģŅŽŅ‡ĐĩвŅ‹Đŧи в иŅŅ‚ĐžŅ€Đ¸Đ¸ ML и ИИ? - ---- -## 1950: МаŅˆĐ¸ĐŊŅ‹, ĐēĐžŅ‚ĐžŅ€Ņ‹Đĩ Đ´ŅƒĐŧĐ°ŅŽŅ‚ - -АĐģĐ°ĐŊ ĐĸŅŒŅŽŅ€Đ¸ĐŊĐŗ, ĐŋОиŅŅ‚иĐŊĐĩ вĐĩĐģиĐēиК Ņ‡ĐĩĐģОвĐĩĐē, ĐēĐžŅ‚ĐžŅ€Ņ‹Đš ĐąŅ‹Đģ вŅ‹ĐąŅ€Đ°ĐŊ [ОйŅ‰ĐĩŅŅ‚вĐĩĐŊĐŊĐžŅŅ‚ŅŒŅŽ в 2019 ĐŗОдŅƒ](https://wikipedia.org/wiki/Icons:_The_Greatest_Person_of_the_20th_Century) вĐĩĐģиŅ‡Đ°ĐšŅˆĐ¸Đŧ ŅƒŅ‡ĐĩĐŊŅ‹Đŧ 20-ĐŗĐž вĐĩĐēĐ°. ĐĄŅ‡Đ¸Ņ‚Đ°ĐĩŅ‚ŅŅ, Ņ‡Ņ‚Đž ĐžĐŊ ĐŋĐžĐŧĐžĐŗ СаĐģĐžĐļиŅ‚ŅŒ ĐžŅĐŊОвŅƒ ĐēĐžĐŊŅ†ĐĩĐŋŅ†Đ¸Đ¸ "ĐŧĐ°ŅˆĐ¸ĐŊŅ‹, ĐēĐžŅ‚ĐžŅ€Đ°Ņ ĐŧĐžĐļĐĩŅ‚ ĐŧŅ‹ŅĐģиŅ‚ŅŒ". ОĐŊ йОŅ€ĐžĐģŅŅ ŅĐž ŅĐēĐĩĐŋŅ‚иĐēĐ°Đŧи и ŅĐ˛ĐžĐĩĐš ŅĐžĐąŅŅ‚вĐĩĐŊĐŊОК ĐŋĐžŅ‚Ņ€ĐĩĐąĐŊĐžŅŅ‚ŅŒŅŽ в ŅĐŧĐŋиŅ€Đ¸Ņ‡ĐĩŅĐēиŅ… Đ´ĐžĐēаСаŅ‚ĐĩĐģŅŒŅŅ‚ваŅ… ŅŅ‚ОК ĐēĐžĐŊŅ†ĐĩĐŋŅ†Đ¸Đ¸, Ņ‡Đ°ŅŅ‚иŅ‡ĐŊĐž ŅĐžĐˇĐ´Đ°Đ˛ [ĐĸĐĩŅŅ‚ ĐĸŅŒŅŽŅ€Đ¸ĐŊĐŗĐ°](https://www.bbc.com/news/technology-18475646), ĐēĐžŅ‚ĐžŅ€Ņ‹Đĩ вŅ‹ иСŅƒŅ‡Đ¸Ņ‚Đĩ ĐŊĐ° ĐŊĐ°ŅˆĐ¸Ņ… ŅƒŅ€ĐžĐēĐ°Ņ… NLP. - ---- -## 1956: ЛĐĩŅ‚ĐŊиК иŅŅĐģĐĩдОваŅ‚ĐĩĐģŅŒŅĐēиК ĐŋŅ€ĐžĐĩĐēŅ‚ в ДаŅ€Ņ‚ĐŧŅƒŅ‚Đĩ - -"ЛĐĩŅ‚ĐŊиК иŅŅĐģĐĩдОваŅ‚ĐĩĐģŅŒŅĐēиК ĐŋŅ€ĐžĐĩĐēŅ‚ ДаŅ€Ņ‚ĐŧŅƒŅ‚Đ° ĐŋĐž иŅĐēŅƒŅŅŅ‚вĐĩĐŊĐŊĐžĐŧŅƒ иĐŊŅ‚ĐĩĐģĐģĐĩĐēŅ‚Ņƒ ĐąŅ‹Đģ ĐžŅĐŊОвОĐŋĐžĐģĐ°ĐŗĐ°ŅŽŅ‰Đ¸Đŧ ŅĐžĐąŅ‹Ņ‚иĐĩĐŧ Đ´ĐģŅ иŅĐēŅƒŅŅŅ‚вĐĩĐŊĐŊĐžĐŗĐž иĐŊŅ‚ĐĩĐģĐģĐĩĐēŅ‚Đ° ĐēĐ°Đē ОйĐģĐ°ŅŅ‚и", и иĐŧĐĩĐŊĐŊĐž СдĐĩŅŅŒ ĐąŅ‹Đģ ĐŋŅ€Đ¸Đ´ŅƒĐŧĐ°ĐŊ Ņ‚ĐĩŅ€ĐŧиĐŊ "иŅĐēŅƒŅŅŅ‚вĐĩĐŊĐŊŅ‹Đš иĐŊŅ‚ĐĩĐģĐģĐĩĐēŅ‚" ([иŅŅ‚ĐžŅ‡ĐŊиĐē](https://250.dartmouth.edu/highlights/artificial-intelligence-ai-coined-dartmouth)). - -> ВŅŅĐēиК Đ°ŅĐŋĐĩĐēŅ‚ ОйŅƒŅ‡ĐĩĐŊиŅ иĐģи ĐģŅŽĐąĐžĐĩ Đ´Ņ€ŅƒĐŗĐžĐĩ ŅĐ˛ĐžĐšŅŅ‚вО иĐŊŅ‚ĐĩĐģĐģĐĩĐēŅ‚Đ° ĐŧĐžĐļĐĩŅ‚ в ĐŋŅ€Đ¸ĐŊŅ†Đ¸ĐŋĐĩ ĐąŅ‹Ņ‚ŅŒ ŅŅ‚ĐžĐģŅŒ Ņ‚ĐžŅ‡ĐŊĐž ĐžĐŋиŅĐ°ĐŊĐž, Ņ‡Ņ‚Đž ĐŧĐ°ŅˆĐ¸ĐŊĐ° ŅĐŧĐžĐļĐĩŅ‚ ĐĩĐŗĐž ŅĐ¸ĐŧŅƒĐģиŅ€ĐžĐ˛Đ°Ņ‚ŅŒ. - ---- - -ВĐĩĐ´ŅƒŅ‰Đ¸Đš иŅŅĐģĐĩдОваŅ‚ĐĩĐģŅŒ, ĐŋŅ€ĐžŅ„ĐĩŅŅĐžŅ€ ĐŧĐ°Ņ‚ĐĩĐŧĐ°Ņ‚иĐēи ДĐļĐžĐŊ МаĐēĐēĐ°Ņ€Ņ‚и, ĐŊĐ°Đ´ĐĩŅĐģŅŅ "Đ´ĐĩĐšŅŅ‚вОваŅ‚ŅŒ, ĐžŅĐŊОвŅ‹Đ˛Đ°ŅŅŅŒ ĐŊĐ° ĐŋŅ€ĐĩĐ´ĐŋĐžĐģĐžĐļĐĩĐŊии, Ņ‡Ņ‚Đž вŅŅĐēиК Đ°ŅĐŋĐĩĐēŅ‚ ОйŅƒŅ‡ĐĩĐŊиŅ иĐģи ĐģŅŽĐąĐžĐĩ Đ´Ņ€ŅƒĐŗĐžĐĩ ŅĐ˛ĐžĐšŅŅ‚вО иĐŊŅ‚ĐĩĐģĐģĐĩĐēŅ‚Đ° ĐŧĐžĐļĐĩŅ‚ в ĐŋŅ€Đ¸ĐŊŅ†Đ¸ĐŋĐĩ ĐąŅ‹Ņ‚ŅŒ ŅŅ‚ĐžĐģŅŒ Ņ‚ĐžŅ‡ĐŊĐž ĐžĐŋиŅĐ°ĐŊĐž, Ņ‡Ņ‚Đž ĐŧĐ°ŅˆĐ¸ĐŊĐ° ŅĐŧĐžĐļĐĩŅ‚ ĐĩĐŗĐž ŅĐ¸ĐŧŅƒĐģиŅ€ĐžĐ˛Đ°Ņ‚ŅŒ". ĐĄŅ€Đĩди ŅƒŅ‡Đ°ŅŅ‚ĐŊиĐēОв ĐąŅ‹Đģ ĐĩŅ‰Đĩ ОдиĐŊ вŅ‹Đ´Đ°ŅŽŅ‰Đ¸ĐšŅŅ ŅƒŅ‡ĐĩĐŊŅ‹Đš в ŅŅ‚ОК ОйĐģĐ°ŅŅ‚и - МаŅ€Đ˛Đ¸ĐŊ МиĐŊŅĐēи. - -ĐĄĐĩĐŧиĐŊĐ°Ņ€Ņƒ ĐŋŅ€Đ¸ĐŋиŅŅ‹Đ˛Đ°ŅŽŅ‚ иĐŊиŅ†Đ¸Đ¸Ņ€ĐžĐ˛Đ°ĐŊиĐĩ и ĐŋООŅ‰Ņ€ĐĩĐŊиĐĩ ĐŊĐĩŅĐēĐžĐģŅŒĐēиŅ… диŅĐēŅƒŅŅĐ¸Đš, в Ņ‚ĐžĐŧ Ņ‡Đ¸ŅĐģĐĩ "Ņ€Đ°ĐˇĐ˛Đ¸Ņ‚иĐĩ ŅĐ¸ĐŧвОĐģиŅ‡ĐĩŅĐēиŅ… ĐŧĐĩŅ‚ОдОв, ŅĐ¸ŅŅ‚ĐĩĐŧ, ĐžŅ€Đ¸ĐĩĐŊŅ‚иŅ€ĐžĐ˛Đ°ĐŊĐŊŅ‹Ņ… ĐŊĐ° ĐžĐŗŅ€Đ°ĐŊиŅ‡ĐĩĐŊĐŊŅ‹Đĩ ОйĐģĐ°ŅŅ‚и (Ņ€Đ°ĐŊĐŊиĐĩ ŅĐēŅĐŋĐĩŅ€Ņ‚ĐŊŅ‹Đĩ ŅĐ¸ŅŅ‚ĐĩĐŧŅ‹), и Đ´ĐĩĐ´ŅƒĐēŅ‚ивĐŊŅ‹Ņ… ŅĐ¸ŅŅ‚ĐĩĐŧ ĐŋĐž ŅŅ€Đ°Đ˛ĐŊĐĩĐŊиŅŽ Ņ иĐŊĐ´ŅƒĐēŅ‚ивĐŊŅ‹Đŧи ŅĐ¸ŅŅ‚ĐĩĐŧĐ°Đŧи". ([иŅŅ‚ĐžŅ‡ĐŊиĐē](https://ru.wikipedia.org/wiki/%D0%94%D0%B0%D1%80%D1%82%D0%BC%D1%83%D1%82%D1%81%D0%BA%D0%B8%D0%B9_%D1%81%D0%B5%D0%BC%D0%B8%D0%BD%D0%B0%D1%80)). - ---- -## 1956 - 1974: "ЗоĐģĐžŅ‚Ņ‹Đĩ ĐŗОдŅ‹" - -ĐĄ 1950-Ņ… Đ´Đž ŅĐĩŅ€ĐĩдиĐŊŅ‹ 70-Ņ… ĐŗОдОв ĐžĐŋŅ‚иĐŧиСĐŧ Ņ€ĐžŅ в ĐŊĐ°Đ´ĐĩĐļĐ´Đĩ, Ņ‡Ņ‚Đž ИИ ŅĐŧĐžĐļĐĩŅ‚ Ņ€ĐĩŅˆĐ¸Ņ‚ŅŒ ĐŧĐŊĐžĐŗиĐĩ ĐŋŅ€ĐžĐąĐģĐĩĐŧŅ‹. В 1967 ĐŗОдŅƒ МаŅ€Đ˛Đ¸ĐŊ МиĐŊŅĐēи ŅƒĐ˛ĐĩŅ€ĐĩĐŊĐŊĐž СаŅĐ˛Đ¸Đģ, Ņ‡Ņ‚Đž "В Ņ‚ĐĩŅ‡ĐĩĐŊиĐĩ ОдĐŊĐžĐŗĐž ĐŋĐžĐēĐžĐģĐĩĐŊиŅ... ĐŋŅ€ĐžĐąĐģĐĩĐŧĐ° ŅĐžĐˇĐ´Đ°ĐŊиŅ "иŅĐēŅƒŅŅŅ‚вĐĩĐŊĐŊĐžĐŗĐž иĐŊŅ‚ĐĩĐģĐģĐĩĐēŅ‚Đ°" ĐąŅƒĐ´ĐĩŅ‚ в СĐŊĐ°Ņ‡Đ¸Ņ‚ĐĩĐģŅŒĐŊОК ŅŅ‚ĐĩĐŋĐĩĐŊи Ņ€ĐĩŅˆĐĩĐŊĐ°". (МиĐŊŅĐēи, МаŅ€Đ˛Đ¸ĐŊ (1967), ВŅ‹Ņ‡Đ¸ŅĐģĐĩĐŊиŅ: КоĐŊĐĩŅ‡ĐŊŅ‹Đĩ и ĐąĐĩŅĐēĐžĐŊĐĩŅ‡ĐŊŅ‹Đĩ ĐŧĐ°ŅˆĐ¸ĐŊŅ‹, Đ­ĐŊĐŗĐģвŅƒĐ´-КĐģиŅ„Ņ„Ņ, НŅŒŅŽ-ДĐļĐĩŅ€ŅĐ¸: ПŅ€ĐĩĐŊŅ‚иŅ-ĐĨĐžĐģĐģ) - -ИŅŅĐģĐĩдОваĐŊиŅ в ОйĐģĐ°ŅŅ‚и ОйŅ€Đ°ĐąĐžŅ‚Đēи ĐĩŅŅ‚ĐĩŅŅ‚вĐĩĐŊĐŊĐžĐŗĐž ŅĐˇŅ‹ĐēĐ° ĐŋŅ€ĐžŅ†Đ˛ĐĩŅ‚Đ°Đģи, ĐŋОиŅĐē ĐąŅ‹Đģ ŅƒŅĐžĐ˛ĐĩŅ€ŅˆĐĩĐŊŅŅ‚вОваĐŊ и ŅŅ‚Đ°Đģ йОĐģĐĩĐĩ ĐŧĐžŅ‰ĐŊŅ‹Đŧ, и ĐąŅ‹ĐģĐ° ŅĐžĐˇĐ´Đ°ĐŊĐ° ĐēĐžĐŊŅ†ĐĩĐŋŅ†Đ¸Ņ "ĐŧиĐēŅ€ĐžĐŧиŅ€ĐžĐ˛", ĐŗĐ´Đĩ ĐŋŅ€ĐžŅŅ‚Ņ‹Đĩ СадаŅ‡Đ¸ вŅ‹ĐŋĐžĐģĐŊŅĐģиŅŅŒ Ņ иŅĐŋĐžĐģŅŒĐˇĐžĐ˛Đ°ĐŊиĐĩĐŧ ĐŋŅ€ĐžŅŅ‚Ņ‹Ņ… ŅĐˇŅ‹ĐēОвŅ‹Ņ… иĐŊŅŅ‚Ņ€ŅƒĐēŅ†Đ¸Đš. - ---- - -ИŅŅĐģĐĩдОваĐŊиŅ Ņ…ĐžŅ€ĐžŅˆĐž Ņ„иĐŊĐ°ĐŊŅĐ¸Ņ€ĐžĐ˛Đ°ĐģиŅŅŒ ĐŋŅ€Đ°Đ˛Đ¸Ņ‚ĐĩĐģŅŒŅŅ‚вĐĩĐŊĐŊŅ‹Đŧи ŅƒŅ‡Ņ€ĐĩĐļĐ´ĐĩĐŊиŅĐŧи, ĐąŅ‹Đģи Đ´ĐžŅŅ‚иĐŗĐŊŅƒŅ‚Ņ‹ ŅƒŅĐŋĐĩŅ…и в вŅ‹Ņ‡Đ¸ŅĐģĐĩĐŊиŅŅ… и Đ°ĐģĐŗĐžŅ€Đ¸Ņ‚ĐŧĐ°Ņ…, ĐąŅ‹Đģи ŅĐžĐˇĐ´Đ°ĐŊŅ‹ ĐŋŅ€ĐžŅ‚ĐžŅ‚иĐŋŅ‹ иĐŊŅ‚ĐĩĐģĐģĐĩĐēŅ‚ŅƒĐ°ĐģŅŒĐŊŅ‹Ņ… ĐŧĐ°ŅˆĐ¸ĐŊ. НĐĩĐēĐžŅ‚ĐžŅ€Ņ‹Đĩ иС ŅŅ‚иŅ… ĐŧĐ°ŅˆĐ¸ĐŊ вĐēĐģŅŽŅ‡Đ°ŅŽŅ‚: - -* [РОйОŅ‚ Shakey](https://ru.wikipedia.org/wiki/Shakey), ĐēĐžŅ‚ĐžŅ€Ņ‹Đš ĐŧĐžĐŗ ĐŧĐ°ĐŊĐĩвŅ€Đ¸Ņ€ĐžĐ˛Đ°Ņ‚ŅŒ и Ņ€ĐĩŅˆĐ°Ņ‚ŅŒ, ĐēĐ°Đē "Ņ€Đ°ĐˇŅƒĐŧĐŊĐž" вŅ‹ĐŋĐžĐģĐŊŅŅ‚ŅŒ СадаŅ‡Đ¸. - - ![Shakey, ŅƒĐŧĐŊŅ‹Đš Ņ€ĐžĐąĐžŅ‚](../images/shakey.jpg) - > Shakey в 1972 ĐŗОдŅƒ - ---- - -* Đ­ĐģиСа, Ņ€Đ°ĐŊĐŊиК "Ņ‡Đ°Ņ‚-йОŅ‚", ĐŧĐžĐŗĐģĐ° ОйŅ‰Đ°Ņ‚ŅŒŅŅ Ņ ĐģŅŽĐ´ŅŒĐŧи и Đ´ĐĩĐšŅŅ‚вОваŅ‚ŅŒ ĐēĐ°Đē ĐŋŅ€Đ¸ĐŧиŅ‚ивĐŊŅ‹Đš "Ņ‚ĐĩŅ€Đ°ĐŋĐĩвŅ‚". ВŅ‹ ŅƒĐˇĐŊĐ°ĐĩŅ‚Đĩ йОĐģŅŒŅˆĐĩ Ой Đ­ĐģиСĐĩ ĐŊĐ° ŅƒŅ€ĐžĐēĐ°Ņ… NLP. - - ![Đ­ĐģиСа, йОŅ‚](../images/eliza.png) - > ВĐĩŅ€ŅĐ¸Ņ Đ­ĐģиСŅ‹, Ņ‡Đ°Ņ‚-йОŅ‚Đ° - ---- - -* "МиŅ€ ĐąĐģĐžĐēОв" ĐąŅ‹Đģ ĐŋŅ€Đ¸ĐŧĐĩŅ€ĐžĐŧ ĐŧиĐēŅ€ĐžĐŧиŅ€Đ°, в ĐēĐžŅ‚ĐžŅ€ĐžĐŧ ĐąĐģĐžĐēи ĐŧĐžĐļĐŊĐž ĐąŅ‹ĐģĐž ŅĐēĐģĐ°Đ´Ņ‹Đ˛Đ°Ņ‚ŅŒ и ŅĐžŅ€Ņ‚иŅ€ĐžĐ˛Đ°Ņ‚ŅŒ, Đ° Ņ‚Đ°ĐēĐļĐĩ ĐŋŅ€ĐžĐ˛ĐžĐ´Đ¸Ņ‚ŅŒ ŅĐēŅĐŋĐĩŅ€Đ¸ĐŧĐĩĐŊŅ‚Ņ‹ ĐŋĐž ОйŅƒŅ‡ĐĩĐŊиŅŽ ĐŧĐ°ŅˆĐ¸ĐŊ ĐŋŅ€Đ¸ĐŊŅŅ‚иŅŽ Ņ€ĐĩŅˆĐĩĐŊиК. ДоŅŅ‚иĐļĐĩĐŊиŅ, ŅĐžĐˇĐ´Đ°ĐŊĐŊŅ‹Đĩ Ņ ĐŋĐžĐŧĐžŅ‰ŅŒŅŽ йийĐģиОŅ‚ĐĩĐē, Ņ‚Đ°ĐēиŅ… ĐēĐ°Đē [SHRDLU](https://ru.wikipedia.org/wiki/SHRDLU) ĐŋĐžĐŧĐžĐŗĐģĐž ĐŋŅ€ĐžĐ´Đ˛Đ¸ĐŊŅƒŅ‚ŅŒ ОйŅ€Đ°ĐąĐžŅ‚ĐēŅƒ ŅĐˇŅ‹ĐēĐ° вĐŋĐĩŅ€ĐĩĐ´. - - [![ĐŧиŅ€ ĐąĐģĐžĐēОв SHRDLU](https://img.youtube.com/vi/QAJz4YKUwqw/0.jpg)](https://www.youtube.com/watch?v=QAJz4YKUwqw "ĐŧиŅ€ ĐąĐģĐžĐēОв SHRDLU") - - > đŸŽĨ НаĐļĐŧиŅ‚Đĩ ĐŊĐ° иСОйŅ€Đ°ĐļĐĩĐŊиĐĩ вŅ‹ŅˆĐĩ Đ´ĐģŅ ĐŋŅ€ĐžŅĐŧĐžŅ‚Ņ€Đ° видĐĩĐž: МиŅ€ ĐąĐģĐžĐēОв SHRDLU - ---- -## 1974-1980: "ЗиĐŧĐ° иŅĐēŅƒŅŅŅ‚вĐĩĐŊĐŊĐžĐŗĐž иĐŊŅ‚ĐĩĐģĐģĐĩĐēŅ‚Đ°" - -К ŅĐĩŅ€ĐĩдиĐŊĐĩ 1970-Ņ… ĐŗОдОв ŅŅ‚Đ°ĐģĐž ĐžŅ‡ĐĩвидĐŊĐž, Ņ‡Ņ‚Đž ŅĐģĐžĐļĐŊĐžŅŅ‚ŅŒ ŅĐžĐˇĐ´Đ°ĐŊиŅ "иĐŊŅ‚ĐĩĐģĐģĐĩĐēŅ‚ŅƒĐ°ĐģŅŒĐŊŅ‹Ņ… ĐŧĐ°ŅˆĐ¸ĐŊ" ĐąŅ‹ĐģĐ° СаĐŊиĐļĐĩĐŊĐ° и Ņ‡Ņ‚Đž ĐĩĐĩ ĐŋĐĩŅ€ŅĐŋĐĩĐēŅ‚ивŅ‹, ŅƒŅ‡Đ¸Ņ‚Ņ‹Đ˛Đ°Ņ Đ´ĐžŅŅ‚ŅƒĐŋĐŊŅ‹Đĩ вŅ‹Ņ‡Đ¸ŅĐģиŅ‚ĐĩĐģŅŒĐŊŅ‹Đĩ ĐŧĐžŅ‰ĐŊĐžŅŅ‚и, ĐąŅ‹Đģи ĐŋŅ€ĐĩŅƒĐ˛ĐĩĐģиŅ‡ĐĩĐŊŅ‹. ФиĐŊĐ°ĐŊŅĐ¸Ņ€ĐžĐ˛Đ°ĐŊиĐĩ иŅŅŅĐēĐģĐž, и дОвĐĩŅ€Đ¸Đĩ Đē ŅŅ‚ОК ОйĐģĐ°ŅŅ‚и ŅĐŊиСиĐģĐžŅŅŒ. НĐĩĐēĐžŅ‚ĐžŅ€Ņ‹Đĩ ĐŋŅ€ĐžĐąĐģĐĩĐŧŅ‹, ĐŋОвĐģиŅĐ˛ŅˆĐ¸Đĩ ĐŊĐ° дОвĐĩŅ€Đ¸Đĩ, вĐēĐģŅŽŅ‡Đ°Đģи: ---- -- **ОĐŗŅ€Đ°ĐŊиŅ‡ĐĩĐŊиŅ**. ВŅ‹Ņ‡Đ¸ŅĐģиŅ‚ĐĩĐģŅŒĐŊĐ°Ņ ĐŧĐžŅ‰ĐŊĐžŅŅ‚ŅŒ ĐąŅ‹ĐģĐ° ŅĐģиŅˆĐēĐžĐŧ ĐžĐŗŅ€Đ°ĐŊиŅ‡ĐĩĐŊĐ°. -- **КоĐŧйиĐŊĐ°Ņ‚ĐžŅ€ĐŊŅ‹Đš вСŅ€Ņ‹Đ˛**. КоĐģиŅ‡ĐĩŅŅ‚вО ĐŋĐ°Ņ€Đ°ĐŧĐĩŅ‚Ņ€ĐžĐ˛, ĐŊĐĩОйŅ…ОдиĐŧŅ‹Ņ… Đ´ĐģŅ ОйŅƒŅ‡ĐĩĐŊиŅ, Ņ€ĐžŅĐģĐž ŅĐēŅĐŋĐžĐŊĐĩĐŊŅ†Đ¸Đ°ĐģŅŒĐŊĐž ĐŋĐž ĐŧĐĩŅ€Đĩ Ņ‚ĐžĐŗĐž, ĐēĐ°Đē ŅƒŅĐģĐžĐļĐŊŅĐģиŅŅŒ СадаŅ‡Đ¸ Đ´ĐģŅ ĐēĐžĐŧĐŋŅŒŅŽŅ‚ĐĩŅ€ĐžĐ˛, ĐąĐĩС ĐŋĐ°Ņ€Đ°ĐģĐģĐĩĐģŅŒĐŊОК ŅĐ˛ĐžĐģŅŽŅ†Đ¸Đ¸ вŅ‹Ņ‡Đ¸ŅĐģиŅ‚ĐĩĐģŅŒĐŊОК ĐŧĐžŅ‰ĐŊĐžŅŅ‚и и вОСĐŧĐžĐļĐŊĐžŅŅ‚ĐĩĐš. -- **НĐĩŅ…ваŅ‚ĐēĐ° Đ´Đ°ĐŊĐŊŅ‹Ņ…**. НĐĩŅ…ваŅ‚ĐēĐ° Đ´Đ°ĐŊĐŊŅ‹Ņ… СаŅ‚Ņ€ŅƒĐ´ĐŊŅĐģĐ° ĐŋŅ€ĐžŅ†ĐĩŅŅ Ņ‚ĐĩŅŅ‚иŅ€ĐžĐ˛Đ°ĐŊиŅ, Ņ€Đ°ĐˇŅ€Đ°ĐąĐžŅ‚Đēи и ŅĐžĐ˛ĐĩŅ€ŅˆĐĩĐŊŅŅ‚вОваĐŊиŅ Đ°ĐģĐŗĐžŅ€Đ¸Ņ‚ĐŧОв. -- **ЗадаĐĩĐŧ Đģи ĐŧŅ‹ ĐŋŅ€Đ°Đ˛Đ¸ĐģŅŒĐŊŅ‹Đĩ вОĐŋŅ€ĐžŅŅ‹?**. ĐĄĐ°Đŧи вОĐŋŅ€ĐžŅŅ‹, ĐēĐžŅ‚ĐžŅ€Ņ‹Đĩ СадаваĐģиŅŅŒ, ĐŊĐ°Ņ‡Đ°Đģи ĐŋОдвĐĩŅ€ĐŗĐ°Ņ‚ŅŒŅŅ ŅĐžĐŧĐŊĐĩĐŊиŅŽ. ИŅŅĐģĐĩдОваŅ‚ĐĩĐģи ĐŊĐ°Ņ‡Đ°Đģи ĐŋОдвĐĩŅ€ĐŗĐ°Ņ‚ŅŒ ĐēŅ€Đ¸Ņ‚иĐēĐĩ ŅĐ˛ĐžĐ¸ ĐŋОдŅ…ОдŅ‹: - - ĐĸĐĩŅŅ‚Ņ‹ ĐĸŅŒŅŽŅ€Đ¸ĐŊĐŗĐ° ĐąŅ‹Đģи ĐŋĐžŅŅ‚авĐģĐĩĐŊŅ‹ ĐŋОд ŅĐžĐŧĐŊĐĩĐŊиĐĩ, ŅŅ€Đĩди ĐŋŅ€ĐžŅ‡ĐĩĐŗĐž, Ņ ĐŋĐžĐŧĐžŅ‰ŅŒŅŽ "Ņ‚ĐĩĐžŅ€Đ¸Đ¸ ĐēиŅ‚Đ°ĐšŅĐēОК ĐēĐžĐŧĐŊĐ°Ņ‚Ņ‹", ĐēĐžŅ‚ĐžŅ€Đ°Ņ ŅƒŅ‚вĐĩŅ€ĐļĐ´Đ°ĐģĐ°, Ņ‡Ņ‚Đž "ĐŋŅ€ĐžĐŗŅ€Đ°ĐŧĐŧиŅ€ĐžĐ˛Đ°ĐŊиĐĩ Ņ†Đ¸Ņ„Ņ€ĐžĐ˛ĐžĐŗĐž ĐēĐžĐŧĐŋŅŒŅŽŅ‚ĐĩŅ€Đ° ĐŧĐžĐļĐĩŅ‚ ŅĐžĐˇĐ´Đ°Ņ‚ŅŒ вĐŋĐĩŅ‡Đ°Ņ‚ĐģĐĩĐŊиĐĩ, Ņ‡Ņ‚Đž ĐžĐŊ ĐŋĐžĐŊиĐŧĐ°ĐĩŅ‚ ŅĐˇŅ‹Đē, ĐŊĐž ĐŊĐĩ ĐŧĐžĐļĐĩŅ‚ ОйĐĩŅĐŋĐĩŅ‡Đ¸Ņ‚ŅŒ Ņ€ĐĩĐ°ĐģŅŒĐŊĐžĐĩ ĐŋĐžĐŊиĐŧĐ°ĐŊиĐĩ". ([иŅŅ‚ĐžŅ‡ĐŊиĐē](https://plato.stanford.edu/entries/chinese-room/)) - - Đ­Ņ‚иĐēĐ° вĐŊĐĩĐ´Ņ€ĐĩĐŊиŅ в ОйŅ‰ĐĩŅŅ‚вО иŅĐēŅƒŅŅŅ‚вĐĩĐŊĐŊĐžĐŗĐž иĐŊŅ‚ĐĩĐģĐģĐĩĐēŅ‚Đ°, Ņ‚Đ°ĐēĐžĐŗĐž ĐēĐ°Đē "Ņ‚ĐĩŅ€Đ°ĐŋĐĩвŅ‚" ЭЛИЗА, ĐąŅ‹ĐģĐ° ĐŋĐžŅŅ‚авĐģĐĩĐŊĐ° ĐŋОд ŅĐžĐŧĐŊĐĩĐŊиĐĩ. - ---- - -В Ņ‚Đž ĐļĐĩ вŅ€ĐĩĐŧŅ ĐŊĐ°Ņ‡Đ°Đģи Ņ„ĐžŅ€ĐŧиŅ€ĐžĐ˛Đ°Ņ‚ŅŒŅŅ Ņ€Đ°ĐˇĐģиŅ‡ĐŊŅ‹Đĩ ŅˆĐēĐžĐģŅ‹ ИИ. ПŅ€ĐžĐ¸ĐˇĐžŅˆĐģĐž Ņ€Đ°ĐˇĐ´ĐĩĐģĐĩĐŊиĐĩ ĐŊĐ° ĐŋОдŅ…ОдŅ‹ ["ĐŊĐĩŅ€ŅŅˆĐģивОĐŗĐž" и "Ņ‡Đ¸ŅŅ‚ĐžĐŗĐž" ИИ](https://wikipedia.org/wiki/Neats_and_scruffies). ПŅ€Đ¸Đ˛ĐĩŅ€ĐļĐĩĐŊŅ†Ņ‹ _ĐŊĐĩŅ€ŅŅˆĐģивОĐŗĐž ИИ_ Ņ‡Đ°ŅĐ°Đŧи ĐēĐžŅ€Ņ€ĐĩĐēŅ‚иŅ€ĐžĐ˛Đ°Đģи ĐŋŅ€ĐžĐŗŅ€Đ°ĐŧĐŧŅ‹, ĐŋĐžĐēĐ° ĐŊĐĩ ĐŋĐžĐģŅƒŅ‡Đ°Đģи ĐļĐĩĐģĐ°ĐĩĐŧŅ‹Ņ… Ņ€ĐĩСŅƒĐģŅŒŅ‚Đ°Ņ‚Ов. ПŅ€Đ¸Đ˛ĐĩŅ€ĐļĐĩĐŊŅ†Ņ‹ _ЧиŅŅ‚ĐžĐŗĐž ИИ_ ĐąŅ‹Đģи "ŅĐžŅŅ€ĐĩĐ´ĐžŅ‚ĐžŅ‡ĐĩĐŊŅ‹ ĐŊĐ° ĐģĐžĐŗиĐēĐĩ и Ņ€ĐĩŅˆĐĩĐŊии Ņ„ĐžŅ€ĐŧĐ°ĐģŅŒĐŊŅ‹Ņ… СадаŅ‡". ЭЛИЗА и SHRDLU ĐąŅ‹Đģи Ņ…ĐžŅ€ĐžŅˆĐž иСвĐĩŅŅ‚ĐŊŅ‹Đŧи _ĐŊĐĩŅ€ŅŅˆĐģивŅ‹Đŧи_ ŅĐ¸ŅŅ‚ĐĩĐŧĐ°Đŧи. В 1980-Ņ… ĐŗОдаŅ…, ĐēĐžĐŗĐ´Đ° вОСĐŊиĐē ŅĐŋŅ€ĐžŅ ĐŊĐ° Ņ‚Đž, Ņ‡Ņ‚ОйŅ‹ ŅĐ´ĐĩĐģĐ°Ņ‚ŅŒ ŅĐ¸ŅŅ‚ĐĩĐŧŅ‹ ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐŗĐž ОйŅƒŅ‡ĐĩĐŊиŅ вОŅĐŋŅ€ĐžĐ¸ĐˇĐ˛ĐžĐ´Đ¸ĐŧŅ‹Đŧи, _ЧиŅŅ‚Ņ‹Đš_ ĐŋОдŅ…Од ĐŋĐžŅŅ‚ĐĩĐŋĐĩĐŊĐŊĐž вŅ‹ŅˆĐĩĐģ ĐŊĐ° ĐŋĐĩŅ€ĐĩĐ´ĐŊиК ĐŋĐģĐ°ĐŊ, ĐŋĐžŅĐēĐžĐģŅŒĐēŅƒ ĐĩĐŗĐž Ņ€ĐĩСŅƒĐģŅŒŅ‚Đ°Ņ‚Ņ‹ йОĐģĐĩĐĩ ОйŅŠŅŅĐŊиĐŧŅ‹. - ---- -## Đ­ĐēŅĐŋĐĩŅ€Ņ‚ĐŊŅ‹Đĩ ŅĐ¸ŅŅ‚ĐĩĐŧŅ‹ 1980-Ņ… ĐŗОдОв - -По ĐŧĐĩŅ€Đĩ Ņ€ĐžŅŅ‚Đ° ĐžŅ‚Ņ€Đ°ŅĐģи ĐĩĐĩ ĐŋŅ€ĐĩиĐŧŅƒŅ‰ĐĩŅŅ‚ва Đ´ĐģŅ йиСĐŊĐĩŅĐ° ŅŅ‚Đ°ĐŊОвиĐģиŅŅŒ вŅĐĩ йОĐģĐĩĐĩ ĐžŅ‡ĐĩвидĐŊŅ‹Đŧи, Đ° в 1980-Ņ… ĐŗОдаŅ… - и Ņ€Đ°ŅĐŋŅ€ĐžŅŅ‚Ņ€Đ°ĐŊĐĩĐŊиĐĩ "ŅĐēŅĐŋĐĩŅ€Ņ‚ĐŊŅ‹Ņ… ŅĐ¸ŅŅ‚ĐĩĐŧ". "Đ­ĐēŅĐŋĐĩŅ€Ņ‚ĐŊŅ‹Đĩ ŅĐ¸ŅŅ‚ĐĩĐŧŅ‹ ĐąŅ‹Đģи ОдĐŊиĐŧи иС ĐŋĐĩŅ€Đ˛Ņ‹Ņ… ĐŋĐž-ĐŊĐ°ŅŅ‚ĐžŅŅ‰ĐĩĐŧŅƒ ŅƒŅĐŋĐĩŅˆĐŊŅ‹Ņ… Ņ„ĐžŅ€Đŧ ĐŋŅ€ĐžĐŗŅ€Đ°ĐŧĐŧĐŊĐžĐŗĐž ОйĐĩŅĐŋĐĩŅ‡ĐĩĐŊиŅ иŅĐēŅƒŅŅŅ‚вĐĩĐŊĐŊĐžĐŗĐž иĐŊŅ‚ĐĩĐģĐģĐĩĐēŅ‚Đ° (ИИ)". ([иŅŅ‚ĐžŅ‡ĐŊиĐē](https://ru.wikipedia.org/wiki/%D0%AD%D0%BA%D1%81%D0%BF%D0%B5%D1%80%D1%82%D0%BD%D0%B0%D1%8F_%D1%81%D0%B8%D1%81%D1%82%D0%B5%D0%BC%D0%B0)). - -Đ­Ņ‚ĐžŅ‚ Ņ‚иĐŋ ŅĐ¸ŅŅ‚ĐĩĐŧŅ‹ ĐŊĐ° ŅĐ°ĐŧĐžĐŧ Đ´ĐĩĐģĐĩ ĐąŅ‹Đģ _ĐŗийŅ€Đ¸Đ´ĐŊŅ‹Đŧ_, Ņ‡Đ°ŅŅ‚иŅ‡ĐŊĐž ŅĐžŅŅ‚ĐžŅŅ‰Đ¸Đŧ иС ĐŧĐĩŅ…Đ°ĐŊиСĐŧĐ° ĐŋŅ€Đ°Đ˛Đ¸Đģ, ĐžĐŋŅ€ĐĩĐ´ĐĩĐģŅŅŽŅ‰ĐĩĐŗĐž йиСĐŊĐĩŅ-Ņ‚Ņ€ĐĩйОваĐŊиŅ, и ĐŧĐĩŅ…Đ°ĐŊиСĐŧĐ° вŅ‹Đ˛ĐžĐ´Đ°, ĐēĐžŅ‚ĐžŅ€Ņ‹Đš иŅĐŋĐžĐģŅŒĐˇŅƒĐĩŅ‚ ŅĐ¸ŅŅ‚ĐĩĐŧŅƒ ĐŋŅ€Đ°Đ˛Đ¸Đģ Đ´ĐģŅ вŅ‹Đ˛ĐžĐ´Đ° ĐŊОвŅ‹Ņ… Ņ„Đ°ĐēŅ‚Ов. - -В ŅŅ‚Ņƒ ŅĐŋĐžŅ…Ņƒ Ņ‚Đ°ĐēĐļĐĩ вŅĐĩ йОĐģŅŒŅˆĐĩĐĩ вĐŊиĐŧĐ°ĐŊиŅ ŅƒĐ´ĐĩĐģŅĐģĐžŅŅŒ ĐŊĐĩĐšŅ€ĐžĐŊĐŊŅ‹Đŧ ŅĐĩŅ‚ŅĐŧ. - ---- -## 1987 - 1993: 'ОŅ…ĐģĐ°ĐļĐ´ĐĩĐŊиĐĩ' Đē ИИ - -Đ Đ°ŅĐŋŅ€ĐžŅŅ‚Ņ€Đ°ĐŊĐĩĐŊиĐĩ ŅĐŋĐĩŅ†Đ¸Đ°ĐģиСиŅ€ĐžĐ˛Đ°ĐŊĐŊĐžĐŗĐž ОйОŅ€ŅƒĐ´ĐžĐ˛Đ°ĐŊиŅ ŅĐēŅĐŋĐĩŅ€Ņ‚ĐŊŅ‹Ņ… ŅĐ¸ŅŅ‚ĐĩĐŧ ĐŋŅ€Đ¸Đ˛ĐĩĐģĐž Đē ĐŋĐĩŅ‡Đ°ĐģŅŒĐŊĐžĐŧŅƒ Ņ€ĐĩСŅƒĐģŅŒŅ‚Đ°Ņ‚Ņƒ - ĐžĐŊĐž ŅŅ‚Đ°ĐģĐž ŅĐģиŅˆĐēĐžĐŧ ŅĐŋĐĩŅ†Đ¸Đ°ĐģиСиŅ€ĐžĐ˛Đ°ĐŊĐŊŅ‹Đŧ. ПоŅĐ˛ĐģĐĩĐŊиĐĩ ĐŋĐĩŅ€ŅĐžĐŊĐ°ĐģŅŒĐŊŅ‹Ņ… ĐēĐžĐŧĐŋŅŒŅŽŅ‚ĐĩŅ€ĐžĐ˛ ĐēĐžĐŊĐēŅƒŅ€Đ¸Ņ€ĐžĐ˛Đ°ĐģĐž Ņ ŅŅ‚иĐŧи ĐēŅ€ŅƒĐŋĐŊŅ‹Đŧи ŅĐŋĐĩŅ†Đ¸Đ°ĐģиСиŅ€ĐžĐ˛Đ°ĐŊĐŊŅ‹Đŧи Ņ†ĐĩĐŊŅ‚Ņ€Đ°ĐģиСОваĐŊĐŊŅ‹Đŧи ŅĐ¸ŅŅ‚ĐĩĐŧĐ°Đŧи. НаŅ‡Đ°ĐģĐ°ŅŅŒ Đ´ĐĩĐŧĐžĐēŅ€Đ°Ņ‚иСаŅ†Đ¸Ņ вŅ‹Ņ‡Đ¸ŅĐģиŅ‚ĐĩĐģŅŒĐŊОК Ņ‚ĐĩŅ…ĐŊиĐēи, и в ĐēĐžĐŊĐĩŅ‡ĐŊĐžĐŧ иŅ‚ĐžĐŗĐĩ ĐžĐŊĐ° ĐŋŅ€ĐžĐģĐžĐļиĐģĐ° ĐŋŅƒŅ‚ŅŒ Đē ŅĐžĐ˛Ņ€ĐĩĐŧĐĩĐŊĐŊĐžĐŧŅƒ вСŅ€Ņ‹Đ˛Ņƒ йОĐģŅŒŅˆĐ¸Ņ… Đ´Đ°ĐŊĐŊŅ‹Ņ…. - ---- -## 1993 - 2011 - -Đ­Ņ‚Đ° ŅĐŋĐžŅ…Đ° ОСĐŊĐ°ĐŧĐĩĐŊОваĐģĐ° ĐŊОвŅƒŅŽ ŅŅ€Ņƒ Đ´ĐģŅ ML и ИИ, ĐēĐžŅ‚ĐžŅ€Ņ‹Đĩ ŅĐŧĐžĐŗĐģи Ņ€ĐĩŅˆĐ¸Ņ‚ŅŒ ĐŊĐĩĐēĐžŅ‚ĐžŅ€Ņ‹Đĩ ĐŋŅ€ĐžĐąĐģĐĩĐŧŅ‹, вОСĐŊиĐēавŅˆĐ¸Đĩ Ņ€Đ°ĐŊĐĩĐĩ иС-Са ĐŊĐĩŅ…ваŅ‚Đēи Đ´Đ°ĐŊĐŊŅ‹Ņ… и вŅ‹Ņ‡Đ¸ŅĐģиŅ‚ĐĩĐģŅŒĐŊŅ‹Ņ… ĐŧĐžŅ‰ĐŊĐžŅŅ‚ĐĩĐš. ОбŅŠĐĩĐŧ Đ´Đ°ĐŊĐŊŅ‹Ņ… ĐŊĐ°Ņ‡Đ°Đģ ĐąŅ‹ŅŅ‚Ņ€Đž ŅƒĐ˛ĐĩĐģиŅ‡Đ¸Đ˛Đ°Ņ‚ŅŒŅŅ и ŅŅ‚Đ°ĐŊОвиŅ‚ŅŒŅŅ вŅĐĩ йОĐģĐĩĐĩ Đ´ĐžŅŅ‚ŅƒĐŋĐŊŅ‹Đŧ, и Đē ĐģŅƒŅ‡ŅˆĐĩĐŧŅƒ и Đē Ņ…ŅƒĐ´ŅˆĐĩĐŧŅƒ, ĐžŅĐžĐąĐĩĐŊĐŊĐž Ņ ĐŋĐžŅĐ˛ĐģĐĩĐŊиĐĩĐŧ ŅĐŧĐ°Ņ€Ņ‚Ņ„ĐžĐŊĐ° ĐŋŅ€Đ¸ĐŧĐĩŅ€ĐŊĐž в 2007 ĐŗОдŅƒ. ВŅ‹Ņ‡Đ¸ŅĐģиŅ‚ĐĩĐģŅŒĐŊĐ°Ņ ĐŧĐžŅ‰ĐŊĐžŅŅ‚ŅŒ Ņ€ĐžŅĐģĐ° ŅĐēŅĐŋĐžĐŊĐĩĐŊŅ†Đ¸Đ°ĐģŅŒĐŊĐž, и вĐŧĐĩŅŅ‚Đĩ Ņ ĐŊĐĩĐš Ņ€Đ°ĐˇĐ˛Đ¸Đ˛Đ°ĐģиŅŅŒ Đ°ĐģĐŗĐžŅ€Đ¸Ņ‚ĐŧŅ‹. Đ­Ņ‚Đ° ОйĐģĐ°ŅŅ‚ŅŒ ĐŊĐ°Ņ‡Đ°ĐģĐ° ĐŊайиŅ€Đ°Ņ‚ŅŒ СŅ€ĐĩĐģĐžŅŅ‚ŅŒ ĐŋĐž ĐŧĐĩŅ€Đĩ Ņ‚ĐžĐŗĐž, ĐēĐ°Đē ŅĐ˛ĐžĐąĐžĐ´ĐŊŅ‹Đĩ Đ´ĐŊи ĐŋŅ€ĐžŅˆĐģĐžĐŗĐž ĐŊĐ°Ņ‡Đ°Đģи ĐŋŅ€ĐĩвŅ€Đ°Ņ‰Đ°Ņ‚ŅŒŅŅ в ĐŊĐ°ŅŅ‚ĐžŅŅ‰ŅƒŅŽ диŅŅ†Đ¸ĐŋĐģиĐŊŅƒ. - ---- -## ĐĄĐĩĐšŅ‡Đ°Ņ - -ĐĄĐĩĐŗОдĐŊŅ ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐĩ ОйŅƒŅ‡ĐĩĐŊиĐĩ и иŅĐēŅƒŅŅŅ‚вĐĩĐŊĐŊŅ‹Đš иĐŊŅ‚ĐĩĐģĐģĐĩĐēŅ‚ СаŅ‚Ņ€Đ°ĐŗиваŅŽŅ‚ ĐŋŅ€Đ°ĐēŅ‚иŅ‡ĐĩŅĐēи вŅĐĩ ŅŅ„ĐĩŅ€Ņ‹ ĐŊĐ°ŅˆĐĩĐš ĐļиСĐŊи. ĐĸĐĩĐēŅƒŅ‰Đ°Ņ ŅĐŋĐžŅ…Đ° Ņ‚Ņ€ĐĩĐąŅƒĐĩŅ‚ Ņ‚Ņ‰Đ°Ņ‚ĐĩĐģŅŒĐŊĐžĐŗĐž ĐŋĐžĐŊиĐŧĐ°ĐŊиŅ Ņ€Đ¸ŅĐēОв и ĐŋĐžŅ‚ĐĩĐŊŅ†Đ¸Đ°ĐģŅŒĐŊŅ‹Ņ… ĐŋĐžŅĐģĐĩĐ´ŅŅ‚виК ŅŅ‚иŅ… Đ°ĐģĐŗĐžŅ€Đ¸Ņ‚ĐŧОв Đ´ĐģŅ Ņ‡ĐĩĐģОвĐĩŅ‡ĐĩŅĐēиŅ… ĐļиСĐŊĐĩĐš. КаĐē СаŅĐ˛Đ¸Đģ БŅ€ŅĐ´ ĐĄĐŧиŅ‚ иС Microsoft, "ИĐŊŅ„ĐžŅ€ĐŧĐ°Ņ†Đ¸ĐžĐŊĐŊŅ‹Đĩ Ņ‚ĐĩŅ…ĐŊĐžĐģĐžĐŗии ĐŋОдĐŊиĐŧĐ°ŅŽŅ‚ ĐŋŅ€ĐžĐąĐģĐĩĐŧŅ‹, ĐēĐžŅ‚ĐžŅ€Ņ‹Đĩ ĐģĐĩĐļĐ°Ņ‚ в ĐžŅĐŊОвĐĩ СаŅ‰Đ¸Ņ‚Ņ‹ ĐžŅĐŊОвĐŊŅ‹Ņ… ĐŋŅ€Đ°Đ˛ Ņ‡ĐĩĐģОвĐĩĐēĐ°, Ņ‚Đ°ĐēиŅ… ĐēĐ°Đē ĐēĐžĐŊŅ„идĐĩĐŊŅ†Đ¸Đ°ĐģŅŒĐŊĐžŅŅ‚ŅŒ и ŅĐ˛ĐžĐąĐžĐ´Đ° вŅ‹Ņ€Đ°ĐļĐĩĐŊиŅ ĐŧĐŊĐĩĐŊиК. Đ­Ņ‚и ĐŋŅ€ĐžĐąĐģĐĩĐŧŅ‹ ĐŋОвŅ‹ŅˆĐ°ŅŽŅ‚ ĐžŅ‚вĐĩŅ‚ŅŅ‚вĐĩĐŊĐŊĐžŅŅ‚ŅŒ Ņ‚ĐĩŅ…ĐŊĐžĐģĐžĐŗиŅ‡ĐĩŅĐēиŅ… ĐēĐžĐŧĐŋĐ°ĐŊиК, ĐēĐžŅ‚ĐžŅ€Ņ‹Đĩ ŅĐžĐˇĐ´Đ°ŅŽŅ‚ ŅŅ‚и ĐŋŅ€ĐžĐ´ŅƒĐēŅ‚Ņ‹. На ĐŊĐ°Ņˆ вСĐŗĐģŅĐ´, ĐžĐŊи Ņ‚Đ°ĐēĐļĐĩ Ņ‚Ņ€ĐĩĐąŅƒŅŽŅ‚ ĐŋŅ€ĐžĐ´ŅƒĐŧĐ°ĐŊĐŊĐžĐŗĐž ĐŗĐžŅŅƒĐ´Đ°Ņ€ŅŅ‚вĐĩĐŊĐŊĐžĐŗĐž Ņ€ĐĩĐŗŅƒĐģиŅ€ĐžĐ˛Đ°ĐŊиŅ и Ņ€Đ°ĐˇŅ€Đ°ĐąĐžŅ‚Đēи ĐŊĐžŅ€Đŧ, ĐēĐ°ŅĐ°ŅŽŅ‰Đ¸Ņ…ŅŅ ĐŋŅ€Đ¸ĐĩĐŧĐģĐĩĐŧŅ‹Ņ… видОв иŅĐŋĐžĐģŅŒĐˇĐžĐ˛Đ°ĐŊиŅ" ([иŅŅ‚ĐžŅ‡ĐŊиĐē](https://www.technologyreview.com/2019/12/18/102365/the-future-of-ais-impact-on-society/)). - ---- - -ЕŅ‰Đĩ ĐŋŅ€ĐĩĐ´ŅŅ‚ОиŅ‚ ŅƒĐ˛Đ¸Đ´ĐĩŅ‚ŅŒ, Ņ‡Ņ‚Đž ĐļĐ´ĐĩŅ‚ ĐŊĐ°Ņ в ĐąŅƒĐ´ŅƒŅ‰ĐĩĐŧ, ĐŊĐž ваĐļĐŊĐž ĐŋĐžĐŊиĐŧĐ°Ņ‚ŅŒ ŅŅ‚и ŅĐ¸ŅŅ‚ĐĩĐŧŅ‹, Đ° Ņ‚Đ°ĐēĐļĐĩ ĐŋŅ€ĐžĐŗŅ€Đ°ĐŧĐŧĐŊĐžĐĩ ОйĐĩŅĐŋĐĩŅ‡ĐĩĐŊиĐĩ и Đ°ĐģĐŗĐžŅ€Đ¸Ņ‚ĐŧŅ‹, ĐēĐžŅ‚ĐžŅ€Ņ‹Đŧи ĐžĐŊи ŅƒĐŋŅ€Đ°Đ˛ĐģŅŅŽŅ‚. МŅ‹ ĐŊĐ°Đ´ĐĩĐĩĐŧŅŅ, Ņ‡Ņ‚Đž ŅŅ‚Đ° ŅƒŅ‡ĐĩĐąĐŊĐ°Ņ ĐŋŅ€ĐžĐŗŅ€Đ°ĐŧĐŧĐ° ĐŋĐžĐŧĐžĐļĐĩŅ‚ ваĐŧ ĐģŅƒŅ‡ŅˆĐĩ ĐŋĐžĐŊŅŅ‚ŅŒ, Ņ‡Ņ‚ОйŅ‹ вŅ‹ ĐŧĐžĐŗĐģи ĐŋŅ€Đ¸ĐŊŅŅ‚ŅŒ Ņ€ĐĩŅˆĐĩĐŊиĐĩ ŅĐ°ĐŧĐžŅŅ‚ĐžŅŅ‚ĐĩĐģŅŒĐŊĐž. - -[![ИŅŅ‚ĐžŅ€Đ¸Ņ ĐŗĐģŅƒĐąĐžĐēĐžĐŗĐž ОйŅƒŅ‡ĐĩĐŊиŅ](https://img.youtube.com/vi/mTtDfKgLm54/0.jpg)](https://www.youtube.com/watch?v=mTtDfKgLm54 "ИŅŅ‚ĐžŅ€Đ¸Ņ ĐŗĐģŅƒĐąĐžĐēĐžĐŗĐž ОйŅƒŅ‡ĐĩĐŊиŅ") -> đŸŽĨ НаĐļĐŧиŅ‚Đĩ ĐŊĐ° иСОйŅ€Đ°ĐļĐĩĐŊиĐĩ вŅ‹ŅˆĐĩ, Ņ‡Ņ‚ОйŅ‹ ĐŋĐžŅĐŧĐžŅ‚Ņ€ĐĩŅ‚ŅŒ видĐĩĐž: Yann LeCun ОйŅŅƒĐļĐ´Đ°ĐĩŅ‚ иŅŅ‚ĐžŅ€Đ¸ŅŽ ĐŗĐģŅƒĐąĐžĐēĐžĐŗĐž ОйŅƒŅ‡ĐĩĐŊиŅ в ŅŅ‚ОК ĐģĐĩĐēŅ†Đ¸Đ¸ - ---- -## 🚀ВŅ‹ĐˇĐžĐ˛ - -ПоĐŗŅ€ŅƒĐˇĐ¸Ņ‚ĐĩŅŅŒ в ОдиĐŊ иС ŅŅ‚иŅ… иŅŅ‚ĐžŅ€Đ¸Ņ‡ĐĩŅĐēиŅ… ĐŧĐžĐŧĐĩĐŊŅ‚Ов и ŅƒĐˇĐŊĐ°ĐšŅ‚Đĩ йОĐģŅŒŅˆĐĩ Đž ĐģŅŽĐ´ŅŅ…, ŅŅ‚ĐžŅŅ‰Đ¸Ņ… Са ĐŊиĐŧи. ЕŅŅ‚ŅŒ ŅƒĐ˛ĐģĐĩĐēĐ°Ņ‚ĐĩĐģŅŒĐŊŅ‹Đĩ ĐŋĐĩŅ€ŅĐžĐŊĐ°Đļи, и ĐŊи ОдĐŊĐž ĐŊĐ°ŅƒŅ‡ĐŊĐžĐĩ ĐžŅ‚ĐēŅ€Ņ‹Ņ‚иĐĩ ĐŊиĐēĐžĐŗĐ´Đ° ĐŊĐĩ ŅĐžĐˇĐ´Đ°Đ˛Đ°ĐģĐžŅŅŒ в ĐēŅƒĐģŅŒŅ‚ŅƒŅ€ĐŊĐžĐŧ ваĐēŅƒŅƒĐŧĐĩ. ЧŅ‚Đž вŅ‹ ОйĐŊĐ°Ņ€ŅƒĐļиŅ‚Đĩ? - -## [ĐĸĐĩŅŅ‚ ĐŋĐžŅĐģĐĩ ĐģĐĩĐēŅ†Đ¸Đ¸](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/4/) - ---- -## ОбзоŅ€ и ŅĐ°ĐŧООйŅƒŅ‡ĐĩĐŊиĐĩ - -ВоŅ‚ Ņ‡Ņ‚Đž ĐŧĐžĐļĐŊĐž ĐŋĐžŅĐŧĐžŅ‚Ņ€ĐĩŅ‚ŅŒ и ĐŋĐžŅĐģŅƒŅˆĐ°Ņ‚ŅŒ: - -[Đ­Ņ‚ĐžŅ‚ ĐŋОдĐēĐ°ŅŅ‚, в ĐēĐžŅ‚ĐžŅ€ĐžĐŧ Đ­Đŧи Бойд ОйŅŅƒĐļĐ´Đ°ĐĩŅ‚ ŅĐ˛ĐžĐģŅŽŅ†Đ¸ŅŽ ИИ](http://runasradio.com/Shows/Show/739) - -[![ИŅŅ‚ĐžŅ€Đ¸Ņ иŅĐēŅƒŅŅŅ‚вĐĩĐŊĐŊĐžĐŗĐž иĐŊŅ‚ĐĩĐģĐģĐĩĐēŅ‚Đ° ĐžŅ‚ Đ­Đŧи Бойд](https://img.youtube.com/vi/EJt3_bFYKss/0.jpg)](https://www.youtube.com/watch?v=EJt3_bFYKss "ИŅŅ‚ĐžŅ€Đ¸Ņ иŅĐēŅƒŅŅŅ‚вĐĩĐŊĐŊĐžĐŗĐž иĐŊŅ‚ĐĩĐģĐģĐĩĐēŅ‚Đ° ĐžŅ‚ Đ­Đŧи Бойд") - ---- - -## ЗадаĐŊиĐĩ - -[ХОСдаКŅ‚Đĩ вŅ€ĐĩĐŧĐĩĐŊĐŊŅƒŅŽ ŅˆĐēĐ°ĐģŅƒ](assignment.ru.md) \ No newline at end of file diff --git a/1-Introduction/2-history-of-ML/translations/README.tr.md b/1-Introduction/2-history-of-ML/translations/README.tr.md deleted file mode 100644 index 4145f666..00000000 --- a/1-Introduction/2-history-of-ML/translations/README.tr.md +++ /dev/null @@ -1,117 +0,0 @@ -# Makine Ãļğreniminin tarihi - -![Bir taslak-notta makine Ãļğrenimi geçmişinin Ãļzeti](../../../sketchnotes/ml-history.png) -> [Tomomi Imura](https://www.twitter.com/girlie_mac) tarafÄąndan hazÄąrlanan taslak-not - -## [Ders Ãļncesi test](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/3?loc=tr) - -Bu derste, makine Ãļğrenimi ve yapay zeka tarihindeki Ãļnemli kilometre taşlarÄąnÄą inceleyeceğiz. - -Bir alan olarak yapay zekanÄąn (AI) tarihi, makine Ãļğreniminin tarihi ile iç içedir, çÃŧnkÃŧ makine Ãļğrenimini destekleyen algoritmalar ve bilgi-işlem kapasitesindeki ilerlemeler, yapay zekanÄąn gelişimini beslemektedir. AyrÄą bilim alanlanlarÄą olarak bu alanlar 1950'lerde belirginleşmeye başlarken, Ãļnemli [algoritmik, istatistiksel, matematiksel, hesaplamalÄą ve teknik keşiflerin](https://wikipedia.org/wiki/Timeline_of_machine_learning) bir kÄąsmÄą bu dÃļnemden Ãļnce gelmiş ve bir kÄąsmÄą da bu dÃļnem ile ÃļrtÃŧşmÃŧştÃŧr. AslÄąnda, insanlar [yÃŧzlerce yÄąldÄąr](https://wikipedia.org/wiki/History_of_artificial_intelligence) bu sorularÄą dÃŧşÃŧnÃŧyorlar: bu makale bir 'dÃŧşÃŧnen makine' fikrinin tarihsel entelektÃŧel temellerini tartÄąÅŸÄąyor. - -## Önemli keşifler - -- 1763, 1812 - [Bayes Teoremi](https://tr.wikipedia.org/wiki/Bayes_teoremi) ve ÃļncÃŧlleri. Bu teorem ve uygulamalarÄą, Ãļnceki bilgilere dayalÄą olarak meydana gelen bir olayÄąn olasÄąlığınÄą tanÄąmlayan Ã§ÄąkarÄąmÄąn temelini oluşturur. -- 1805 - [En KÃŧçÃŧk Kareler Teorisi](https://tr.wikipedia.org/wiki/En_k%C3%BC%C3%A7%C3%BCk_kareler_y%C3%B6ntemi), FransÄąz matematikçi Adrien-Marie Legendre tarafÄąndan bulunmuştur. Regresyon Ãŧnitemizde Ãļğreneceğiniz bu teori, makine Ãļğrenimi modelini veriye uydurmada yardÄąmcÄą olur. -- 1913 - Rus matematikçi Andrey Markov'un adÄąnÄą taÅŸÄąyan [Markov Zincirleri](https://tr.wikipedia.org/wiki/Markov_zinciri), Ãļnceki bir duruma dayalÄą olasÄą olaylar dizisini tanÄąmlamak için kullanÄąlÄąr. -- 1957 - [AlgÄąlayÄącÄą (Perceptron)](https://tr.wikipedia.org/wiki/Perceptron), derin Ãļğrenmedeki ilerlemelerin temelini oluşturan AmerikalÄą psikolog Frank Rosenblatt tarafÄąndan icat edilen bir tÃŧr doğrusal sÄąnÄąflandÄąrÄącÄądÄąr. -- 1967 - [En YakÄąn Komşu](https://wikipedia.org/wiki/Nearest_neighbor), orijinal olarak rotalarÄą haritalamak için tasarlanmÄąÅŸ bir algoritmadÄąr. Bir ML bağlamÄąnda kalÄąplarÄą tespit etmek için kullanÄąlÄąr. -- 1970 - [Geri YayÄąlÄąm](https://wikipedia.org/wiki/Backpropagation), [ileri beslemeli sinir ağlarÄąnÄą](https://wikipedia.org/wiki/Feedforward_neural_network) eğitmek için kullanÄąlÄąr. -- 1982 - [Tekrarlayan Sinir AğlarÄą](https://wikipedia.org/wiki/Recurrent_neural_network), zamansal grafikler oluşturan ileri beslemeli sinir ağlarÄąndan tÃŧretilen yapay sinir ağlarÄądÄąr. - -✅ Biraz araştÄąrma yapÄąn. Makine Ãļğrenimi ve yapay zeka tarihinde Ãļnemli olan başka hangi tarihler Ãļne Ã§ÄąkÄąyor? - -## 1950: DÃŧşÃŧnen makineler - -[2019'da halk tarafÄąndan](https://wikipedia.org/wiki/Icons:_The_Greatest_Person_of_the_20th_Century) 20. yÃŧzyÄąlÄąn en bÃŧyÃŧk bilim adamÄą seçilen gerçekten dikkate değer bir kişi olan Alan Turing'in, 'dÃŧşÃŧnebilen makine' kavramÄąnÄąn temellerini attığı kabul edilir. Kendisine karÅŸÄą Ã§Äąkanlara yanÄąt olmasÄą için ve bu kavramÄąn deneysel kanÄątlarÄąnÄą bulma ihtiyacÄą sebebiyle, NLP derslerimizde keşfedeceğiniz [Turing Testi'ni](https://www.bbc.com/news/technology-18475646) oluşturdu. - -## 1956: Dartmouth Yaz AraştÄąrma Projesi - -"Yapay zeka Ãŧzerine Dartmouth Yaz AraştÄąrma Projesi", bir alan olarak yapay zeka için Ã§ÄąÄŸÄąr açan bir olaydÄą ve burada 'yapay zeka' terimi ortaya Ã§ÄąktÄą ([kaynak](https://250.dartmouth.edu/highlights/artificial-intelligence-ai-coined-dartmouth)). - -> Öğrenmenin her yÃļnÃŧ veya zekanÄąn diğer herhangi bir Ãļzelliği, prensipte o kadar kesin bir şekilde tanÄąmlanabilir ki, onu simÃŧle etmek için bir makine yapÄąlabilir. - -Baş araştÄąrmacÄą, matematik profesÃļrÃŧ John McCarthy, "Ãļğrenmenin her yÃļnÃŧnÃŧn veya zekanÄąn diğer herhangi bir Ãļzelliğinin prensipte oldukça kesin bir şekilde tanÄąmlanabileceği varsayÄąmÄąna dayanarak, onu simÃŧle etmek için bir makine yapÄąlabileceği" varsayÄąmÄąnÄąn doğru olmasÄąnÄą umarak ilerliyordu. KatÄąlÄąmcÄąlar arasÄąnda bu alanÄąn bir diğer Ãļnderi olan Marvin Minsky de vardÄą. - -ÇalÄąÅŸtay, "sembolik yÃļntemlerin yÃŧkselişi, sÄąnÄąrlÄą alanlara odaklanan sistemler (ilk uzman sistemler) ve tÃŧmdengelimli sistemlere karÅŸÄą tÃŧmevarÄąmlÄą sistemler" dahil olmak Ãŧzere çeşitli tartÄąÅŸmalarÄą başlatmÄąÅŸ ve teşvik etmiştir. ([kaynak](https://tr.wikipedia.org/wiki/Dartmouth_Konferans%C4%B1)). - -## 1956 - 1974: "AltÄąn yÄąllar" - -1950'lerden 70'lerin ortalarÄąna kadar, yapay zekanÄąn birçok sorunu çÃļzebileceği umuduyla iyimserlik arttÄą. 1967'de Marvin Minsky kendinden emin bir şekilde "Bir nesil içinde... 'yapay zeka' yaratma sorunu bÃŧyÃŧk ÃļlçÃŧde çÃļzÃŧlecek" dedi. (Minsky, Marvin (1967), Computation: Finite and Infinite Machines, Englewood Cliffs, N.J.: Prentice-Hall) - -Doğal dil işleme araştÄąrmalarÄą gelişti, aramalar iyileştirildi ve daha gÃŧçlÃŧ hale getirildi, ve basit gÃļrevlerin sade dil talimatlarÄą kullanÄąlarak tamamlandığı 'mikro dÃŧnyalar' kavramÄą yaratÄąldÄą. - -AraştÄąrmalar, devlet kurumlarÄą tarafÄąndan iyi finanse edildi, hesaplamalar ve algoritmalarda ilerlemeler kaydedildi ve akÄąllÄą makinelerin prototipleri yapÄąldÄą. Bu makinelerden bazÄąlarÄą şunlardÄąr: - -* [Robot Shakey](https://wikipedia.org/wiki/Shakey_the_robot), manevra yapabilir ve gÃļrevleri 'akÄąllÄąca' nasÄąl yerine getireceğine karar verebilir. - - ![Shakey, akÄąllÄą bir robot](../images/shakey.jpg) - > 1972'de Shakey - -* Erken bir 'sohbet botu' olan Eliza, insanlarla sohbet edebilir ve ilkel bir 'terapist' gibi davranabilirdi. NLP derslerinde Eliza hakkÄąnda daha fazla bilgi edineceksiniz. - - ![Eliza, bir bot](../images/eliza.png) - > Bir sohbet robotu olan Eliza'nÄąn bir versiyonu - -* "DÃŧnya BloklarÄą", bloklarÄąn Ãŧst Ãŧste koyulabilecekleri, sÄąralanabilecekleri ve karar vermeyi Ãļğreten makinelerdeki deneylerin test edilebileceği bir mikro dÃŧnyaya Ãļrnekti. [SHRDLU](https://wikipedia.org/wiki/SHRDLU) gibi kÃŧtÃŧphanelerle oluşturulan gelişmeler, dil işlemeyi ilerletmeye yardÄąmcÄą oldu. - - [![SHRDLU ile DÃŧnya BloklarÄą](https://img.youtube.com/vi/QAJz4YKUwqw/0.jpg)](https://www.youtube.com/watch?v=QAJz4YKUwqw "SHRDLU ile DÃŧnya BloklarÄą" ) - - > đŸŽĨ Video için yukarÄądaki resme tÄąklayÄąn: SHRDLU ile DÃŧnya BloklarÄą - -## 1974 - 1980: "Yapay ZekÃĸ KÄąÅŸÄą" - -1970'lerin ortalarÄąna gelindiğinde, 'akÄąllÄą makineler' yapmanÄąn karmaÅŸÄąklığınÄąn hafife alÄąndığı ve mevcut hesaplama gÃŧcÃŧ gÃļz ÃļnÃŧne alÄąndığında, verilen vaatlerin abartÄąldığı ortaya Ã§ÄąktÄą. Finansman kurudu ve alana olan gÃŧven azaldÄą. GÃŧveni etkileyen bazÄą sorunlar şunlardÄą: - -- **KÄąsÄątlÄąklar**. Hesaplama gÃŧcÃŧ çok sÄąnÄąrlÄąydÄą. -- **Kombinasyonel patlama**. Hesaplama gÃŧcÃŧ ve yeteneğinde paralel bir evrim olmaksÄązÄąn, bilgisayarlardan daha fazla soru istendikçe, eğitilmesi gereken parametre miktarÄą katlanarak arttÄą. -- **Veri eksikliği**. AlgoritmalarÄą test etme, geliştirme ve iyileştirme sÃŧrecini engelleyen bir veri kÄątlığı vardÄą. -- **Doğru sorularÄą mÄą soruyoruz?**. Sorulan sorular sorgulanmaya başlandÄą. AraştÄąrmacÄąlar mevcut yaklaÅŸÄąmlarÄą eleştirmeye başladÄą: - - Turing testleri, diğer fikirlerin yanÄą sÄąra, "Çin odasÄą teorisi" aracÄąlığıyla sorgulanmaya başlandÄą. Bu teori, "dijital bir bilgisayar, programlanarak dili anlÄąyormuş gibi gÃļsterilebilir fakat gerçek bir dil anlayÄąÅŸÄą elde edilemez" savÄąnÄą Ãļne sÃŧrmektedir. ([kaynak](https://plato.stanford.edu/entries/chinese-room/) - - "Terapist" ELIZA gibi yapay zekalarÄąn topluma tanÄątÄąlmasÄąnÄąn etiğine meydan okundu. - -AynÄą zamanda, çeşitli yapay zekÃĸ dÃŧşÃŧnce okullarÄą oluşmaya başladÄą. ["dağınÄąk" ile "dÃŧzenli AI"](https://wikipedia.org/wiki/Neats_and_scruffies) uygulamalarÄą arasÄąnda bir ikilem kuruldu. _DağınÄąk_ laboratuvarlar, istenen sonuçlarÄą elde edene kadar programlar Ãŧzerinde saatlerce ince ayar yaptÄą. _DÃŧzenli_ laboratuvarlar "mantÄąk ve biçimsel problem çÃļzmeye odaklandÄą". ELIZA ve SHRDLU, iyi bilinen _dağınÄąk_ sistemlerdi. 1980'lerde, ML sistemlerinin sonuçlarÄąnÄą tekrarlanabilir hale getirmek için talep ortaya Ã§ÄąktÄąkça, sonuçlarÄą daha aÃ§Äąklanabilir olduğu için _dÃŧzenli_ yaklaÅŸÄąm yavaş yavaş Ãļn plana Ã§ÄąktÄą. - -## 1980'ler: Uzman sistemler - -Alan bÃŧyÃŧdÃŧkçe, şirketlere olan faydasÄą daha net hale geldi ve 1980'lerde 'uzman sistemlerin' yaygÄąnlaşmasÄą da bu şekilde meydana geldi. "Uzman sistemler, yapay zeka (AI) yazÄąlÄąmlarÄąnÄąn gerçek anlamda başarÄąlÄą olan ilk formlarÄą arasÄąndaydÄą." ([kaynak](https://tr.wikipedia.org/wiki/Uzman_sistemler)). - -Bu sistem tÃŧrÃŧ aslÄąnda kÄąsmen iş gereksinimlerini tanÄąmlayan bir kural aracÄąndan ve yeni gerçekleri Ã§Äąkarmak için kurallar sisteminden yararlanan bir Ã§ÄąkarÄąm aracÄąndan oluşan bir _melezdir_. - -Bu çağda aynÄą zamanda sinir ağlarÄąna artan ilgi de gÃļrÃŧlmÃŧştÃŧr. - -## 1987 - 1993: Yapay Zeka 'SoğumasÄą' - -Özelleşmiş uzman sistem donanÄąmÄąnÄąn yaygÄąnlaşmasÄą, talihsiz bir şekilde bunlarÄą aÅŸÄąrÄą Ãļzelleşmiş hale getirdi. Kişisel bilgisayarlarÄąn yÃŧkselişi de bu bÃŧyÃŧk, Ãļzelleşmiş, merkezi sistemlerle rekabet etti. BilgisayarÄąn demokratikleşmesi başlamÄąÅŸtÄą ve sonunda modern bÃŧyÃŧk veri patlamasÄąnÄąn yolunu açtÄą. - -## 1993 - 2011 - -Bu çağ, daha Ãļnce veri ve hesaplama gÃŧcÃŧ eksikliğinden kaynaklanan bazÄą sorunlarÄą çÃļzebilmek için ML ve AI için yeni bir dÃļnemi getirdi. Veri miktarÄą hÄązla artmaya başladÄą ve Ãļzellikle 2007'de akÄąllÄą telefonun ortaya Ã§ÄąkmasÄąyla birlikte iyisiyle kÃļtÃŧsÃŧyle daha yaygÄąn bir şekilde ulaÅŸÄąlabilir hale geldi. Hesaplama gÃŧcÃŧ katlanarak arttÄą ve algoritmalar da onunla birlikte gelişti. Geçmişin baÅŸÄąboş gÃŧnleri gitmiş, yerine giderek olgunlaşan gerçek bir disipline dÃļnÃŧşÃŧm başlamÄąÅŸtÄą. - -## Şimdi - -GÃŧnÃŧmÃŧzde makine Ãļğrenimi ve yapay zeka hayatÄąmÄązÄąn neredeyse her alanÄąna dokunuyor. Bu çağ, bu algoritmalarÄąn insan yaşamÄą Ãŧzerindeki risklerinin ve potansiyel etkilerinin dikkatli bir şekilde anlaÅŸÄąlmasÄąnÄą gerektirmektedir. Microsoft'tan Brad Smith'in belirttiği gibi, "Bilgi teknolojisi, gizlilik ve ifade ÃļzgÃŧrlÃŧğÃŧ gibi temel insan haklarÄą korumalarÄąnÄąn kalbine giden sorunlarÄą gÃŧndeme getiriyor. Bu sorunlar, bu ÃŧrÃŧnleri yaratan teknoloji şirketlerinin sorumluluğunu artÄąrÄąyor. Bizim aÃ§ÄąmÄązdan bakÄąldığında, dÃŧşÃŧnceli hÃŧkÃŧmet dÃŧzenlemeleri ve kabul edilebilir kullanÄąmlar etrafÄąnda normlarÄąn geliştirilmesi için de bir çağrÄą niteliği taÅŸÄąyor." ([kaynak](https://www.technologyreview.com/2019/12/18/102365/the-future-of-ais-impact-on-society/) )). - -Geleceğin neler getireceğini birlikte gÃļreceğiz, ancak bu bilgisayar sistemlerini ve çalÄąÅŸtÄąrdÄąklarÄą yazÄąlÄąm ve algoritmalarÄą anlamak Ãļnemlidir. Bu mÃŧfredatÄąn, kendi kararlarÄąnÄązÄą verebilmeniz için daha iyi bir anlayÄąÅŸ kazanmanÄąza yardÄąmcÄą olacağınÄą umuyoruz. - -[![Derin Ãļğrenmenin tarihi](https://img.youtube.com/vi/mTtDfKgLm54/0.jpg)](https://www.youtube.com/watch?v=mTtDfKgLm54 "Derin Ãļğrenmenin tarihi") -> đŸŽĨ Video için yukarÄądaki resme tÄąklayÄąn: Yann LeCun bu derste derin Ãļğrenmenin tarihini tartÄąÅŸÄąyor - ---- -## 🚀Meydan okuma - -Bu tarihi anlardan birine girin ve arkasÄąndaki insanlar hakkÄąnda daha fazla bilgi edinin. BÃŧyÃŧleyici karakterler var ve kÃŧltÃŧrel bir boşlukta hiçbir bilimsel keşif yaratÄąlmadÄą. Ne keşfedersiniz? - -## [Ders sonrasÄą test](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/4?loc=tr) - -## Ä°nceleme ve Bireysel ÇalÄąÅŸma - -İşte izlenmesi ve dinlenmesi gerekenler: - -[Amy Boyd'un yapay zekanÄąn evrimini tartÄąÅŸtığı bu podcast](http://runasradio.com/Shows/Show/739) - -[![Amy Boyd ile Yapay ZekÃĸ'nÄąn tarihi](https://img.youtube.com/vi/EJt3_bFYKss/0.jpg)](https://www.youtube.com/watch?v=EJt3_bFYKss "Amy Boyd ile Yapay ZekÃĸ'nÄąn tarihi") - -## Ödev - -[Bir zaman çizelgesi oluşturun](assignment.tr.md) \ No newline at end of file diff --git a/1-Introduction/2-history-of-ML/translations/README.zh-cn.md b/1-Introduction/2-history-of-ML/translations/README.zh-cn.md deleted file mode 100644 index ddd2430d..00000000 --- a/1-Introduction/2-history-of-ML/translations/README.zh-cn.md +++ /dev/null @@ -1,116 +0,0 @@ -# æœē器å­Ļäš įš„åŽ†å˛ - -![æœē器å­Ļäš åŽ†å˛æĻ‚čŋ°](../../../sketchnotes/ml-history.png) -> äŊœč€… [Tomomi Imura](https://www.twitter.com/girlie_mac) - -## [č¯žå‰æĩ‹éĒŒ](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/3/) - -在æœŦč¯žä¸­īŧŒæˆ‘äģŦ将čĩ°čŋ‡æœē器å­Ļäš å’ŒäēēåˇĨæ™ēčƒŊåŽ†å˛ä¸Šįš„ä¸ģčĻé‡Œį¨‹įĸ‘。 - -äēēåˇĨæ™ēčƒŊīŧˆAIīŧ‰äŊœä¸ē一ä¸Ēéĸ†åŸŸįš„åŽ†å˛ä¸Žæœē器å­Ļäš įš„åŽ†å˛äē¤įģ‡åœ¨ä¸€čĩˇīŧŒå› ä¸ē支持æœē器å­Ļäš įš„įŽ—æŗ•å’ŒčŽĄįŽ—čƒŊ力įš„čŋ›æ­Ĩ推动äē†AIįš„å‘åą•ã€‚čŽ°äŊīŧŒč™Ŋį„ļčŋ™äē›éĸ†åŸŸäŊœä¸ē不同į ”įŠļéĸ†åŸŸåœ¨ 20 世įēĒ 50 åš´äģŖ才åŧ€å§‹å…ˇäŊ“化īŧŒäŊ†é‡čĻįš„[įŽ—æŗ•ã€įģŸčŽĄã€æ•°å­Ļã€čŽĄįŽ—和技术发įŽ°](https://wikipedia.org/wiki/Timeline_of_machine_learning) čĻæ—ŠäēŽå’Œé‡å äē†čŋ™ä¸Ēæ—ļäģŖ。 äē‹åŽžä¸ŠīŧŒ[数į™žåš´æĨ](https://wikipedia.org/wiki/History_of_artificial_intelligence)äēēäģŦ一į›´åœ¨æ€č€ƒčŋ™äē›é—Žéĸ˜īŧšæœŦæ–‡čŽ¨čŽēäē†â€œæ€įģ´æœē器”čŋ™ä¸€æĻ‚åŋĩįš„åŽ†å˛įŸĨč¯†åŸēįĄ€ã€‚ - -## ä¸ģčĻå‘įŽ° - -- 1763, 1812 [贝åļ斯厚į†](https://wikipedia.org/wiki/Bayes%27_theorem) 及å…ļ前čēĢ。č¯Ĩ厚į†åŠå…ļåē”į”¨æ˜¯æŽ¨į†įš„åŸēįĄ€īŧŒæčŋ°äē†åŸēäēŽå…ˆéĒŒįŸĨč¯†įš„äē‹äģļ发į”Ÿįš„æĻ‚įŽ‡ã€‚ -- 1805 [最小äēŒäš˜į†čŽē](https://wikipedia.org/wiki/Least_squares)į”ąæŗ•å›Ŋ数å­ĻåŽļ Adrien-Marie Legendre 提å‡ē。 äŊ å°†åœ¨æˆ‘äģŦįš„回åŊ’单元中äē†č§Ŗčŋ™ä¸€į†čŽēīŧŒåŽƒæœ‰åŠŠäēŽæ•°æŽæ‹Ÿåˆã€‚ -- 1913 [éŠŦ尔可å¤Ģ链](https://wikipedia.org/wiki/Markov_chain)äģĨäŋ„įŊ—斯数å­ĻåŽļ Andrey Markov įš„名字å‘Ŋ名īŧŒį”¨äēŽæčŋ°åŸēäēŽå…ˆå‰įŠļ态įš„一įŗģ列可čƒŊäē‹äģļ。 -- 1957 [感įŸĨ器](https://wikipedia.org/wiki/Perceptron)是įžŽå›Ŋåŋƒį†å­ĻåŽļ Frank Rosenblatt 发明įš„一į§įēŋ性分įąģ器īŧŒæ˜¯æˇąåēĻå­Ļäš å‘åą•įš„åŸēįĄ€ã€‚ -- 1967 [最čŋ‘é‚ģ](https://wikipedia.org/wiki/Nearest_neighbor)是一į§æœ€åˆčŽžčŽĄį”¨äēŽæ˜ å°„čˇ¯įēŋįš„įŽ—æŗ•ã€‚ 在 ML 中īŧŒåŽƒį”¨äēŽæŖ€æĩ‹æ¨Ąåŧã€‚ -- 1970 [反向äŧ æ’­](https://wikipedia.org/wiki/Backpropagation)į”¨äēŽčŽ­įģƒ[前éĻˆįĨžįģįŊ‘įģœ](https://wikipedia.org/wiki/Feedforward_neural_network)。 -- 1982 [åžĒįŽ¯įĨžįģįŊ‘įģœ](https://wikipedia.org/wiki/Recurrent_neural_network) 是æēč‡Ēäē§į”Ÿæ—ļ间回įš„前éĻˆįĨžįģįŊ‘įģœįš„äēēåˇĨįĨžįģįŊ‘įģœã€‚ - -✅ 做į‚šč°ƒæŸĨ。在 ML 和 AI įš„åŽ†å˛ä¸ŠīŧŒčŋ˜æœ‰å“Ēäē›æ—Ĩ期是重čĻįš„īŧŸ -## 1950: äŧšæ€č€ƒįš„æœē器 - -Alan TuringīŧŒä¸€ä¸ĒįœŸæ­Ŗ杰å‡ēįš„äēēīŧŒ[在 2019 åš´čĸĢå…Ŧäŧ—投įĨ¨é€‰å‡ē](https://wikipedia.org/wiki/Icons:_The_Greatest_Person_of_the_20th_Century) äŊœä¸ē 20 世įēĒ最äŧŸå¤§įš„į§‘å­ĻåŽļīŧŒäģ–莤ä¸ē有劊äēŽä¸ē“äŧšæ€č€ƒįš„æœē器”įš„æĻ‚åŋĩ打下åŸēįĄ€ã€‚äģ–通čŋ‡åˆ›åģē [回įĩæĩ‹č¯•](https://www.bbc.com/news/technology-18475646)æĨč§Ŗå†ŗåå¯šč€…å’Œäģ–č‡Ēåˇąå¯ščŋ™ä¸€æĻ‚åŋĩįš„įģéĒŒč¯æŽįš„éœ€æą‚īŧŒäŊ å°†åœ¨æˆ‘äģŦįš„ NLP č¯žį¨‹ä¸­čŋ›čĄŒæŽĸį´ĸ。 - -## 1956: čžžį‰ščŒ…斯夏å­Ŗį ”įŠļ饚į›Ž - -“达į‰ščŒ…斯夏å­ŖäēēåˇĨæ™ēčƒŊį ”įŠļ饚į›Žæ˜¯äēēåˇĨæ™ēčƒŊéĸ†åŸŸįš„一ä¸Ēåŧ€åˆ›æ€§äē‹äģļīŧŒâ€æ­Ŗ是在čŋ™é‡ŒīŧŒäēēäģŦ创造äē†â€œäēēåˇĨæ™ēčƒŊâ€ä¸€č¯īŧˆ[æĨæē](https://250.dartmouth.edu/highlights/artificial-intelligence-ai-coined-dartmouth)īŧ‰ã€‚ - -> 原则上īŧŒå­Ļäš įš„每ä¸Ēæ–šéĸ或æ™ēčƒŊįš„äģģäŊ•å…ļäģ–į‰šåžéƒŊ可äģĨčĸĢį˛žįĄŽåœ°æčŋ°īŧŒäģĨč‡ŗäēŽå¯äģĨį”¨æœē器æĨæ¨Ąæ‹ŸåŽƒã€‚ - -éĻ–席į ”įŠļ员、数å­Ļ教授 John McCarthy 希望“åŸēäēŽčŋ™æ ˇä¸€į§įŒœæƒŗīŧŒåŗå­Ļäš įš„每ä¸Ēæ–šéĸ或æ™ēčƒŊįš„äģģäŊ•å…ļäģ–į‰šåžåŽŸåˆ™ä¸ŠéƒŊ可äģĨåĻ‚æ­¤į˛žįĄŽåœ°æčŋ°īŧŒäģĨč‡ŗäēŽå¯äģĨåˆļ造å‡ē一台æœē器æĨæ¨Ąæ‹ŸåŽƒã€‚â€ å‚ä¸Žč€…åŒ…æ‹Ŧč¯Ĩéĸ†åŸŸįš„åĻ一äŊæ°å‡ēäēēį‰Š Marvin Minsky。 - -į ”莨äŧščĸĢ莤ä¸ē发čĩˇåšļéŧ“åŠąäē†ä¸€äē›čŽ¨čŽēīŧŒåŒ…æ‹Ŧ“įŦĻåˇæ–šæŗ•įš„å…´čĩˇã€ä¸“æŗ¨äēŽæœ‰é™éĸ†åŸŸįš„įŗģįģŸīŧˆæ—ŠæœŸä¸“åŽļįŗģįģŸīŧ‰īŧŒäģĨ及æŧ”įģŽįŗģįģŸä¸ŽåŊ’įēŗįŗģįģŸįš„寚比。”īŧˆ[æĨæē](https://wikipedia.org/wiki/Dartmouth_workshop)īŧ‰ã€‚ - -## 1956 - 1974: “éģ„é‡‘å˛æœˆâ€ - -äģŽ 20 世įēĒ 50 åš´äģŖ到 70 åš´äģŖ中期īŧŒäšč§‚情įģĒéĢ˜æļ¨īŧŒå¸Œæœ›äēēåˇĨæ™ēčƒŊčƒŊ够č§Ŗå†ŗčŽ¸å¤šé—Žéĸ˜ã€‚1967 åš´īŧŒMarvin Minsky č‡ĒäŋĄåœ°č¯´īŧŒâ€œä¸€äģŖäēē䚋内...创造‘äēēåˇĨæ™ēčƒŊ’įš„é—Žéĸ˜å°†åž—åˆ°åŽžč´¨æ€§įš„č§Ŗå†ŗ。”īŧˆMinskyīŧŒMarvinīŧˆ1967īŧ‰īŧŒã€ŠčŽĄįŽ—īŧšæœ‰é™å’Œæ— é™æœē器》īŧŒæ–°æŗŊčĨŋåˇžæŠæ ŧäŧåžˇå…‹åˆŠå¤Ģ斯īŧšPrentice Hallīŧ‰ - -č‡Ēį„ļč¯­č¨€å¤„į†į ”įŠļč“Ŧå‹ƒå‘åą•īŧŒæœį´ĸčĸĢ提į‚ŧåšļ变垗更加åŧē大īŧŒåˆ›é€ äē†â€œåžŽč§‚世į•Œâ€įš„æĻ‚åŋĩīŧŒåœ¨čŋ™ä¸ĒæĻ‚åŋĩ中īŧŒįŽ€å•įš„äģģåŠĄæ˜¯į”¨įŽ€å•įš„č¯­č¨€æŒ‡äģ¤åŽŒæˆįš„。 - -čŋ™éĄšį ”įŠļ垗到äē†æ”ŋåēœæœē构įš„充分čĩ„劊īŧŒåœ¨čŽĄįŽ—å’ŒįŽ—æŗ•æ–šéĸ取垗äē†čŋ›åą•īŧŒåšļåģē造äē†æ™ēčƒŊæœē器įš„原型。å…ļ中一äē›æœē器包æ‹Ŧīŧš - -* [æœē器äēē Shakey](https://wikipedia.org/wiki/Shakey_the_robot)īŧŒäģ–äģŦ可äģĨ“čĒ明地”操įēĩ和å†ŗ厚åĻ‚äŊ•æ‰§čĄŒäģģåŠĄã€‚ - - ![Shakey, æ™ēčƒŊæœē器äēē](../images/shakey.jpg) - > 1972 åš´įš„ Shakey - -* ElizaīŧŒä¸€ä¸Ē旊期įš„â€œčŠå¤Šæœē器äēē”īŧŒå¯äģĨ与äēēäē¤č°ˆåšļ充åŊ“原始įš„“æ˛ģį–—师”。 äŊ å°†åœ¨ NLP č¯žį¨‹ä¸­äē†č§Ŗ有å…ŗ Eliza įš„更多äŋĄæ¯ã€‚ - - ![Eliza, æœē器äēē](../images/eliza.png) - > Eliza įš„一ä¸Ēį‰ˆæœŦīŧŒä¸€ä¸ĒčŠå¤Šæœē器äēē - -* “į§¯æœ¨ä¸–į•Œâ€æ˜¯ä¸€ä¸ĒåžŽč§‚ä¸–į•Œįš„䞋子īŧŒåœ¨é‚Ŗ里į§¯æœ¨å¯äģĨ堆叠和分įąģīŧŒåšļ且可äģĨæĩ‹č¯•æ•™æœē器做å‡ēå†ŗį­–įš„厞éĒŒã€‚ äŊŋį”¨ [SHRDLU](https://wikipedia.org/wiki/SHRDLU) į­‰åē“æž„åģēįš„éĢ˜įē§åŠŸčƒŊ有劊äēŽæŽ¨åŠ¨č¯­č¨€å¤„į†å‘å‰å‘åą•ã€‚ - - [![į§¯æœ¨ä¸–į•Œä¸Ž SHRDLU](https://img.youtube.com/vi/QAJz4YKUwqw/0.jpg)](https://www.youtube.com/watch?v=QAJz4YKUwqw "į§¯æœ¨ä¸–į•Œä¸ŽSHRDLU") - - > đŸŽĨ į‚šå‡ģä¸Šå›žč§‚įœ‹č§†éĸ‘īŧš į§¯æœ¨ä¸–į•Œä¸Ž SHRDLU - -## 1974 - 1980: AI įš„寒å†Ŧ - -到äē† 20 世įēĒ 70 åš´äģŖ中期īŧŒåžˆæ˜Žæ˜žåˆļ造“æ™ēčƒŊæœē器”įš„复杂性čĸĢäŊŽäŧ°äē†īŧŒč€Œä¸”č€ƒč™‘åˆ°å¯į”¨įš„莥įŽ—čƒŊ力īŧŒåŽƒįš„前景čĸĢ夸大äē†ã€‚čĩ„金枯įĢ­īŧŒå¸‚åœēäŋĄåŋƒæ”žįŧ“。åŊąå“äŋĄåŋƒįš„一äē›é—Žéĸ˜åŒ…æ‹Ŧīŧš - -- **限åˆļ**ã€‚čŽĄįŽ—čƒŊ力å¤Ē有限äē† -- **įģ„合įˆ†į‚¸**。随į€å¯ščŽĄįŽ—æœēįš„čĻæą‚čļŠæĨčļŠéĢ˜īŧŒéœ€čĻčŽ­įģƒįš„参数数量呈指数įē§åĸžé•ŋīŧŒč€ŒčŽĄįŽ—čƒŊåŠ›å´æ˛Ąæœ‰åšŗčĄŒå‘åą•ã€‚ -- **įŧē䚏数捎**。 įŧē䚏数捎é˜ģįĸäē†æĩ‹č¯•ã€åŧ€å‘和攚čŋ›įŽ—æŗ•įš„čŋ‡į¨‹ã€‚ -- **我äģŦ是åĻ在闎æ­ŖįĄŽįš„é—Žéĸ˜īŧŸ**。 čĸĢ闎到įš„é—Žéĸ˜äšŸåŧ€å§‹å—åˆ°č´¨į–‘。 į ”įŠļäēē员åŧ€å§‹å¯šäģ–äģŦįš„æ–šæŗ•æå‡ēæ‰šč¯„īŧš - - 回įĩæĩ‹č¯•å—åˆ°č´¨į–‘įš„æ–šæŗ•äš‹ä¸€æ˜¯â€œä¸­å›Ŋæˆŋ间į†čŽē”īŧŒč¯Ĩį†čŽē莤ä¸ēīŧŒâ€œå¯šæ•°å­—莥įŽ—æœēčŋ›čĄŒįŧ–į¨‹å¯čƒŊäŊŋå…ļįœ‹čĩˇæĨčƒŊį†č§Ŗč¯­č¨€īŧŒäŊ†ä¸čƒŊäē§į”ŸįœŸæ­Ŗįš„į†č§Ŗ。” ([æĨæē](https://plato.stanford.edu/entries/chinese-room/)) - - 将“æ˛ģį–—师”ELIZA čŋ™æ ˇįš„äēēåˇĨæ™ēčƒŊåŧ•å…Ĩį¤žäŧšįš„äŧĻį†å—到äē†æŒ‘战。 - -与此同æ—ļīŧŒå„į§äēēåˇĨæ™ēčƒŊå­Ļæ´žåŧ€å§‹åŊĸ成。 在 [“scruffy” 与 “neat AI”](https://wikipedia.org/wiki/Neats_and_scruffies) 之间åģēįĢ‹äē†äēŒåˆ†æŗ•ã€‚ _Scruffy_ 厞éĒŒåŽ¤å¯šį¨‹åēčŋ›čĄŒäē†æ•°å°æ—ļįš„č°ƒæ•´īŧŒį›´åˆ°čŽˇåž—所需įš„įģ“果。 _Neat_ 厞éĒŒåŽ¤â€œä¸“æŗ¨äēŽé€ģčž‘å’ŒåŊĸåŧé—Žéĸ˜įš„č§Ŗå†ŗ”。 ELIZA 和 SHRDLU 是äŧ—所周įŸĨįš„ _scruffy_ įŗģįģŸã€‚ 在 1980 åš´äģŖīŧŒéšį€äŊŋ ML įŗģįģŸå¯é‡įŽ°įš„éœ€æą‚å‡ēįŽ°īŧŒ_neat_ æ–šæŗ•é€æ¸čĩ°ä¸Šå‰æ˛ŋīŧŒå› ä¸ēå…ļįģ“果更易äēŽč§Ŗ释。 - -## 1980s 专åŽļįŗģįģŸ - -随į€čŋ™ä¸Ēéĸ†åŸŸįš„å‘åą•īŧŒåŽƒå¯šå•†ä¸šįš„åĨŊ处变垗čļŠæĨčļŠæ˜Žæ˜žīŧŒåœ¨ 20 世įēĒ 80 åš´äģŖīŧŒâ€˜ä¸“åŽļįŗģįģŸâ€™äšŸåŧ€å§‹åšŋæŗ›æĩčĄŒčĩˇæĨ。“专åŽļįŗģįģŸæ˜¯éĻ–扚įœŸæ­Ŗ成功įš„äēēåˇĨæ™ēčƒŊ (AI) čŊ¯äģļåŊĸåŧäš‹ä¸€ã€‚” īŧˆ[æĨæē](https://wikipedia.org/wiki/Expert_system)īŧ‰ã€‚ - -čŋ™į§įąģ型įš„įŗģįģŸåŽžé™…ä¸Šæ˜¯æˇˇåˆįŗģįģŸīŧŒéƒ¨åˆ†į”ąåŽšäš‰ä¸šåŠĄéœ€æą‚įš„č§„åˆ™åŧ•æ“Žå’ŒåˆŠį”¨č§„则įŗģįģŸæŽ¨æ–­æ–°äē‹åŽžįš„推į†åŧ•æ“Žįģ„成。 - -在čŋ™ä¸Ēæ—ļäģŖīŧŒįĨžįģįŊ‘įģœäšŸčļŠæĨčļŠå—åˆ°é‡č§†ã€‚ - -## 1987 - 1993: AI įš„å†ˇé™æœŸ - -专业įš„专åŽļįŗģįģŸįĄŦäģļįš„æŋ€åĸžé€ æˆäē†čŋ‡äēŽä¸“业化įš„不嚸后果。ä¸Ēäēēį”ĩ脑įš„å…´čĩˇäšŸä¸Žčŋ™äē›å¤§åž‹ã€ä¸“业化、集中化įŗģįģŸåą•åŧ€äē†įĢžäē‰ã€‚莥įŽ—æœēįš„åšŗæ°‘åŒ–åˇ˛įģåŧ€å§‹īŧŒåŽƒæœ€įģˆä¸ē大数捎įš„įŽ°äģŖįˆ†į‚¸é“ēåšŗäē†é“čˇ¯ã€‚ - -## 1993 - 2011 - -čŋ™ä¸Ēæ—ļäģŖč§č¯äē†ä¸€ä¸Ē新įš„æ—ļäģŖīŧŒML 和 AI čƒŊ够č§Ŗå†ŗ旊期į”ąäēŽįŧēäšæ•°æŽå’ŒčŽĄįŽ—čƒŊåŠ›č€Œå¯ŧ致įš„一äē›é—Žéĸ˜ã€‚数捎量åŧ€å§‹čŋ…速åĸžåŠ īŧŒå˜åž—čļŠæĨčļŠåšŋæŗ›īŧŒæ— čŽēåĨŊ坏īŧŒå°¤å…ļ是 2007 åš´åˇĻåŗæ™ēčƒŊ手æœēįš„å‡ēįŽ°īŧŒčŽĄįŽ—čƒŊ力呈指数įē§åĸžé•ŋīŧŒįŽ—æŗ•äšŸéšäš‹å‘åą•ã€‚čŋ™ä¸Ēéĸ†åŸŸåŧ€å§‹å˜åž—成į†ŸīŧŒå› ä¸ēčŋ‡åŽģé‚Ŗäē›éšåŋƒæ‰€æŦ˛įš„æ—Ĩ子åŧ€å§‹å…ˇäŊ“化ä¸ē一į§įœŸæ­Ŗįš„įēĒ型。 - -## įŽ°åœ¨ - -äģŠå¤ŠīŧŒæœē器å­Ļäš å’ŒäēēåˇĨæ™ēčƒŊ几䚎č§Ļ及我äģŦį”Ÿæ´ģįš„每一ä¸Ē部分。čŋ™ä¸Ēæ—ļäģŖčĻæą‚äģ”įģ†äē†č§Ŗčŋ™äē›įŽ—æŗ•å¯šäēēįąģį”Ÿæ´ģįš„éŖŽé™Šå’ŒæŊœåœ¨åŊąå“ã€‚æ­ŖåĻ‚垎čŊ¯įš„ Brad Smith æ‰€č¨€īŧŒâ€œäŋĄæ¯æŠ€æœ¯åŧ•å‘įš„é—Žéĸ˜č§Ļ及隐į§å’Œč¨€čŽēč‡Ēį”ąį­‰åŸēæœŦäēē权äŋæŠ¤įš„æ ¸åŋƒã€‚čŋ™äē›é—Žéĸ˜åŠ é‡äē†åˆļ造čŋ™äē›äē§å“įš„į§‘技å…Ŧ司įš„č´Ŗäģģ。在我äģŦįœ‹æĨīŧŒåŽƒäģŦčŋ˜å‘ŧ吁æ”ŋåēœčŋ›čĄŒæˇąæ€į†Ÿč™‘įš„į›‘įŽĄīŧŒåšļ围įģ•å¯æŽĨ受įš„į”¨é€”åˆļåŽšč§„čŒƒâ€īŧˆ[æĨæē](https://www.technologyreview.com/2019/12/18/102365/the-future-of-ais-impact-on-society/)īŧ‰ã€‚ - -æœĒæĨįš„情å†ĩčŋ˜æœ‰åž…č§‚å¯ŸīŧŒäŊ†äē†č§Ŗčŋ™äē›čŽĄįŽ—æœēįŗģįģŸäģĨ及厃äģŦčŋčĄŒįš„čŊ¯äģļ和įŽ—æŗ•æ˜¯åžˆé‡čĻįš„。我äģŦ希望čŋ™é—¨č¯žį¨‹čƒŊ帎劊äŊ æ›´åĨŊįš„į†č§ŖīŧŒäģĨäžŋäŊ č‡Ēåˇąå†ŗ厚。 - -[![æˇąåēĻå­Ļäš įš„åŽ†å˛](https://img.youtube.com/vi/mTtDfKgLm54/0.jpg)](https://www.youtube.com/watch?v=mTtDfKgLm54 "æˇąåēĻå­Ļäš įš„åŽ†å˛") -> đŸŽĨ į‚šå‡ģä¸Šå›žč§‚įœ‹č§†éĸ‘īŧšYann LeCun 在æœŦæŦĄčŽ˛åē§ä¸­čŽ¨čŽēæˇąåēĻå­Ļäš įš„åŽ†å˛ - ---- -## đŸš€æŒ‘æˆ˜ - -æˇąå…Ĩäē†č§Ŗčŋ™äē›åŽ†å˛æ—ļåˆģ之一īŧŒåšļ更多地äē†č§Ŗ厃äģŦčƒŒåŽįš„äēē。čŋ™é‡Œæœ‰čŽ¸å¤šåŧ•äēēå…Ĩ胜įš„äēēį‰ŠīŧŒæ˛Ąæœ‰ä¸€éĄšį§‘å­Ļ发įŽ°æ˜¯åœ¨æ–‡åŒ–įœŸįŠē中创造å‡ēæĨįš„。äŊ å‘įŽ°äē†äģ€äšˆīŧŸ - -## [č¯žåŽæĩ‹éĒŒ](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/4/) - -## 复䚠与č‡Ēå­Ļ - -äģĨ下是čĻč§‚įœ‹å’Œæ”ļåŦįš„节į›Žīŧš - -[čŋ™æ˜¯ Amy Boyd 莨čŽēäēēåˇĨæ™ēčƒŊčŋ›åŒ–įš„æ’­åŽĸ](http://runasradio.com/Shows/Show/739) - -[![Amy Boydįš„《äēēåˇĨæ™ēčƒŊå˛ã€‹](https://img.youtube.com/vi/EJt3_bFYKss/0.jpg)](https://www.youtube.com/watch?v=EJt3_bFYKss "Amy Boydįš„《äēēåˇĨæ™ēčƒŊå˛ã€‹") - -## äģģåŠĄ - -[创åģēæ—ļ间įēŋ](assignment.zh-cn.md) diff --git a/1-Introduction/2-history-of-ML/translations/README.zh-tw.md b/1-Introduction/2-history-of-ML/translations/README.zh-tw.md deleted file mode 100644 index 7c88c2ee..00000000 --- a/1-Introduction/2-history-of-ML/translations/README.zh-tw.md +++ /dev/null @@ -1,110 +0,0 @@ -# 抟器學įŋ’įš„æ­ˇå˛ - -![抟器學įŋ’æ­ˇå˛æĻ‚čŋ°](../../../sketchnotes/ml-history.png) -> äŊœč€… [Tomomi Imura](https://www.twitter.com/girlie_mac) -## [čĒ˛å‰æ¸Ŧ驗](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/3/) - -在æœŦčĒ˛ä¸­īŧŒæˆ‘們將čĩ°éŽæŠŸå™¨å­¸įŋ’å’ŒäēēåˇĨæ™ēčƒŊæ­ˇå˛ä¸Šįš„ä¸ģčĻčŖį¨‹įĸ‘。 - -äēēåˇĨæ™ēčƒŊīŧˆAIīŧ‰äŊœį‚ē一個領域įš„æ­ˇå˛čˆ‡æŠŸå™¨å­¸įŋ’įš„æ­ˇå˛äē¤įš”在一čĩˇīŧŒå› į‚ē支持抟器學įŋ’įš„įŽ—æŗ•å’Œč¨ˆįŽ—čƒŊ力įš„進æ­Ĩ推動äē†AIįš„į™ŧåą•ã€‚č¨˜äŊīŧŒé›–į„ļ這äē›é ˜åŸŸäŊœį‚ē不同į ”įŠļ領域在 20 世į´€ 50 åš´äģŖæ‰é–‹å§‹å…ˇéĢ”化īŧŒäŊ†é‡čĻįš„[įŽ—æŗ•ã€įĩąč¨ˆã€æ•¸å­¸ã€č¨ˆįŽ—å’ŒæŠ€čĄ“į™ŧįž](https://wikipedia.org/wiki/Timeline_of_machine_learning) čĻæ—Šæ–ŧ和重į–Šäē†é€™å€‹æ™‚äģŖ。 äē‹å¯Ļ上īŧŒ[數į™žåš´äž†](https://wikipedia.org/wiki/History_of_artificial_intelligence)äēē們一į›´åœ¨æ€č€ƒé€™äē›å•éĄŒīŧšæœŦæ–‡č¨ŽčĢ–äē†ã€Œæ€įļ­æŠŸå™¨ã€é€™ä¸€æĻ‚åŋĩįš„æ­ˇå˛įŸĨ識åŸēį¤Žã€‚ - -## ä¸ģčĻį™ŧįž - -- 1763, 1812 [č˛č‘‰æ–¯åŽšį†](https://wikipedia.org/wiki/Bayes%27_theorem) 及å…ļ前čēĢã€‚čŠ˛åŽšį†åŠå…ļ應į”¨æ˜¯æŽ¨į†įš„åŸēį¤ŽīŧŒæčŋ°äē†åŸēæ–ŧ先銗įŸĨ識įš„äē‹äģļį™ŧį”Ÿįš„æĻ‚įŽ‡ã€‚ -- 1805 [最小äēŒäš˜į†čĢ–](https://wikipedia.org/wiki/Least_squares)į”ąæŗ•åœ‹æ•¸å­¸åŽļ Adrien-Marie Legendre 提å‡ē。 äŊ å°‡åœ¨æˆ‘們įš„回歸喎元中äē†č§Ŗ這一į†čĢ–īŧŒåŽƒæœ‰åŠŠæ–ŧ數據æ“Ŧ合。 -- 1913 [éĻŦįˆžå¯å¤Ģ鏈](https://wikipedia.org/wiki/Markov_chain)äģĨäŋ„įž…斯數學åŽļ Andrey Markov įš„名字å‘Ŋ名īŧŒį”¨æ–ŧ描čŋ°åŸēæ–ŧ先前į‹€æ…‹įš„一įŗģ列可čƒŊäē‹äģļ。 -- 1957 [感įŸĨ器](https://wikipedia.org/wiki/Perceptron)是įžŽåœ‹åŋƒį†å­¸åŽļ Frank Rosenblatt į™ŧ明įš„一į¨Žįˇšæ€§åˆ†éĄžå™¨īŧŒæ˜¯æˇąåēĻå­¸įŋ’į™ŧåą•įš„åŸēį¤Žã€‚ -- 1967 [最čŋ‘é„°](https://wikipedia.org/wiki/Nearest_neighbor)是一į¨Žæœ€åˆč¨­č¨ˆį”¨æ–ŧæ˜ å°„čˇ¯įˇšįš„įŽ—æŗ•ã€‚ 在 ML 中īŧŒåŽƒį”¨æ–ŧæĒĸæ¸Ŧæ¨Ąåŧã€‚ -- 1970 [反向å‚ŗ播](https://wikipedia.org/wiki/Backpropagation)į”¨æ–ŧ訓įˇ´[前éĨ‹įĨžįļ“įļ˛įĩĄ](https://wikipedia.org/wiki/Feedforward_neural_network)。 -- 1982 [åžĒį’°įĨžįļ“įļ˛įĩĄ](https://wikipedia.org/wiki/Recurrent_neural_network) 是æēč‡Ēį”ĸį”Ÿæ™‚間圖įš„前éĨ‹įĨžįļ“įļ˛įĩĄįš„äēēåˇĨįĨžįļ“įļ˛įĩĄã€‚ - -✅ 做éģžčĒŋæŸĨ。在 ML 和 AI įš„æ­ˇå˛ä¸ŠīŧŒé‚„有å“Ēäē›æ—Ĩ期是重čĻįš„īŧŸ -## 1950: æœƒæ€č€ƒįš„抟器 - -Alan TuringīŧŒä¸€å€‹įœŸæ­Ŗ傑å‡ēįš„äēēīŧŒ[在 2019 åš´čĸĢå…ŦįœžæŠ•įĨ¨é¸å‡ē](https://wikipedia.org/wiki/Icons:_The_Greatest_Person_of_the_20th_Century) äŊœį‚ē 20 世į´€æœ€å‰å¤§įš„į§‘å­¸åŽļīŧŒäģ–čĒį‚ē有劊æ–ŧį‚ēã€Œæœƒæ€č€ƒįš„抟器」įš„æĻ‚åŋĩ打下åŸēį¤Žã€‚äģ–通過å‰ĩåģē [圖靈æ¸ŦčŠĻ](https://www.bbc.com/news/technology-18475646)來č§Ŗæąēåå°č€…å’Œäģ–č‡Ēåˇąå°é€™ä¸€æĻ‚åŋĩįš„įļ“éŠ—č­‰æ“šįš„éœ€æą‚īŧŒäŊ å°‡åœ¨æˆ‘們įš„ NLP čĒ˛į¨‹ä¸­é€˛čĄŒæŽĸį´ĸ。 - -## 1956: 達į‰ščŒ…斯夏å­Ŗį ”įŠļ項į›Ž - -「達į‰ščŒ…斯夏å­ŖäēēåˇĨæ™ēčƒŊį ”įŠļ項į›Žæ˜¯äēēåˇĨæ™ēčƒŊ領域įš„一個開å‰ĩ性äē‹äģļīŧŒã€æ­Ŗ是在這čŖīŧŒäēē們å‰ĩ造äē†ã€ŒäēēåˇĨæ™ēčƒŊã€ä¸€čŠžīŧˆ[來æē](https://250.dartmouth.edu/highlights/artificial-intelligence-ai-coined-dartmouth)īŧ‰ã€‚ - -> 原則上īŧŒå­¸įŋ’įš„每個斚éĸ或æ™ēčƒŊįš„äģģäŊ•å…ļäģ–į‰šåžéƒŊ可äģĨčĸĢį˛žįĸē地描čŋ°īŧŒäģĨč‡ŗæ–ŧ可äģĨį”¨æŠŸå™¨äž†æ¨Ąæ“Ŧ厃。 -éĻ–席į ”įŠļå“Ąã€æ•¸å­¸æ•™æŽˆ John McCarthy 希望「åŸēæ–ŧ這æ¨Ŗ一į¨ŽįŒœæƒŗīŧŒåŗå­¸įŋ’įš„每個斚éĸ或æ™ēčƒŊįš„äģģäŊ•å…ļäģ–į‰šåžåŽŸå‰‡ä¸ŠéƒŊ可äģĨåĻ‚æ­¤į˛žįĸē地描čŋ°īŧŒäģĨč‡ŗæ–ŧ可äģĨčŖŊ造å‡ē一č‡ēæŠŸå™¨äž†æ¨Ąæ“Ŧ厃。」 åƒčˆ‡č€…åŒ…æ‹ŦčŠ˛é ˜åŸŸįš„åĻ一äŊå‚‘å‡ēäēēį‰Š Marvin Minsky。 - -į ”č¨ŽæœƒčĸĢčĒį‚ēį™ŧčĩˇä¸Ļéŧ“å‹ĩäē†ä¸€äē›č¨ŽčĢ–īŧŒåŒ…æ‹Ŧ「įŦĻč™Ÿæ–šæŗ•įš„čˆˆčĩˇã€å°ˆč¨ģæ–ŧ有限領域įš„įŗģįĩąīŧˆæ—ŠæœŸå°ˆåŽļįŗģįĩąīŧ‰īŧŒäģĨ及æŧ”įššįŗģįĩąčˆ‡æ­¸į´įŗģįĩąįš„對比。」īŧˆ[來æē](https://wikipedia.org/wiki/Dartmouth_workshop)īŧ‰ã€‚ - -## 1956 - 1974: 「éģƒé‡‘æ­˛æœˆã€ - -åžž 20 世į´€ 50 åš´äģŖ到 70 åš´äģŖ中期īŧŒæ¨‚č§€æƒ…įˇ’éĢ˜æŧ˛īŧŒå¸Œæœ›äēēåˇĨæ™ēčƒŊčƒŊ夠č§Ŗæąēč¨ąå¤šå•éĄŒã€‚1967 åš´īŧŒMarvin Minsky č‡ĒäŋĄåœ°čĒĒīŧŒã€Œä¸€äģŖäēēäš‹å…§...å‰ĩ造『äēēåˇĨæ™ēčƒŊ』įš„å•éĄŒå°‡åž—åˆ°å¯ĻčŗĒ性įš„č§Ŗæąē。」īŧˆMinskyīŧŒMarvinīŧˆ1967īŧ‰īŧŒã€Šč¨ˆįŽ—īŧšæœ‰é™å’Œį„Ąé™æŠŸå™¨ã€‹īŧŒæ–°æž¤čĨŋåˇžæŠæ ŧäŧåžˇå…‹åˆŠå¤Ģ斯īŧšPrentice Hallīŧ‰ - -č‡Ēį„ļčĒžč¨€č™•į†į ”įŠļč“Ŧ勃į™ŧåą•īŧŒæœį´ĸčĸĢ提į…‰ä¸ĻčŽŠåž—æ›´åŠ åŧˇå¤§īŧŒå‰ĩ造äē†ã€ŒåžŽč§€ä¸–į•Œã€įš„æĻ‚åŋĩīŧŒåœ¨é€™å€‹æĻ‚åŋĩ中īŧŒį°Ąå–Žįš„äģģ務是į”¨į°Ąå–Žįš„čĒžč¨€æŒ‡äģ¤åŽŒæˆįš„。 - -這項į ”įŠļ垗到äē†æ”ŋåēœæŠŸæ§‹įš„充分čŗ‡åŠŠīŧŒåœ¨č¨ˆįŽ—å’ŒįŽ—æŗ•æ–šéĸ取垗äē†é€˛åą•īŧŒä¸Ļåģē造äē†æ™ēčƒŊ抟器įš„原型。å…ļ中一äē›æŠŸå™¨åŒ…æ‹Ŧīŧš - -* [抟器äēē Shakey](https://wikipedia.org/wiki/Shakey_the_robot)īŧŒäģ–們可äģĨã€Œč°æ˜Žåœ°ã€æ“į¸ąå’Œæąē厚åĻ‚äŊ•åŸˇčĄŒäģģ務。 - - ![Shakey, æ™ēčƒŊ抟器äēē](../images/shakey.jpg) - > 1972 åš´įš„ Shakey -* ElizaīŧŒä¸€å€‹æ—ŠæœŸįš„ã€ŒčŠå¤ŠæŠŸå™¨äēē」īŧŒå¯äģĨ與äēēäē¤čĢ‡ä¸Ļ充į•ļ原始įš„「æ˛ģį™‚å¸Ģ」。 äŊ å°‡åœ¨ NLP čĒ˛į¨‹ä¸­äē†č§Ŗ有關 Eliza įš„更多äŋĄæ¯ã€‚ - - ![Eliza, 抟器äēē](../images/eliza.png) - > Eliza įš„一個į‰ˆæœŦīŧŒä¸€å€‹čŠå¤ŠæŠŸå™¨äēē -* 「įŠæœ¨ä¸–į•Œã€æ˜¯ä¸€å€‹åžŽč§€ä¸–į•Œįš„䞋子īŧŒåœ¨é‚ŖčŖįŠæœ¨å¯äģĨ堆į–Šå’Œåˆ†éĄžīŧŒä¸Ļ且可äģĨæ¸ŦčŠĻ教抟器做å‡ēæąēį­–įš„å¯Ļ銗。 äŊŋį”¨ [SHRDLU](https://wikipedia.org/wiki/SHRDLU) į­‰åēĢ構åģēįš„éĢ˜į´šåŠŸčƒŊ有劊æ–ŧ推動čĒžč¨€č™•į†å‘前į™ŧåą•ã€‚ - - [![įŠæœ¨ä¸–į•Œčˆ‡ SHRDLU](https://img.youtube.com/vi/QAJz4YKUwqw/0.jpg)](https://www.youtube.com/watch?v=QAJz4YKUwqw "įŠæœ¨ä¸–į•Œčˆ‡SHRDLU") - - > đŸŽĨ éģžæ“Šä¸Šåœ–觀įœ‹čĻ–é ģīŧš įŠæœ¨ä¸–į•Œčˆ‡ SHRDLU -## 1974 - 1980: AI įš„寒å†Ŧ - -到äē† 20 世į´€ 70 åš´äģŖ中期īŧŒåžˆæ˜ŽéĄ¯čŖŊ造「æ™ēčƒŊ抟器」įš„垊雜性čĸĢäŊŽäŧ°äē†īŧŒč€Œä¸”č€ƒæ…Žåˆ°å¯į”¨įš„č¨ˆįŽ—čƒŊ力īŧŒåŽƒįš„前景čĸĢčĒ‡å¤§äē†ã€‚čŗ‡é‡‘枯įĢ­īŧŒå¸‚å ´äŋĄåŋƒæ”žįˇŠã€‚åŊąéŸŋäŋĄåŋƒįš„一äē›å•éĄŒåŒ…æ‹Ŧīŧš - -- **限čŖŊ**ã€‚č¨ˆįŽ—čƒŊ力å¤Ē有限äē† -- **įĩ„合įˆ†į‚¸**ã€‚éš¨č‘—å°č¨ˆįŽ—抟įš„čĻæą‚čļŠäž†čļŠéĢ˜īŧŒéœ€čĻč¨“įˇ´įš„參數數量呈指數į´šåĸžé•ˇīŧŒč€Œč¨ˆįŽ—čƒŊ力åģæ˛’æœ‰åšŗ行į™ŧåą•ã€‚ -- **įŧē䚏數據**。 įŧē䚏數據é˜ģį¤™äē†æ¸ŦčŠĻ、開į™ŧå’Œæ”šé€˛įŽ—æŗ•įš„過į¨‹ã€‚ -- **我們是åĻ在問æ­Ŗįĸēįš„å•éĄŒīŧŸ**。 čĸĢ問到įš„å•éĄŒäšŸé–‹å§‹å—åˆ°čŗĒį–‘。 į ”įŠļäēēå“Ąé–‹å§‹å°äģ–們įš„æ–šæŗ•æå‡ēæ‰ščŠ•īŧš - - 圖靈æ¸ŦčŠĻ受到čŗĒį–‘įš„æ–šæŗ•äš‹ä¸€æ˜¯ã€Œä¸­åœ‹æˆŋ間į†čĢ–」īŧŒčŠ˛į†čĢ–čĒį‚ēīŧŒã€Œå°æ•¸å­—č¨ˆįŽ—æŠŸé€˛čĄŒįˇ¨į¨‹å¯čƒŊäŊŋå…ļįœ‹čĩˇäž†čƒŊį†č§ŖčĒžč¨€īŧŒäŊ†ä¸čƒŊį”ĸį”ŸįœŸæ­Ŗįš„į†č§Ŗ。」 ([來æē](https://plato.stanford.edu/entries/chinese-room/)) - - 將「æ˛ģį™‚å¸Ģ」ELIZA 這æ¨Ŗįš„äēēåˇĨæ™ēčƒŊåŧ•å…Ĩį¤žæœƒįš„å€Ģį†å—到äē†æŒ‘戰。 - -čˆ‡æ­¤åŒæ™‚īŧŒå„į¨ŽäēēåˇĨæ™ēčƒŊ學洞開始åŊĸ成。 在 [「scruffy」 與 「neat AI」](https://wikipedia.org/wiki/Neats_and_scruffies) 之間åģēįĢ‹äē†äēŒåˆ†æŗ•ã€‚ _Scruffy_ å¯Ļ銗厤對į¨‹åēé€˛čĄŒäē†æ•¸å°æ™‚įš„čĒŋ整īŧŒį›´åˆ°į˛åž—所需įš„įĩæžœã€‚ _Neat_ å¯Ļ銗厤「專č¨ģæ–ŧ邏čŧ¯å’ŒåŊĸåŧå•éĄŒįš„č§Ŗæąē」。 ELIZA 和 SHRDLU 是įœžæ‰€å‘¨įŸĨįš„ _scruffy_ įŗģįĩąã€‚ 在 1980 åš´äģŖīŧŒéš¨č‘—äŊŋ ML įŗģįĩąå¯é‡įžįš„éœ€æą‚å‡ēįžīŧŒ_neat_ æ–šæŗ•é€æŧ¸čĩ°ä¸Šå‰æ˛ŋīŧŒå› į‚ēå…ļįĩæžœæ›´æ˜“æ–ŧč§Ŗ釋。 - -## 1980s 專åŽļįŗģįĩą - -éš¨č‘—é€™å€‹é ˜åŸŸįš„į™ŧåą•īŧŒåŽƒå°å•†æĨ­įš„åĨŊč™•čŽŠåž—čļŠäž†čļŠæ˜ŽéĄ¯īŧŒåœ¨ 20 世į´€ 80 åš´äģŖīŧŒã€Žå°ˆåŽļįŗģįĩąã€äšŸé–‹å§‹åģŖæŗ›æĩčĄŒčĩˇäž†ã€‚「專åŽļįŗģįĩąæ˜¯éĻ–扚įœŸæ­Ŗ成功įš„äēēåˇĨæ™ēčƒŊ (AI) čģŸäģļåŊĸåŧäš‹ä¸€ã€‚」 īŧˆ[來æē](https://wikipedia.org/wiki/Expert_system)īŧ‰ã€‚ - -這į¨ŽéĄžåž‹įš„įŗģįĩąå¯Ļéš›ä¸Šæ˜¯æˇˇåˆįŗģįĩąīŧŒéƒ¨åˆ†į”ąåŽšįžŠæĨ­å‹™éœ€æą‚įš„čĻå‰‡åŧ•æ“Žå’ŒåˆŠį”¨čĻå‰‡įŗģįĩąæŽ¨æ–ˇæ–°äē‹å¯Ļįš„推į†åŧ•æ“Žįĩ„成。 - -在這個時äģŖīŧŒįĨžįļ“įļ˛įĩĄäšŸčļŠäž†čļŠå—到重čĻ–。 - -## 1987 - 1993: AI įš„å†ˇéœæœŸ - -專æĨ­įš„å°ˆåŽļįŗģįĩąįĄŦäģļįš„æŋ€åĸžé€ æˆäē†éŽæ–ŧ專æĨ­åŒ–įš„不嚸垌果。個äēēé›ģč…Ļįš„čˆˆčĩˇäšŸčˆ‡é€™äē›å¤§åž‹ã€å°ˆæĨ­åŒ–、集中化įŗģįĩąåą•é–‹äē†įĢļįˆ­ã€‚č¨ˆįŽ—抟įš„åšŗæ°‘åŒ–åˇ˛įļ“開始īŧŒåŽƒæœ€įĩ‚į‚ē大數據įš„įžäģŖįˆ†į‚¸é‹Ēåšŗäē†é“čˇ¯ã€‚ - -## 1993 - 2011 - -這個時äģŖčĻ‹č­‰äē†ä¸€å€‹æ–°įš„時äģŖīŧŒML 和 AI čƒŊ夠č§Ŗæąē旊期į”ąæ–ŧįŧēäšæ•¸æ“šå’Œč¨ˆįŽ—čƒŊåŠ›č€Œå°Žč‡´įš„一äē›å•éĄŒã€‚數據量開始čŋ…速åĸžåŠ īŧŒčŽŠåž—čļŠäž†čļŠåģŖæŗ›īŧŒį„ĄčĢ–åĨŊåŖžīŧŒå°¤å…ļ是 2007 åš´åˇĻåŗæ™ēčƒŊ手抟įš„å‡ēįžīŧŒč¨ˆįŽ—čƒŊ力呈指數į´šåĸžé•ˇīŧŒįŽ—æŗ•äšŸéš¨äš‹į™ŧåą•ã€‚é€™å€‹é ˜åŸŸé–‹å§‹čŽŠåž—æˆį†ŸīŧŒå› į‚ē過åŽģé‚Ŗäē›éš¨åŋƒæ‰€æŦ˛įš„æ—Ĩå­é–‹å§‹å…ˇéĢ”化į‚ē一į¨ŽįœŸæ­Ŗįš„į´€åž‹ã€‚ - -## įžåœ¨ - -äģŠå¤ŠīŧŒæŠŸå™¨å­¸įŋ’å’ŒäēēåˇĨæ™ēčƒŊåšžäšŽč§¸åŠæˆ‘å€‘į”Ÿæ´ģįš„每一個部分。這個時äģŖčĻæą‚äģ”į´°äē†č§Ŗ這äē›įŽ—æŗ•å°äēē類į”Ÿæ´ģįš„éĸ¨éšĒ和æŊ›åœ¨åŊąéŸŋ。æ­ŖåĻ‚垎čģŸįš„ Brad Smith æ‰€č¨€īŧŒã€ŒäŋĄæ¯æŠ€čĄ“åŧ•į™ŧįš„å•éĄŒč§¸åŠéšąį§å’Œč¨€čĢ–č‡Ēį”ąį­‰åŸēæœŦäēēæŦŠäŋč­ˇįš„æ ¸åŋƒã€‚這äē›å•éĄŒåŠ é‡äē†čŖŊ造這äē›į”ĸ品įš„į§‘技å…Ŧ司įš„č˛Ŧäģģ。在我們įœ‹äž†īŧŒåŽƒå€‘é‚„å‘ŧįą˛æ”ŋåēœé€˛čĄŒæˇąæ€į†Ÿæ…Žįš„į›ŖįŽĄīŧŒä¸Ļ圍įšžå¯æŽĨ受įš„į”¨é€”čŖŊ厚čĻį¯„」īŧˆ[來æē](https://www.technologyreview.com/2019/12/18/102365/the-future-of-ais-impact-on-society/)īŧ‰ã€‚ - -æœĒ來įš„情æŗé‚„æœ‰åž…č§€å¯ŸīŧŒäŊ†äē†č§Ŗ這äē›č¨ˆįŽ—抟įŗģįĩąäģĨåŠåŽƒå€‘é‹čĄŒįš„čģŸäģļ和įŽ—æŗ•æ˜¯åžˆé‡čĻįš„。我們希望這門čĒ˛į¨‹čƒŊåšĢ劊äŊ æ›´åĨŊįš„į†č§ŖīŧŒäģĨäžŋäŊ č‡Ēåˇąæąē厚。 - -[![æˇąåēĻå­¸įŋ’įš„æ­ˇå˛](https://img.youtube.com/vi/mTtDfKgLm54/0.jpg)](https://www.youtube.com/watch?v=mTtDfKgLm54 "æˇąåēĻå­¸įŋ’įš„æ­ˇå˛") -> đŸŽĨ éģžæ“Šä¸Šåœ–觀įœ‹čĻ–é ģīŧšYann LeCun 在æœŦæŦĄčŦ›åē§ä¸­č¨ŽčĢ–æˇąåēĻå­¸įŋ’įš„æ­ˇå˛ ---- -## đŸš€æŒ‘æˆ° - -æˇąå…Ĩäē†č§Ŗ這äē›æ­ˇå˛æ™‚åˆģ之一īŧŒä¸Ļ更多地äē†č§ŖåŽƒå€‘čƒŒåžŒįš„äēē。這čŖæœ‰č¨ąå¤šåŧ•äēēå…Ĩ勝įš„äēēį‰ŠīŧŒæ˛’有一項į§‘å­¸į™ŧįžæ˜¯åœ¨æ–‡åŒ–įœŸįŠē中å‰ĩ造å‡ē來įš„。äŊ į™ŧįžäē†äģ€éēŊīŧŸ - -## [čĒ˛åžŒæ¸Ŧ驗](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/4/) - -## 垊įŋ’čˆ‡č‡Ēå­¸ - -äģĨ下是čĻč§€įœ‹å’Œæ”ļčŊįš„į¯€į›Žīŧš - -[這是 Amy Boyd 討čĢ–äēēåˇĨæ™ēčƒŊé€˛åŒ–įš„æ’­åŽĸ](http://runasradio.com/Shows/Show/739) - -[![Amy Boydįš„《äēēåˇĨæ™ēčƒŊå˛ã€‹](https://img.youtube.com/vi/EJt3_bFYKss/0.jpg)](https://www.youtube.com/watch?v=EJt3_bFYKss "Amy Boydįš„《äēēåˇĨæ™ēčƒŊå˛ã€‹") - -## äģģ務 - -[å‰ĩåģē時間įˇš](assignment.zh-tw.md) \ No newline at end of file diff --git a/1-Introduction/2-history-of-ML/translations/assignment.es.md b/1-Introduction/2-history-of-ML/translations/assignment.es.md deleted file mode 100644 index 504796e7..00000000 --- a/1-Introduction/2-history-of-ML/translations/assignment.es.md +++ /dev/null @@ -1,11 +0,0 @@ -# Crea una línea de tiempo - -## Instrucciones - -Usando [este repositorio](https://github.com/Digital-Humanities-Toolkit/timeline-builder), crea una línea temporal de algunos aspectos de la historia de los algoritmos, matemÃĄticas, estadística, Inteligencia Artificial (AI), Aprendizaje AutomÃĄtico (ML), o una combinaciÃŗn de todos estos. Te puedes enfocar en una persona, una idea o período largo de tiempo de pensamiento. AsegÃērate de agregar elementos multimedia. - -## RÃēbrica - -| Criterio | Ejemplar | Adecuado | Necesita mejorar | -| -------- | ------------------------------------------------- | --------------------------------------- | ---------------------------------------------------------------- | -| | Una línea de tiempo desplegada es representada como una pÃĄgina de Github | El cÃŗdigo estÃĄ incompleto y no fue desplegado | La línea del tiempo estÃĄ incompleta, sin buena investigaciÃŗn y sin desplegar | diff --git a/1-Introduction/2-history-of-ML/translations/assignment.fr.md b/1-Introduction/2-history-of-ML/translations/assignment.fr.md deleted file mode 100644 index c562516e..00000000 --- a/1-Introduction/2-history-of-ML/translations/assignment.fr.md +++ /dev/null @@ -1,11 +0,0 @@ -# CrÊer une frise chronologique - -## Instructions - -Utiliser [ce repo](https://github.com/Digital-Humanities-Toolkit/timeline-builder), crÊer une frise chronologique de certains aspects de l'histoire des algorithmes, des mathÊmatiques, des statistiques, de l'IA ou du machine learning, ou une combinaison de ceux-ci. Vous pouvez vous concentrer sur une personne, une idÊe ou une longue pÊriode d'innovations. Assurez-vous d'ajouter des ÊlÊments multimÊdias. - -## Rubrique - -| Critères | Exemplaire | AdÊquate | A amÊliorer | -| -------- | ---------------------------------------------------------------- | ------------------------------------ | ------------------------------------------------------------------ | -| | Une chronologie dÊployÊe est prÊsentÊe sous forme de page GitHub | Le code est incomplet et non dÊployÊ | La chronologie est incomplète, pas bien recherchÊe et pas dÊployÊe | diff --git a/1-Introduction/2-history-of-ML/translations/assignment.id.md b/1-Introduction/2-history-of-ML/translations/assignment.id.md deleted file mode 100644 index 0ee7c009..00000000 --- a/1-Introduction/2-history-of-ML/translations/assignment.id.md +++ /dev/null @@ -1,11 +0,0 @@ -# Membuat sebuah *timeline* - -## Instruksi - -Menggunakan [repo ini](https://github.com/Digital-Humanities-Toolkit/timeline-builder), buatlah sebuah *timeline* dari beberapa aspek sejarah algoritma, matematika, statistik, AI, atau ML, atau kombinasi dari semuanya. Kamu dapat fokus pada satu orang, satu ide, atau rentang waktu pemikiran yang panjang. Pastikan untuk menambahkan elemen multimedia. - -## Rubrik - -| Kriteria | Sangat Bagus | Cukup | Perlu Peningkatan | -| -------- | ------------------------------------------------- | --------------------------------------- | ---------------------------------------------------------------- | -| | *Timeline* yang dideploy disajikan sebagai halaman GitHub | Kode belum lengkap dan belum dideploy | *Timeline* belum lengkap, belum diriset dengan baik dan belum dideploy | \ No newline at end of file diff --git a/1-Introduction/2-history-of-ML/translations/assignment.it.md b/1-Introduction/2-history-of-ML/translations/assignment.it.md deleted file mode 100644 index 4de7ed14..00000000 --- a/1-Introduction/2-history-of-ML/translations/assignment.it.md +++ /dev/null @@ -1,11 +0,0 @@ -# Creare una sequenza temporale - -## Istruzioni - -Usando [questo repository](https://github.com/Digital-Humanities-Toolkit/timeline-builder), si crei una sequenza temporale di alcuni aspetti della storia di algoritmi, matematica, statistica, AI o ML, o una combinazione di questi. Ci si puÃ˛ concentrare su una persona, un'idea o un lungo lasso di tempo di pensiero. Ci si assicuri di aggiungere elementi multimediali. - -## Rubrica - -| Criteri | Ottimo | Adeguato | Necessita miglioramento | -| -------- | ------------------------------------------------- | --------------------------------------- | ---------------------------------------------------------------- | -| | Una sequenza temporale distribuita viene presentata come una pagina GitHub | Il codice è incompleto e non è stato distribuito | La sequenza temporale è incompleta, non ben studiata e non implementata | diff --git a/1-Introduction/2-history-of-ML/translations/assignment.ja.md b/1-Introduction/2-history-of-ML/translations/assignment.ja.md deleted file mode 100644 index f5f78799..00000000 --- a/1-Introduction/2-history-of-ML/translations/assignment.ja.md +++ /dev/null @@ -1,11 +0,0 @@ -# åš´čĄ¨ã‚’äŊœæˆã™ã‚‹ - -## 指į¤ē - -[こぎãƒĒポジトãƒĒ](https://github.com/Digital-Humanities-Toolkit/timeline-builder) をäŊŋãŖãĻ、ã‚ĸãƒĢゴãƒĒã‚ēムãƒģ数å­Ļãƒģįĩąč¨ˆå­ĻãƒģäēēåˇĨįŸĨčƒŊãƒģ抟æĸ°å­Ļįŋ’、ぞたはこれらぎįĩ„ãŋ合わせãĢ寞しãĻã€æ­´å˛ãŽã˛ã¨ã¤ãŽå´éĸãĢé–ĸã™ã‚‹åš´čĄ¨ã‚’äŊœæˆã—ãĻください。į„Ļį‚šã‚’åŊ“ãĻã‚‹ãŽã¯ã€ã˛ã¨ã‚ŠãŽäēēį‰Šãƒģã˛ã¨ã¤ãŽã‚ĸイデã‚Ŗã‚ĸãƒģé•ˇæœŸé–“ãĢわたる思æƒŗぎいずれぎもぎでも構いぞせん。マãƒĢãƒãƒĄãƒ‡ã‚Ŗã‚ĸぎčĻį´ ã‚’åŋ…ず加えるようãĢしãĻください。 - -## 評価åŸēæē– - -| åŸēæē– | æ¨Ąį¯„įš„ | 十分 | čĻæ”šå–„ | -| ---- | -------------------------------------- | ------------------------------------ | ------------------------------------------------------------ | -| | GitHub page ãĢåš´čĄ¨ãŒãƒ‡ãƒ—ãƒ­ã‚¤ã•ã‚ŒãĻいる | ã‚ŗãƒŧドがæœĒ厌成でデプロイされãĻいãĒい | åš´čĄ¨ãŒæœĒ厌成で、十分ãĢčĒŋæŸģされãĻおらず、デプロイされãĻいãĒい | diff --git a/1-Introduction/2-history-of-ML/translations/assignment.ko.md b/1-Introduction/2-history-of-ML/translations/assignment.ko.md deleted file mode 100644 index 7d3d2fa7..00000000 --- a/1-Introduction/2-history-of-ML/translations/assignment.ko.md +++ /dev/null @@ -1,11 +0,0 @@ -# 타ėž„ëŧė¸ė„ 만들ė–´ 봅ė‹œë‹¤ - -## ė„¤ëĒ… - -ė´ [ė €ėžĨė†Œ(repository)](https://github.com/Digital-Humanities-Toolkit/timeline-builder)ëĨŧ ė‚ŦėšŠí•´ ė•Œęŗ ëĻŦėĻ˜, ėˆ˜í•™, í†ĩęŗ„, ė¸ęŗĩė§€ëŠĨ 또는 머ė‹ ëŸŦ닝 ė¤‘ 한 가ė§€ ė´ėƒė˜ ė—°í˜ė‚ŦëĨŧ ėĄ°í•Ší•˜ė—Ŧ 타ėž„ëŧė¸ė„ 만들ė–´ ëŗ´ė„¸ėš”. 한 ëĒ…ė˜ ė¸ëŦŧ 또는 한 가ė§€ ė•„ė´ë””ė–´ëĨŧ ė§‘ė¤‘ė ėœŧ로 다ëŖ¨ė…”도 되ęŗ , ė—ŦëŸŦ ė„¸ę¸°ė— 깸ėšœ 긴 ė—°í˜ė‚ŦëĨŧ 다ëŖ¨ė‹œëŠ” 것도 ėĸ‹ėŠĩ니다. 각 ė‚Ŧęą´ęŗŧ 관련된 늀티미디ė–´ë„ 타ėž„ëŧė¸ė— ėļ”가해 ëŗ´ė‹œę¸° 바랍니다. - -## 평가기ė¤€í‘œ - -| 평가기ė¤€ | ëĒ¨ë˛” | ė ė ˆ | í–Ĩėƒ 필ėš” | -| -------- | ----------------------------------------- | -------------------- | --------------------------------- | -| | 깃허브(GitHub) 페ė´ė§€ė— ė™„ė„ąëœ 타ėž„ëŧė¸ ęŗĩ개 | ėŊ”ë“œ 미ė™„ė„ą 및 미배íŦ | 타ėž„ëŧė¸ ėĄ°ė‚Ŧ ë¯¸íĄ, 미ė™„ė„ą 및 미배íŦ | diff --git a/1-Introduction/2-history-of-ML/translations/assignment.pt-br.md b/1-Introduction/2-history-of-ML/translations/assignment.pt-br.md deleted file mode 100644 index 9e1e6ce1..00000000 --- a/1-Introduction/2-history-of-ML/translations/assignment.pt-br.md +++ /dev/null @@ -1,11 +0,0 @@ -# Crie uma linha do tempo - -## InstruçÃĩes - -Usando [este repositÃŗrio](https://github.com/Digital-Humanities-Toolkit/timeline-builder), crie uma linha do tempo de algum aspecto da histÃŗria de algoritmos, matemÃĄtica, estatística, AI ou ML, ou uma combinaçÃŖo de esses. VocÃĒ pode se concentrar em uma pessoa, uma ideia ou um longo período de pensamento. Certifique-se de adicionar elementos de multimídia. - -## Rubrica - -| CritÊrios | Exemplar | Adequado | Precisa Melhorar | -| -------- | ------------------------------------------------- | --------------------------------------- | ---------------------------------------------------------------- | -| | Um cronograma implantado Ê apresentado como uma pÃĄgina do GitHub (GitHub Page) | O cÃŗdigo estÃĄ incompleto e nÃŖo implementado | O cronograma estÃĄ incompleto, nÃŖo foi bem pesquisado e nÃŖo implantado | \ No newline at end of file diff --git a/1-Introduction/2-history-of-ML/translations/assignment.ru.md b/1-Introduction/2-history-of-ML/translations/assignment.ru.md deleted file mode 100644 index 7ee1b620..00000000 --- a/1-Introduction/2-history-of-ML/translations/assignment.ru.md +++ /dev/null @@ -1,11 +0,0 @@ -# ХОСдаКŅ‚Đĩ вŅ€ĐĩĐŧĐĩĐŊĐŊŅƒŅŽ ŅˆĐēĐ°ĐģŅƒ - -## ИĐŊŅŅ‚Ņ€ŅƒĐēŅ†Đ¸Đ¸ - -ИŅĐŋĐžĐģŅŒĐˇŅƒŅ [ŅŅ‚ĐžŅ‚ Ņ€ĐĩĐŋОСиŅ‚ĐžŅ€Đ¸Đš](https://github.com/Digital-Humanities-Toolkit/timeline-builder), ŅĐžĐˇĐ´Đ°ĐšŅ‚Đĩ вŅ€ĐĩĐŧĐĩĐŊĐŊŅƒŅŽ ŅˆĐēĐ°ĐģŅƒ ĐēĐ°ĐēĐžĐŗĐž-ĐģийО Đ°ŅĐŋĐĩĐēŅ‚Đ° иŅŅ‚ĐžŅ€Đ¸Đ¸ Đ°ĐģĐŗĐžŅ€Đ¸Ņ‚ĐŧОв, ĐŧĐ°Ņ‚ĐĩĐŧĐ°Ņ‚иĐēи, ŅŅ‚Đ°Ņ‚иŅŅ‚иĐēи, иŅĐēŅƒŅŅŅ‚вĐĩĐŊĐŊĐžĐŗĐž иĐŊŅ‚ĐĩĐģĐģĐĩĐēŅ‚Đ° иĐģи ML иĐģи иŅ… ĐēĐžĐŧйиĐŊĐ°Ņ†Đ¸Đ¸. ВŅ‹ ĐŧĐžĐļĐĩŅ‚Đĩ ŅĐžŅŅ€ĐĩĐ´ĐžŅ‚ĐžŅ‡Đ¸Ņ‚ŅŒŅŅ ĐŊĐ° ОдĐŊĐžĐŧ Ņ‡ĐĩĐģОвĐĩĐēĐĩ, ОдĐŊОК идĐĩĐĩ иĐģи ĐŊĐ° Đ´ĐģиŅ‚ĐĩĐģŅŒĐŊĐžĐŧ ĐŋŅ€ĐžĐŧĐĩĐļŅƒŅ‚ĐēĐĩ вŅ€ĐĩĐŧĐĩĐŊи. ОбŅĐˇĐ°Ņ‚ĐĩĐģŅŒĐŊĐž дОйавŅŒŅ‚Đĩ ĐŧŅƒĐģŅŒŅ‚иĐŧĐĩдиКĐŊŅ‹Đĩ ŅĐģĐĩĐŧĐĩĐŊŅ‚Ņ‹. - -## Đ ŅƒĐąŅ€Đ¸ĐēĐ° - -| КŅ€Đ¸Ņ‚ĐĩŅ€Đ¸Đ¸ | ОбŅ€Đ°ĐˇŅ†ĐžĐ˛Ņ‹Đš | АдĐĩĐēваŅ‚ĐŊŅ‹Đš | НŅƒĐļĐ´Đ°ĐĩŅ‚ŅŅ в ŅƒĐģŅƒŅ‡ŅˆĐĩĐŊии | -| -------- | ------------------------------------------------- | --------------------------------------- | ---------------------------------------------------------------- | -| | РаСвĐĩŅ€ĐŊŅƒŅ‚Đ°Ņ вŅ€ĐĩĐŧĐĩĐŊĐŊĐ°Ņ ŅˆĐēĐ°ĐģĐ° ĐŋŅ€ĐĩĐ´ŅŅ‚авĐģĐĩĐŊĐ° в видĐĩ ŅŅ‚Ņ€Đ°ĐŊиŅ†Ņ‹ GitHub | Код ĐŊĐĩĐŋĐžĐģĐžĐŊ и ĐŊĐĩ Ņ€Đ°ĐˇĐ˛ĐĩŅ€ĐŊŅƒŅ‚ | ВŅ€ĐĩĐŧĐĩĐŊĐŊĐ°Ņ ŅˆĐēĐ°ĐģĐ° ĐŊĐĩĐŋĐžĐģĐŊĐ°Ņ, ĐŊĐĩĐ´ĐžŅŅ‚Đ°Ņ‚ĐžŅ‡ĐŊĐž иСŅƒŅ‡ĐĩĐŊĐ° и ĐŊĐĩ Ņ€Đ°ĐˇĐ˛ĐĩŅ€ĐŊŅƒŅ‚Đ° | \ No newline at end of file diff --git a/1-Introduction/2-history-of-ML/translations/assignment.tr.md b/1-Introduction/2-history-of-ML/translations/assignment.tr.md deleted file mode 100644 index f0e87763..00000000 --- a/1-Introduction/2-history-of-ML/translations/assignment.tr.md +++ /dev/null @@ -1,11 +0,0 @@ -# Bir zaman çizelgesi oluşturun - -## Talimatlar - -[Bu repoyu](https://github.com/Digital-Humanities-Toolkit/timeline-builder) kullanarak; algoritmalarÄąn, matematiğin, istatistiğin, AI veya ML'in veya bunlarÄąn bir kombinasyonunun tarihinin bazÄą yÃļnlerinin bir zaman çizelgesini oluşturun. Bir kişiye, bir fikre veya bir dÃŧşÃŧncenin uzun bir zamanÄąna odaklanabilirsiniz. Multimedya Ãļğeleri eklediğinizden emin olun. - -## Değerlendirme Listesi - -| | Takdir edilesi | Yeterli | Ä°yileştirilmesi LazÄąm | -| -------- | ------------------------------------------------- | --------------------------------------- | ---------------------------------------------------------------- | -| Kriterler | Zaman çizelgesi bir GitHub sayfasÄą olarak yayÄąnlanmÄąÅŸ | Kod eksik ve henÃŧz yayÄąnlanmamÄąÅŸ | Zaman çizelgesi eksik, iyi araştÄąrÄąlmamÄąÅŸ ve yayÄąnlanmamÄąÅŸ | \ No newline at end of file diff --git a/1-Introduction/2-history-of-ML/translations/assignment.zh-cn.md b/1-Introduction/2-history-of-ML/translations/assignment.zh-cn.md deleted file mode 100644 index adf3ee15..00000000 --- a/1-Introduction/2-history-of-ML/translations/assignment.zh-cn.md +++ /dev/null @@ -1,11 +0,0 @@ -# åģēįĢ‹ä¸€ä¸Ēæ—ļ间čŊ´ - -## č¯´æ˜Ž - -äŊŋį”¨čŋ™ä¸Ē [äģ“åē“](https://github.com/Digital-Humanities-Toolkit/timeline-builder)īŧŒåˆ›åģē一ä¸Ēå…ŗäēŽįŽ—æŗ•ã€æ•°å­Ļ、įģŸčŽĄå­Ļ、äēēåˇĨæ™ēčƒŊ、æœē器å­Ļäš įš„某ä¸Ēæ–šéĸæˆ–č€…å¯äģĨįģŧ合多ä¸ĒäģĨ上å­Ļį§‘æĨčŽ˛ã€‚äŊ å¯äģĨį€é‡äģ‹įģæŸä¸ĒäēēīŧŒæŸä¸Ēæƒŗæŗ•īŧŒæˆ–者一ä¸Ēįģäš…不衰įš„思æƒŗã€‚č¯ˇįĄŽäŋæˇģ加äē†å¤šåĒ’äŊ“å…ƒį´ åœ¨äŊ įš„æ—ļ间įēŋ中。 - -## č¯„åˆ¤æ ‡å‡† - -| 标准 | äŧ˜į§€ | 中规中įŸŠ | äģéœ€åŠĒ力 | -| ------------ | ---------------------------------- | ---------------------- | ------------------------------------------ | -| | 有一ä¸Ēį”¨ GitHub page åą•į¤ēįš„ timeline | äģŖį čŋ˜ä¸åŽŒæ•´åšļä¸”æ˛Ąæœ‰éƒ¨įŊ˛ | æ—ļ间įēŋ不厌整īŧŒæ˛Ąæœ‰įģčŋ‡å……分įš„į ”įŠļīŧŒåšļä¸”æ˛Ąæœ‰éƒ¨įŊ˛ | diff --git a/1-Introduction/2-history-of-ML/translations/assignment.zh-tw.md b/1-Introduction/2-history-of-ML/translations/assignment.zh-tw.md deleted file mode 100644 index f372e6ae..00000000 --- a/1-Introduction/2-history-of-ML/translations/assignment.zh-tw.md +++ /dev/null @@ -1,12 +0,0 @@ - -# åģēįĢ‹ä¸€å€‹æ™‚é–“čģ¸ - -## čĒĒ明 - -äŊŋį”¨é€™å€‹ [倉åēĢ](https://github.com/Digital-Humanities-Toolkit/timeline-builder)īŧŒå‰ĩåģē一個關æ–ŧįŽ—æŗ•ã€æ•¸å­¸ã€įĩąč¨ˆå­¸ã€äēēåˇĨæ™ēčƒŊ、抟器學įŋ’įš„某個斚éĸæˆ–č€…å¯äģĨįļœåˆå¤šå€‹äģĨ上學į§‘䞆čŦ›ã€‚äŊ å¯äģĨ著重äģ‹į´šæŸå€‹äēēīŧŒæŸå€‹æƒŗæŗ•īŧŒæˆ–č€…ä¸€å€‹įļ“äš…ä¸čĄ°įš„思æƒŗ。čĢ‹įĸēäŋæˇģ加äē†å¤šåĒ’éĢ”å…ƒį´ åœ¨äŊ įš„時間įˇšä¸­ã€‚ - -## čŠ•åˆ¤æ¨™æē– - -| 標æē– | å„Ēį§€ | 中čĻä¸­įŸŠ | äģéœ€åŠĒ力 | -| ------------ | ---------------------------------- | ---------------------- | ------------------------------------------ | -| | 有一個į”¨ GitHub page åą•į¤ēįš„ timeline | äģŖįĸŧ還不厌整ä¸Ļä¸”æ˛’æœ‰éƒ¨įŊ˛ | 時間įˇšä¸åŽŒæ•´īŧŒæ˛’有įļ“過充分įš„į ”įŠļīŧŒä¸Ļä¸”æ˛’æœ‰éƒ¨įŊ˛ | \ No newline at end of file diff --git a/1-Introduction/3-fairness/README.md b/1-Introduction/3-fairness/README.md deleted file mode 100644 index 240181a8..00000000 --- a/1-Introduction/3-fairness/README.md +++ /dev/null @@ -1,158 +0,0 @@ -# Building Machine Learning solutions with responsible AI - -![Summary of responsible AI in Machine Learning in a sketchnote](../../sketchnotes/ml-fairness.png) -> Sketchnote by [Tomomi Imura](https://www.twitter.com/girlie_mac) - -## [Pre-lecture quiz](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/5/) - -## Introduction - -In this curriculum, you will start to discover how machine learning can and is impacting our everyday lives. Even now, systems and models are involved in daily decision-making tasks, such as health care diagnoses, loan approvals or detecting fraud. So, it is important that these models work well to provide outcomes that are trustworthy. Just as any software application, AI systems are going to miss expectations or have an undesirable outcome. That is why it is essential to be about to understand and explain the behavior of an AI model. - -Imagine what can happen when the data you are using to build these models lacks certain demographics, such as race, gender, political view, religion, or disproportionally represents such demographics. What about when the model’s output is interpreted to favor some demographic? What is the consequence for the application? In addition, what happens when the model has an adverse outcome and is harmful to people? Who is accountable for the AI systems behavior? These are some questions we will explore in this curriculum. - -In this lesson, you will: - -- Raise your awareness of the importance of fairness in machine learning and fairness-related harms. -- Become familiar with the practice of exploring outliers and unusual scenarios to ensure reliability and safety -- Gain understanding on the need to empower everyone by designing inclusive systems -- Explore how vital it is to protect privacy and security of data and people -- See the importance of having a glass box approach to explain the behavior of AI models -- Be mindful of how accountability is essential to build trust in AI systems - -## Prerequisite - -As a prerequisite, please take the "Responsible AI Principles" Learn Path and watch the video below on the topic: - -Learn more about Responsible AI by following this [Learning Path](https://docs.microsoft.com/learn/modules/responsible-ai-principles/?WT.mc_id=academic-77952-leestott) - -[![Microsoft's Approach to Responsible AI](https://img.youtube.com/vi/dnC8-uUZXSc/0.jpg)](https://youtu.be/dnC8-uUZXSc "Microsoft's Approach to Responsible AI") - -> đŸŽĨ Click the image above for a video: Microsoft's Approach to Responsible AI - -## Fairness - -AI systems should treat everyone fairly and avoid affecting similar groups of people in different ways. For example, when AI systems provide guidance on medical treatment, loan applications, or employment, they should make the same recommendations to everyone with similar symptoms, financial circumstances, or professional qualifications. Each of us as humans carries around inherited biases that affect our decisions and actions. These biases can be evident in the data that we use to train AI systems. Such manipulation can sometimes happen unintentionally. It is often difficult to consciously know when you are introducing bias in data. - -**“Unfairness”** encompasses negative impacts, or “harms”, for a group of people, such as those defined in terms of race, gender, age, or disability status. The main fairness-related harms can be classified as: - -- **Allocation**, if a gender or ethnicity for example is favored over another. -- **Quality of service**. If you train the data for one specific scenario but reality is much more complex, it leads to a poor performing service. For instance, a hand soap dispenser that could not seem to be able to sense people with dark skin. [Reference](https://gizmodo.com/why-cant-this-soap-dispenser-identify-dark-skin-1797931773) -- **Denigration**. To unfairly criticize and label something or someone. For example, an image labeling technology infamously mislabeled images of dark-skinned people as gorillas. -- **Over- or under- representation**. The idea is that a certain group is not seen in a certain profession, and any service or function that keeps promoting that is contributing to harm. -- **Stereotyping**. Associating a given group with pre-assigned attributes. For example, a language translation system betweem English and Turkish may have inaccuraces due to words with stereotypical associations to gender. - -![translation to Turkish](images/gender-bias-translate-en-tr.png) -> translation to Turkish - -![translation back to English](images/gender-bias-translate-tr-en.png) -> translation back to English - -When designing and testing AI systems, we need to ensure that AI is fair and not programmed to make biased or discriminatory decisions, which human beings are also prohibited from making. Guaranteeing fairness in AI and machine learning remains a complex sociotechnical challenge. - -### Reliability and safety - -To build trust, AI systems need to be reliable, safe, and consistent under normal and unexpected conditions. It is important to know how AI systems will behavior in a variety of situations, especially when they are outliers. When building AI solutions, there needs to be a substantial amount of focus on how to handle a wide variety of circumstances that the AI solutions would encounter. For example, a self-driving car needs to put people's safety as a top priority. As a result, the AI powering the car need to consider all the possible scenarios that the car could come across such as night, thunderstorms or blizzards, kids running across the street, pets, road constructions etc. How well an AI system can handle a wild range of conditions reliably and safely reflects the level of anticipation the data scientist or AI developer considered during the design or testing of the system. - -> [đŸŽĨ Click the here for a video: ](https://www.microsoft.com/videoplayer/embed/RE4vvIl) - -### Inclusiveness - -AI systems should be designed to engage and empower everyone. When designing and implementing AI systems data scientists and AI developers identify and address potential barriers in the system that could unintentionally exclude people. For example, there are 1 billion people with disabilities around the world. With the advancement of AI, they can access a wide range of information and opportunities more easily in their daily lives. By addressing the barriers, it creates opportunities to innovate and develop AI products with better experiences that benefit everyone. - -> [đŸŽĨ Click the here for a video: inclusiveness in AI](https://www.microsoft.com/videoplayer/embed/RE4vl9v) - -### Security and privacy - -AI systems should be safe and respect people’s privacy. People have less trust in systems that put their privacy, information, or lives at risk. When training machine learning models, we rely on data to produce the best results. In doing so, the origin of the data and integrity must be considered. For example, was the data user submitted or publicly available? Next, while working with the data, it is crucial to develop AI systems that can protect confidential information and resist attacks. As AI becomes more prevalent, protecting privacy and securing important personal and business information is becoming more critical and complex. Privacy and data security issues require especially close attention for AI because access to data is essential for AI systems to make accurate and informed predictions and decisions about people. - -> [đŸŽĨ Click the here for a video: security in AI](https://www.microsoft.com/videoplayer/embed/RE4voJF) - -- As an industry we have made significant advancements in Privacy & security, fueled significantly by regulations like the GDPR (General Data Protection Regulation). -- Yet with AI systems we must acknowledge the tension between the need for more personal data to make systems more personal and effective – and privacy. -- Just like with the birth of connected computers with the internet, we are also seeing a huge uptick in the number of security issues related to AI. -- At the same time, we have seen AI being used to improve security. As an example, most modern anti-virus scanners are driven by AI heuristics today. -- We need to ensure that our Data Science processes blend harmoniously with the latest privacy and security practices. - - -### Transparency -AI systems should be understandable. A crucial part of transparency is explaining the behavior of AI systems and their components. Improving the understanding of AI systems requires that stakeholders comprehend how and why they function so that they can identify potential performance issues, safety and privacy concerns, biases, exclusionary practices, or unintended outcomes. We also believe that those who use AI systems should be honest and forthcoming about when, why, and how they choose to deploy them. As well as the limitations of the systems they use. For example, if a bank uses an AI system to support its consumer lending decisions, it is important to examine the outcomes and understand which data influences the system’s recommendations. Governments are starting to regulate AI across industries, so data scientists and organizations must explain if an AI system meets regulatory requirements, especially when there is an undesirable outcome. - -> [đŸŽĨ Click the here for a video: transparency in AI](https://www.microsoft.com/videoplayer/embed/RE4voJF) - -- Because AI systems are so complex, it is hard to understand how they work and interpret the results. -- This lack of understanding affects the way these systems are managed, operationalized, and documented. -- This lack of understanding more importantly affects the decisions made using the results these systems produce. - -### Accountability - -The people who design and deploy AI systems must be accountable for how their systems operate. The need for accountability is particularly crucial with sensitive use technologies like facial recognition. Recently, there has been a growing demand for facial recognition technology, especially from law enforcement organizations who see the potential of the technology in uses like finding missing children. However, these technologies could potentially be used by a government to put their citizens’ fundamental freedoms at risk by, for example, enabling continuous surveillance of specific individuals. Hence, data scientists and organizations need to be responsible for how their AI system impacts individuals or society. - -[![Leading AI Researcher Warns of Mass Surveillance Through Facial Recognition](images/accountability.png)](https://www.youtube.com/watch?v=Wldt8P5V6D0 "Microsoft's Approach to Responsible AI") - -> đŸŽĨ Click the image above for a video: Warnings of Mass Surveillance Through Facial Recognition - -Ultimately one of the biggest questions for our generation, as the first generation that is bringing AI to society, is how to ensure that computers will remain accountable to people and how to ensure that the people that design computers remain accountable to everyone else. - -## Impact assessment - -Before training a machine learning model, it is important to conduct an impact assessmet to understand the purpose of the AI system; what the intended use is; where it will be deployed; and who will be interacting with the system. These are helpful for reviewer(s) or testers evaluating the system to know what factors to take into consideration when identifying potential risks and expected consequences. - -The following are areas of focus when conducting an impact assessment: - -* **Adverse impact on individuals**. Being aware of any restriction or requirements, unsupported use or any known limitations hindering the system's performance is vital to ensure that the system is not used in a way that could cause harm to individuals. -* **Data requirements**. Gaining an understanding of how and where the system will use data enables reviewers to explore any data requirements you would need to be mindful of (e.g., GDPR or HIPPA data regulations). In addition, examine whether the source or quantity of data is substantial for training. -* **Summary of impact**. Gather a list of potential harms that could arise from using the system. Throughout the ML lifecycle, review if the issues identified are mitigated or addressed. -* **Applicable goals** for each of the six core principles. Assess if the goals from each of the principles are met and if there are any gaps. - - -## Debugging with responsible AI - -Similar to debugging a software application, debugging an AI system is a necessary process of identifying and resolving issues in the system. There are many factors that would affect a model not performing as expected or responsibly. Most traditional model performance metrics are quantitative aggregates of a model's performance, which are not sufficient to analyze how a model violates the responsible AI principles. Furthermore, a machine learning model is a black box that makes it difficult to understand what drives its outcome or provide explanation when it makes a mistake. Later in this course, we will learn how to use the Responsible AI dashboard to help debug AI systems. The dashboard provides a holistic tool for data scientists and AI developers to perform: - -* **Error analysis**. To identify the error distribution of the model that can affect the system's fairness or reliability. -* **Model overview**. To discover where there are disparities in the model's performance across data cohorts. -* **Data analysis**. To understand the data distribution and identify any potential bias in the data that could lead to fairness, inclusiveness, and reliability issues. -* **Model interpretability**. To understand what affects or influences the model's predictions. This helps in explaining the model's behavior, which is important for transparency and accountability. - - -## 🚀 Challenge - -To prevent harms from being introduced in the first place, we should: - -- have a diversity of backgrounds and perspectives among the people working on systems -- invest in datasets that reflect the diversity of our society -- develop better methods throughout the machine learning lifecycle for detecting and correcting responible AI when it occurs - -Think about real-life scenarios where a model's untrustworthiness is evident in model-building and usage. What else should we consider? - -## [Post-lecture quiz](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/6/) -## Review & Self Study - -In this lesson, you have learned some basics of the concepts of fairness and unfairness in machine learning. - -Watch this workshop to dive deeper into the topics: - -- In pursuit of responsible AI: Bringing principles to practice by Besmira Nushi, Mehrnoosh Sameki and Amit Sharma - -[![Responsible AI Toolbox: An open-source framework for building responsible AI](https://img.youtube.com/vi/tGgJCrA-MZU/0.jpg)](https://www.youtube.com/watch?v=tGgJCrA-MZU "RAI Toolbox: An open-source framework for building responsible AI") - -> đŸŽĨ Click the image above for a video: RAI Toolbox: An open-source framework for building responsible AI by Besmira Nushi, Mehrnoosh Sameki, and Amit Sharma - -Also, read: - -- Microsoft’s RAI resource center: [Responsible AI Resources – Microsoft AI](https://www.microsoft.com/ai/responsible-ai-resources?activetab=pivot1%3aprimaryr4) - -- Microsoft’s FATE research group: [FATE: Fairness, Accountability, Transparency, and Ethics in AI - Microsoft Research](https://www.microsoft.com/research/theme/fate/) - -RAI Toolbox: - -- [Responsible AI Toolbox GitHub repository](https://github.com/microsoft/responsible-ai-toolbox) - -Read about Azure Machine Learning's tools to ensure fairness: - -- [Azure Machine Learning](https://docs.microsoft.com/azure/machine-learning/concept-fairness-ml?WT.mc_id=academic-77952-leestott) - -## Assignment - -[Explore RAI Toolbox](assignment.md) diff --git a/1-Introduction/3-fairness/assignment.md b/1-Introduction/3-fairness/assignment.md deleted file mode 100644 index 6da0a381..00000000 --- a/1-Introduction/3-fairness/assignment.md +++ /dev/null @@ -1,11 +0,0 @@ -# Explore the Responsible AI Toolbox - -## Instructions - -In this lesson you learned about the Responsible AI Toolbox, an "open-source, community-driven project to help data scientists to analyze and improve AI systems." For this assignment, explore one of RAI Toolbox's [notebooks](https://github.com/microsoft/responsible-ai-toolbox/blob/main/notebooks/responsibleaidashboard/getting-started.ipynb) and report your findings in a paper or presentation. - -## Rubric - -| Criteria | Exemplary | Adequate | Needs Improvement | -| -------- | --------- | -------- | ----------------- | -| | A paper or powerpoint presentation is presented discussing Fairlearn's systems, the notebook that was run, and the conclusions drawn from running it | A paper is presented without conclusions | No paper is presented | diff --git a/1-Introduction/3-fairness/images/accessibility.png b/1-Introduction/3-fairness/images/accessibility.png deleted file mode 100644 index be33e9a9..00000000 Binary files a/1-Introduction/3-fairness/images/accessibility.png and /dev/null differ diff --git a/1-Introduction/3-fairness/images/accountability.png b/1-Introduction/3-fairness/images/accountability.png deleted file mode 100644 index 98015292..00000000 Binary files a/1-Introduction/3-fairness/images/accountability.png and /dev/null differ diff --git a/1-Introduction/3-fairness/translations/assignment.es.md b/1-Introduction/3-fairness/translations/assignment.es.md deleted file mode 100644 index e69de29b..00000000 diff --git a/1-Introduction/4-techniques-of-ML/README.md b/1-Introduction/4-techniques-of-ML/README.md deleted file mode 100644 index 4fcd5ea3..00000000 --- a/1-Introduction/4-techniques-of-ML/README.md +++ /dev/null @@ -1,118 +0,0 @@ -# Techniques of Machine Learning - -The process of building, using, and maintaining machine learning models and the data they use is a very different process from many other development workflows. In this lesson, we will demystify the process, and outline the main techniques you need to know. You will: - -- Understand the processes underpinning machine learning at a high level. -- Explore base concepts such as 'models', 'predictions', and 'training data'. - -## [Pre-lecture quiz](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/7/) - -[![ML for beginners - Techniques of Machine Learning](https://img.youtube.com/vi/4NGM0U2ZSHU/0.jpg)](https://youtu.be/4NGM0U2ZSHU "ML for beginners - Techniques of Machine Learning") - -> đŸŽĨ Click the image above for a short video working through this lesson. - -## Introduction - -On a high level, the craft of creating machine learning (ML) processes is comprised of a number of steps: - -1. **Decide on the question**. Most ML processes start by asking a question that cannot be answered by a simple conditional program or rules-based engine. These questions often revolve around predictions based on a collection of data. -2. **Collect and prepare data**. To be able to answer your question, you need data. The quality and, sometimes, quantity of your data will determine how well you can answer your initial question. Visualizing data is an important aspect of this phase. This phase also includes splitting the data into a training and testing group to build a model. -3. **Choose a training method**. Depending on your question and the nature of your data, you need to choose how you want to train a model to best reflect your data and make accurate predictions against it. This is the part of your ML process that requires specific expertise and, often, a considerable amount of experimentation. -4. **Train the model**. Using your training data, you'll use various algorithms to train a model to recognize patterns in the data. The model might leverage internal weights that can be adjusted to privilege certain parts of the data over others to build a better model. -5. **Evaluate the model**. You use never before seen data (your testing data) from your collected set to see how the model is performing. -6. **Parameter tuning**. Based on the performance of your model, you can redo the process using different parameters, or variables, that control the behavior of the algorithms used to train the model. -7. **Predict**. Use new inputs to test the accuracy of your model. - -## What question to ask - -Computers are particularly skilled at discovering hidden patterns in data. This utility is very helpful for researchers who have questions about a given domain that cannot be easily answered by creating a conditionally-based rules engine. Given an actuarial task, for example, a data scientist might be able to construct handcrafted rules around the mortality of smokers vs non-smokers. - -When many other variables are brought into the equation, however, a ML model might prove more efficient to predict future mortality rates based on past health history. A more cheerful example might be making weather predictions for the month of April in a given location based on data that includes latitude, longitude, climate change, proximity to the ocean, patterns of the jet stream, and more. - -✅ This [slide deck](https://www2.cisl.ucar.edu/sites/default/files/2021-10/0900%20June%2024%20Haupt_0.pdf) on weather models offers a historical perspective for using ML in weather analysis. - -## Pre-building tasks - -Before starting to build your model, there are several tasks you need to complete. To test your question and form a hypothesis based on a model's predictions, you need to identify and configure several elements. - -### Data - -To be able to answer your question with any kind of certainty, you need a good amount of data of the right type. There are two things you need to do at this point: - -- **Collect data**. Keeping in mind the previous lesson on fairness in data analysis, collect your data with care. Be aware of the sources of this data, any inherent biases it might have, and document its origin. -- **Prepare data**. There are several steps in the data preparation process. You might need to collate data and normalize it if it comes from diverse sources. You can improve the data's quality and quantity through various methods such as converting strings to numbers (as we do in [Clustering](../../5-Clustering/1-Visualize/README.md)). You might also generate new data, based on the original (as we do in [Classification](../../4-Classification/1-Introduction/README.md)). You can clean and edit the data (as we will prior to the [Web App](../../3-Web-App/README.md) lesson). Finally, you might also need to randomize it and shuffle it, depending on your training techniques. - -✅ After collecting and processing your data, take a moment to see if its shape will allow you to address your intended question. It may be that the data will not perform well in your given task, as we discover in our [Clustering](../../5-Clustering/1-Visualize/README.md) lessons! - -### Features and Target - -A [feature](https://www.datasciencecentral.com/profiles/blogs/an-introduction-to-variable-and-feature-selection) is a measurable property of your data. In many datasets it is expressed as a column heading like 'date' 'size' or 'color'. Your feature variable, usually represented as `X` in code, represent the input variable which will be used to train model. - -A target is a thing you are trying to predict. Target usually represented as `y` in code, represents the answer to the question you are trying to ask of your data: in December, what **color** pumpkins will be cheapest? in San Francisco, what neighborhoods will have the best real estate **price**? Sometimes target is also referred as label attribute. - -### Selecting your feature variable - -🎓 **Feature Selection and Feature Extraction** How do you know which variable to choose when building a model? You'll probably go through a process of feature selection or feature extraction to choose the right variables for the most performant model. They're not the same thing, however: "Feature extraction creates new features from functions of the original features, whereas feature selection returns a subset of the features." ([source](https://wikipedia.org/wiki/Feature_selection)) - -### Visualize your data - -An important aspect of the data scientist's toolkit is the power to visualize data using several excellent libraries such as Seaborn or MatPlotLib. Representing your data visually might allow you to uncover hidden correlations that you can leverage. Your visualizations might also help you to uncover bias or unbalanced data (as we discover in [Classification](../../4-Classification/2-Classifiers-1/README.md)). - -### Split your dataset - -Prior to training, you need to split your dataset into two or more parts of unequal size that still represent the data well. - -- **Training**. This part of the dataset is fit to your model to train it. This set constitutes the majority of the original dataset. -- **Testing**. A test dataset is an independent group of data, often gathered from the original data, that you use to confirm the performance of the built model. -- **Validating**. A validation set is a smaller independent group of examples that you use to tune the model's hyperparameters, or architecture, to improve the model. Depending on your data's size and the question you are asking, you might not need to build this third set (as we note in [Time Series Forecasting](../../7-TimeSeries/1-Introduction/README.md)). - -## Building a model - -Using your training data, your goal is to build a model, or a statistical representation of your data, using various algorithms to **train** it. Training a model exposes it to data and allows it to make assumptions about perceived patterns it discovers, validates, and accepts or rejects. - -### Decide on a training method - -Depending on your question and the nature of your data, you will choose a method to train it. Stepping through [Scikit-learn's documentation](https://scikit-learn.org/stable/user_guide.html) - which we use in this course - you can explore many ways to train a model. Depending on your experience, you might have to try several different methods to build the best model. You are likely to go through a process whereby data scientists evaluate the performance of a model by feeding it unseen data, checking for accuracy, bias, and other quality-degrading issues, and selecting the most appropriate training method for the task at hand. - -### Train a model - -Armed with your training data, you are ready to 'fit' it to create a model. You will notice that in many ML libraries you will find the code 'model.fit' - it is at this time that you send in your feature variable as an array of values (usually 'X') and a target variable (usually 'y'). - -### Evaluate the model - -Once the training process is complete (it can take many iterations, or 'epochs', to train a large model), you will be able to evaluate the model's quality by using test data to gauge its performance. This data is a subset of the original data that the model has not previously analyzed. You can print out a table of metrics about your model's quality. - -🎓 **Model fitting** - -In the context of machine learning, model fitting refers to the accuracy of the model's underlying function as it attempts to analyze data with which it is not familiar. - -🎓 **Underfitting** and **overfitting** are common problems that degrade the quality of the model, as the model fits either not well enough or too well. This causes the model to make predictions either too closely aligned or too loosely aligned with its training data. An overfit model predicts training data too well because it has learned the data's details and noise too well. An underfit model is not accurate as it can neither accurately analyze its training data nor data it has not yet 'seen'. - -![overfitting model](images/overfitting.png) -> Infographic by [Jen Looper](https://twitter.com/jenlooper) - -## Parameter tuning - -Once your initial training is complete, observe the quality of the model and consider improving it by tweaking its 'hyperparameters'. Read more about the process [in the documentation](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-tune-hyperparameters?WT.mc_id=academic-77952-leestott). - -## Prediction - -This is the moment where you can use completely new data to test your model's accuracy. In an 'applied' ML setting, where you are building web assets to use the model in production, this process might involve gathering user input (a button press, for example) to set a variable and send it to the model for inference, or evaluation. - -In these lessons, you will discover how to use these steps to prepare, build, test, evaluate, and predict - all the gestures of a data scientist and more, as you progress in your journey to become a 'full stack' ML engineer. - ---- - -## 🚀Challenge - -Draw a flow chart reflecting the steps of a ML practitioner. Where do you see yourself right now in the process? Where do you predict you will find difficulty? What seems easy to you? - -## [Post-lecture quiz](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/8/) - -## Review & Self Study - -Search online for interviews with data scientists who discuss their daily work. Here is [one](https://www.youtube.com/watch?v=Z3IjgbbCEfs). - -## Assignment - -[Interview a data scientist](assignment.md) diff --git a/1-Introduction/4-techniques-of-ML/assignment.md b/1-Introduction/4-techniques-of-ML/assignment.md deleted file mode 100644 index db20bb5d..00000000 --- a/1-Introduction/4-techniques-of-ML/assignment.md +++ /dev/null @@ -1,11 +0,0 @@ -# Interview a data scientist - -## Instructions - -In your company, in a user group, or among your friends or fellow students, talk to someone who works professionally as a data scientist. Write a short paper (500 words) about their daily occupations. Are they specialists, or do they work 'full stack'? - -## Rubric - -| Criteria | Exemplary | Adequate | Needs Improvement | -| -------- | ------------------------------------------------------------------------------------ | ------------------------------------------------------------------ | --------------------- | -| | An essay of the correct length, with attributed sources, is presented as a .doc file | The essay is poorly attributed or shorter than the required length | No essay is presented | diff --git a/1-Introduction/4-techniques-of-ML/images/overfitting.png b/1-Introduction/4-techniques-of-ML/images/overfitting.png deleted file mode 100644 index 9395accf..00000000 Binary files a/1-Introduction/4-techniques-of-ML/images/overfitting.png and /dev/null differ diff --git a/1-Introduction/4-techniques-of-ML/translations/README.es.md b/1-Introduction/4-techniques-of-ML/translations/README.es.md deleted file mode 100755 index 75828793..00000000 --- a/1-Introduction/4-techniques-of-ML/translations/README.es.md +++ /dev/null @@ -1,112 +0,0 @@ -# TÊcnicas de Machine Learning - -El proceso de creaciÃŗn, uso y mantenimiento de modelos de machine learning, y los datos que se utilizan, es un proceso muy diferente de muchos otros flujos de trabajo de desarrollo. En esta lecciÃŗn, demistificaremos el proceso y describiremos las principales tÊcnicas que necesita saber. Vas a: - -- Comprender los procesos que sustentan el machine learning a un alto nivel. -- Explorar conceptos bÃĄsicos como 'modelos', 'predicciones', y 'datos de entrenamiento' - - -## [Cuestionario previo a la conferencia](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/7?loc=es) -## IntroducciÃŗn - -A un alto nivel, el arte de crear procesos de machine learning (ML) se compone de una serie de pasos: - -1. **Decidir sobre la pregunta**. La mayoría de los procesos de ML, comienzan por hacer una pregunta que no puede ser respondida por un simple programa condicional o un motor basado en reglas. Esas preguntas a menudo giran en torno a predicciones basadas en una recopilaciÃŗn de datos. -2. **Recopile y prepare datos**. Para poder responder a su pregunta, necesita datos. La calidad y, a veces, cantidad de sus datos determinarÃĄn que tan bien puede responder a su pregunta inicial. La visualizaciÃŗn de datos es un aspecto importante de esta fase. Esta fase tambiÊn incluye dividir los datos en un grupo de entrenamiento y pruebas para construir un modelo. -3. **Elige un mÊtodo de entrenamiento**. Dependiendo de su pregunta y la naturaleza de sus datos, debe elegir cÃŗmo desea entrenar un modelo para reflejar mejor sus datos y hacer predicciones precisas contra ellos. Esta es la parte de su proceso de ML que requiere experiencia específica y, a menudo, una cantidad considerable de experimentaciÃŗn. -4. **Entrena el modelo**. Usando sus datos de entrenamiento, usarÃĄ varios algoritmos para entrenar un modelo para reconocer patrones en los datos. El modelo puede aprovechar las ponderaciones internas que se pueden ajustar para privilegiar ciertas partes de los datos sobre otras para construir un modelo mejor. -5. **Evaluar el modelo**. Utiliza datos nunca antes vistos (sus datos de prueba) de su conjunto recopilado para ver cÃŗmo se estÃĄ desempeÃąando el modelo. -6. **Ajuste de parÃĄmetros**. SegÃēn el rendimiento de su modelo, puede rehacer el proceso utilizando diferentes parÃĄmetros, o variables, que controlan el comportamiento de los algoritmos utilizados para entrenar el modelo. -7. **Predecir**. Utilice nuevas entradas para probar la precisiÃŗn de su modelo. - -## QuÊ preguntas hacer - -Las computadoras son particularmente hÃĄbiles para descubrir patrones ocultos en los datos. Esta utlidad es muy Ãētil para los investigadores que tienen preguntas sobre un dominio determinado que no pueden responderse fÃĄcilmente mediante la creaciÃŗn de un motor de reglas basadas en condicionales. Dada una tarea actuarial, por ejemplo, un científico de datos podría construir reglas creadas manualmente sobre la mortalidad de los fumadores frente a los no fumadores. - -Sin embargo, cuando se incorporan muchas otras variables a la ecuaciÃŗn, un modelo de ML podría resultar mÃĄs eficiente para predecir las tasas de mortalidad futuras en funciÃŗn de los antecedentes de salud. Un ejemplo mÃĄs alegre podría hacer predicciones meteorolÃŗgicas para el mes de abril en una ubicaciÃŗn determinada que incluya latitud, longitud, cambio climÃĄtico, proximidad al ocÊano, patrones de la corriente en chorro, y mÃĄs. - -✅ Esta [presentaciÃŗn de diapositivas](https://www2.cisl.ucar.edu/sites/default/files/2021-10/0900%20June%2024%20Haupt_0.pdf) sobre modelos meteorolÃŗgicos ofrece una perspectiva histÃŗrica del uso de ML en el anÃĄlisis meteorolÃŗgico. - -## Tarea previas a la construcciÃŗn - -Antes de comenzar a construir su modelo, hay varias tareas que debe completar. Para examinar su pregunta y formar una hipÃŗtesis basada en las predicciones de su modelo, debe identificar y configurar varios elementos. - -### Datos - -Para poder responder su pregunta con algÃēn tipo de certeza, necesita una buena cantidad de datos del tipo correcto. -Hay dos cosas que debe hacer en este punto: - -- **Recolectar datos**. Teniendo en cuenta la lecciÃŗn anterior sobre la equidad en el anÃĄlisis de datos, recopile sus datos con cuidado. Tenga en cuenta la fuente de estos datos, cualquier sesgo inherente que pueda tener y documente su origen. -- **Preparar datos**. Hay varios pasos en el proceso de preparaciÃŗn de datos. Podría necesitar recopilar datos y normalizarlos si provienen de diversas fuentes. Puede mejorar la calidad y cantidad de los datos mediante varios mÊtodos, como convertir strings en nÃēmeros (como hacemos en [Clustering](../../5-Clustering/1-Visualize/README.md)). TambiÊn puede generar nuevos datos, basados en los originales (como hacemos en [ClasificaciÃŗn](../../4-Classification/1-Introduction/README.md)). Puede limpiar y editar los datos (como lo haremos antes de la lecciÃŗn [Web App](../../3-Web-App/README.md)). Por Ãēltimo, es posible que tambiÊn deba aleatorizarlo y mezclarlo, segÃēn sus tÊcnicas de entrenamiento. - -✅ DespÃēes de recopilar y procesar sus datos, tÃŗmese un momento para ver si su forma le permitirÃĄ responder a su pregunta. ÂĄPuede ser que los datos no funcionen bien en su tarea dada, como descubriremos en nuestras lecciones de[Clustering](../../5-Clustering/1-Visualize/README.md)! - -### Características y destino - -Una característica es una propiedad medible de los datos. En muchos conjuntos de datos se expresa como un encabezado de columna como 'date' 'size' o 'color'. La variable de entidad, normalmente representada como `X` en el cÃŗdigo, representa la variable de entrada que se utilizarÃĄ para entrenar el modelo. - -Un objetivo es una cosa que estÃĄ tratando de predecir. Target generalmente representado como `y` en el cÃŗdigo, representa la respuesta a la pregunta que estÃĄ tratando de hacer de sus datos: en diciembre, ÂŋquÊ color de calabazas serÃĄn mÃĄs baratas?; en San Francisco, ÂŋquÊ barrios tendrÃĄn el mejor precio de bienes raíces? A veces, target tambiÊn se conoce como atributo label. - -### Seleccionando su variable característica - -🎓 **SelecciÃŗn y extracciÃŗn de características** ÂŋCÃŗmo sabe que variable elegir al construir un modelo? Probablemente pasarÃĄ por un proceso de selecciÃŗn o extracciÃŗn de características para elegir las variables correctas para un mayor rendimiento del modelo. Sin embargo, no son lo mismo: "La extracciÃŗn de características crea nuevas características a partir de funciones de las características originales, mientras que la selecciÃŗn de características devuelve un subconjunto de las características." ([fuente](https://wikipedia.org/wiki/Feature_selection)) - -### Visualiza tus datos - -Un aspecto importante del conjunto de herramientas del científico de datos es el poder de visualizar datos utilizando varias bibliotecas excelentes como Seaborn o MatPlotLib. Representar sus datos visualmente puede permitirle descubrir correlaciones ocultas que puede aprovechar. Sus visualizaciones tambiÊn pueden ayudarlo a descubrir sesgos o datos desequilibrados. (como descubrimos en [ClasificaciÃŗn](../../4-Classification/2-Classifiers-1/README.md)). - -### Divide tu conjunto de datos - -Antes del entrenamiento, debe dividir su conjunto de datos en dos o mÃĄs partes de tamaÃąo desigual pero que representen bien los datos. - -- **Entrenamiento**. Esta parte del conjunto de datos se ajusta a su modelo para entrenarlo. Este conjunto constituye la mayor parte del conjunto de datos original. -- **Pruebas**. Un conjunto de datos de pruebas es un grupo independiente de datos, a menudo recopilado a partir de los datos originales, que se utiliza para confirmar el rendimiento del modelo construido. -- **ValidaciÃŗn**. Un conjunto de validaciÃŗn es un pequeÃąo grupo independiente de ejemplos que se usa para ajustar los hiperparÃĄmetros o la arquitectura del modelo para mejorar el modelo. Dependiendo del tamaÃąo de su conjunto de datos y de la pregunta que se estÃĄ haciendo, es posible que no necesite crear este tercer conjunto (como notamos en [PronÃŗstico se series de tiempo](../../7-TimeSeries/1-Introduction/README.md)). - -## Contruye un modelo - -Usando sus datos de entrenamiento, su objetivo es construir un modelo, o una representaciÃŗn estadística de sus datos, utilizando varios algoritmos para **entrenarlo**. El entrenamiento de un modelo lo expone a los datos y le permite hacer suposiciones sobre los patrones percibidos que descubre, valida y rechaza. - -### Decide un mÊtodo de entrenamiento - -Dependiendo de su pregunta y la naturaleza de sus datos, elegirÃĄ un mÊtodo para entrenarlos. Echando un vistazo a la [documentaciÃŗn de Scikit-learn ](https://scikit-learn.org/stable/user_guide.html) - que usamos en este curso - puede explorar muchas formas de entrenar un modelo. Dependiendo de su experiencia, es posible que deba probar varios mÊtodos diferentes para construir el mejor modelo. Es probable que pase por un proceso en el que los científicos de datos evalÃēan el rendimiento de un modelo alimentÃĄndolo con datos no vistos anteriormente por el modelo, verificando la precisiÃŗn, el sesgo, y otros problemas que degradan la calidad, y seleccionando el mÊtodo de entrenamieto mÃĄs apropiado para la tarea en cuestiÃŗn. -### Entrena un modelo - -Armado con sus datos de entrenamiento, estÃĄ listo para "ajustarlo" para crear un modelo. NotarÃĄ que en muchas bibliotecas de ML encontrarÃĄ un mÊtodo de la forma 'model.fit' - es en este momento que envía su variable de característica como una matriz de valores (generalmente `X`) y una variable de destino (generalmente `y`). - -### Evaluar el modelo - -Una vez que se completa el proceso de entrenamiento (puede tomar muchas iteraciones, o 'Êpocas', entrenar un modelo de gran tamaÃąo), podrÃĄ evaluar la calidad del modelo utilizando datos de prueba para medir su rendimiento. Estos datos son un subconjunto de los datos originales que el modelo no ha analizado previamente. Puede imprimir una tabla de mÊtricas sobre la calidad de su modelo. - -🎓 **Ajuste del modelo (Model fitting)** - -En el contexto del machine learning, el ajuste del modelo se refiere a la precisiÃŗn de la funciÃŗn subyacente del modelo cuando intenta analizar datos con los que no estÃĄ familiarizado. - -🎓 **Ajuste insuficiente (Underfitting)** y **sobreajuste (overfitting)** son problemas comunes que degradan la calidad del modelo, ya que el modelo no encaja suficientemente bien, o encaja demasiado bien. Esto hace que el modelo haga predicciones demasiado estrechamente alineadas o demasiado poco alineadas con sus datos de entrenamiento. Un modelo sobreajustado (overfitting) predice demasiado bien los datos de entrenamiento porque ha aprendido demasiado bien los detalles de los datos y el ruido. Un modelo insuficientemente ajustado (Underfitting) es impreciso, ya que ni puede analizar con precisiÃŗn sus datos de entrenamiento ni los datos que aÃēn no ha 'visto'. - -![Sobreajuste de un modelo](images/overfitting.png) -> Infografía de [Jen Looper](https://twitter.com/jenlooper) - -## Ajuste de parÃĄmetros - -Una vez que haya completado su entrenamiento inicial, observe la calidad del modelo y considere mejorarlo ajustando sus 'hiperparÃĄmetros'. Lea mÃĄs sobre el proceso [en la documentaciÃŗn](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-tune-hyperparameters?WT.mc_id=academic-77952-leestott). - -## PredicciÃŗn - -Este es el momento en el que puede usar datos completamente nuevos para probar la precisiÃŗn de su modelo. En una configuraciÃŗn de ML aplicado, donde estÃĄ creando activos web para usar el modelo en producciÃŗn, este proceso puede implicar la recopilaciÃŗn de la entrada del usuario (presionar un botÃŗn, por ejemplo) para establecer una variable y enviarla al modelo para la inferencia o evaluaciÃŗn. -En estas lecciones, descubrirÃĄ cÃŗmo utilizar estos pasos para preparar, construir, probar, evaluar, y predecir - todos los gestos de un científico de datos y mÃĄs, a medida que avanza en su viaje para convertirse en un ingeniero de machine learning 'full stack'. ---- - -## 🚀Desafío - -Dibuje un diagrama de flujos que refleje los pasos de practicante de ML. ÂŋDÃŗnde te ves ahora mismo en el proceso? ÂŋDÃŗnde predice que encontrarÃĄ dificultades? ÂŋQuÊ te parece fÃĄcil? - -## [Cuestionario posterior a la conferencia](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/8?loc=es) - -## RevisiÃŗn & Autoestudio - -Busque entrevistas en línea con científicos de datos que analicen su trabajo diario. Aquí estÃĄ [uno](https://www.youtube.com/watch?v=Z3IjgbbCEfs). - -## AsignaciÃŗn - -[Entrevistar a un científico de datos](assignment.md) diff --git a/1-Introduction/4-techniques-of-ML/translations/README.id.md b/1-Introduction/4-techniques-of-ML/translations/README.id.md deleted file mode 100644 index e745955f..00000000 --- a/1-Introduction/4-techniques-of-ML/translations/README.id.md +++ /dev/null @@ -1,111 +0,0 @@ -# Teknik-teknik Machine Learning - -Proses membangun, menggunakan, dan memelihara model machine learning dan data yang digunakan adalah proses yang sangat berbeda dari banyak alur kerja pengembangan lainnya. Dalam pelajaran ini, kita akan mengungkap prosesnya dan menguraikan teknik utama yang perlu Kamu ketahui. Kamu akan: - -- Memahami gambaran dari proses yang mendasari machine learning. -- Menjelajahi konsep dasar seperti '*models*', '*predictions*', dan '*training data*'. - -## [Quiz Pra-Pelajaran](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/7/) -## Pengantar - -Gambaran membuat proses machine learning (ML) terdiri dari sejumlah langkah: - -1. **Menentukan pertanyaan**. Sebagian besar proses ML dimulai dengan mengajukan pertanyaan yang tidak dapat dijawab oleh program kondisional sederhana atau mesin berbasis aturan (*rules-based engine*). Pertanyaan-pertanyaan ini sering berkisar seputar prediksi berdasarkan kumpulan data. -2. **Mengumpulkan dan menyiapkan data**. Untuk dapat menjawab pertanyaanmu, Kamu memerlukan data. Bagaimana kualitas dan terkadang kuantitas data kamu akan menentukan seberapa baik kamu dapat menjawab pertanyaan awal kamu. Memvisualisasikan data merupakan aspek penting dari fase ini. Fase ini juga mencakup pemisahan data menjadi kelompok *training* dan *testing* untuk membangun model. -3. **Memilih metode training**. Tergantung dari pertanyaan dan sifat datamu, Kamu perlu memilih bagaimana kamu ingin men-training sebuah model untuk mencerminkan data kamu dengan baik dan membuat prediksi yang akurat terhadapnya. Ini adalah bagian dari proses ML yang membutuhkan keahlian khusus dan seringkali perlu banyak eksperimen. -4. **Melatih model**. Dengan menggunakan data *training*, kamu akan menggunakan berbagai algoritma untuk melatih model guna mengenali pola dalam data. Modelnya mungkin bisa memanfaatkan *internal weight* yang dapat disesuaikan untuk memberi hak istimewa pada bagian tertentu dari data dibandingkan bagian lainnya untuk membangun model yang lebih baik. -5. **Mengevaluasi model**. Gunakan data yang belum pernah dilihat sebelumnya (data *testing*) untuk melihat bagaimana kinerja model. -6. **Parameter tuning**. Berdasarkan kinerja modelmu, Kamu dapat mengulang prosesnya menggunakan parameter atau variabel yang berbeda, yang mengontrol perilaku algoritma yang digunakan untuk melatih model. -7. **Prediksi**. Gunakan input baru untuk menguji keakuratan model kamu. - -## Pertanyaan apa yang harus ditanyakan? - -Komputer sangat ahli dalam menemukan pola tersembunyi dalam data. Hal ini sangat membantu peneliti yang memiliki pertanyaan tentang domain tertentu yang tidak dapat dijawab dengan mudah dari hanya membuat mesin berbasis aturan kondisional (*conditionally-based rules engine*). Untuk tugas aktuaria misalnya, seorang data scientist mungkin dapat membuat aturan secara manual seputar mortalitas perokok vs non-perokok. - -Namun, ketika banyak variabel lain dimasukkan ke dalam persamaan, model ML mungkin terbukti lebih efisien untuk memprediksi tingkat mortalitas di masa depan berdasarkan riwayat kesehatan masa lalu. Contoh yang lebih menyenangkan mungkin membuat prediksi cuaca untuk bulan April di lokasi tertentu berdasarkan data yang mencakup garis lintang, garis bujur, perubahan iklim, kedekatan dengan laut, pola aliran udara (Jet Stream), dan banyak lagi. - -✅ [Slide deck](https://www2.cisl.ucar.edu/sites/default/files/2021-10/0900%20June%2024%20Haupt_0.pdf) ini menawarkan perspektif historis pada model cuaca dengan menggunakan ML dalam analisis cuaca. - -## Tugas Pra-Pembuatan - -Sebelum mulai membangun model kamu, ada beberapa tugas yang harus kamu selesaikan. Untuk menguji pertanyaan kamu dan membentuk hipotesis berdasarkan prediksi model, Kamu perlu mengidentifikasi dan mengonfigurasi beberapa elemen. - -### Data - -Untuk dapat menjawab pertanyaan kamu dengan kepastian, Kamu memerlukan sejumlah besar data dengan jenis yang tepat. Ada dua hal yang perlu kamu lakukan pada saat ini: - -- **Mengumpulkan data**. Ingat pelajaran sebelumnya tentang keadilan dalam analisis data, kumpulkan data kamu dengan hati-hati. Waspadai sumber datanya, bias bawaan apa pun yang mungkin dimiliki, dan dokumentasikan asalnya. -- **Menyiapkan data**. Ada beberapa langkah dalam proses persiapan data. Kamu mungkin perlu menyusun data dan melakukan normalisasi jika berasal dari berbagai sumber. Kamu dapat meningkatkan kualitas dan kuantitas data melalui berbagai metode seperti mengonversi string menjadi angka (seperti yang kita lakukan di [Clustering](../../5-Clustering/1-Visualize/translations/README.id.md)). Kamu mungkin juga bisa membuat data baru berdasarkan data yang asli (seperti yang kita lakukan di [Classification](../../4-Classification/1-Introduction/translations/README.id.md)). Kamu bisa membersihkan dan mengubah data (seperti yang kita lakukan sebelum pelajaran [Web App](../3-Web-App/translations/README.id.md)). Terakhir, Kamu mungkin juga perlu mengacaknya dan mengubah urutannya, tergantung pada teknik *training* kamu. - -✅ Setelah mengumpulkan dan memproses data kamu, luangkan waktu sejenak untuk melihat apakah bentuknya memungkinkan kamu untuk menjawab pertanyaan yang kamu maksudkan. Mungkin data tidak akan berkinerja baik dalam tugas yang kamu berikan, seperti yang kita temukan dalam pelajaran [Clustering](../../5-Clustering/1-Visualize/translations/README.id.md). - -### Fitur dan Target - -Fitur adalah properti terukur dari data Anda. Dalam banyak set data, data tersebut dinyatakan sebagai judul kolom seperti 'date' 'size' atau 'color'. Variabel fitur Anda, biasanya direpresentasikan sebagai `X` dalam kode, mewakili variabel input yang akan digunakan untuk melatih model. - -A target is a thing you are trying to predict. Target usually represented as `y` in code, represents the answer to the question you are trying to ask of your data: in December, what color pumpkins will be cheapest? in San Francisco, what neighborhoods will have the best real estate price? Sometimes target is also referred as label attribute. - -### Memilih variabel fiturmu - -🎓 **Feature Selection dan Feature Extraction** Bagaimana kamu tahu variabel mana yang harus dipilih saat membangun model? Kamu mungkin akan melalui proses pemilihan fitur (*Feature Selection*) atau ekstraksi fitur (*Feature Extraction*) untuk memilih variabel yang tepat untuk membuat model yang berkinerja paling baik. Namun, keduanya tidak sama: "Ekstraksi fitur membuat fitur baru dari fungsi fitur asli, sedangkan pemilihan fitur mengembalikan subset fitur." ([sumber](https://wikipedia.org/wiki/Feature_selection)) -### Visualisasikan datamu - -Aspek penting dari toolkit data scientist adalah kemampuan untuk memvisualisasikan data menggunakan beberapa *library* seperti Seaborn atau MatPlotLib. Merepresentasikan data kamu secara visual memungkinkan kamu mengungkap korelasi tersembunyi yang dapat kamu manfaatkan. Visualisasimu mungkin juga membantu kamu mengungkap data yang bias atau tidak seimbang (seperti yang kita temukan dalam [Classification](../../4-Classification/2-Classifiers-1/translations/README.id.md)). -### Membagi dataset - -Sebelum memulai *training*, Kamu perlu membagi dataset menjadi dua atau lebih bagian dengan ukuran yang tidak sama tapi masih mewakili data dengan baik. - -- **Training**. Bagian dataset ini digunakan untuk men-training model kamu. Bagian dataset ini merupakan mayoritas dari dataset asli. -- **Testing**. Sebuah dataset tes adalah kelompok data independen, seringkali dikumpulkan dari data yang asli yang akan digunakan untuk mengkonfirmasi kinerja dari model yang dibuat. -- **Validating**. Dataset validasi adalah kumpulan contoh mandiri yang lebih kecil yang kamu gunakan untuk menyetel hyperparameter atau arsitektur model untuk meningkatkan model. Tergantung dari ukuran data dan pertanyaan yang kamu ajukan, Kamu mungkin tidak perlu membuat dataset ketiga ini (seperti yang kita catat dalam [Time Series Forecasting](../7-TimeSeries/1-Introduction/translations/README.id.md)). - -## Membuat sebuah model - -Dengan menggunakan data *training*, tujuan kamu adalah membuat model atau representasi statistik data kamu menggunakan berbagai algoritma untuk **melatihnya**. Melatih model berarti mengeksposnya dengan data dan mengizinkannya membuat asumsi tentang pola yang ditemukan, divalidasi, dan diterima atau ditolak. - -### Tentukan metode training - -Tergantung dari pertanyaan dan sifat datamu, Kamu akan memilih metode untuk melatihnya. Buka dokumentasi [Scikit-learn](https://scikit-learn.org/stable/user_guide.html) yang kita gunakan dalam pelajaran ini, kamu bisa menjelajahi banyak cara untuk melatih sebuah model. Tergantung dari pengalamanmu, kamu mungkin perlu mencoba beberapa metode yang berbeda untuk membuat model yang terbaik. Kemungkinan kamu akan melalui proses di mana data scientist mengevaluasi kinerja model dengan memasukkan data yang belum pernah dilihat, memeriksa akurasi, bias, dan masalah penurunan kualitas lainnya, dan memilih metode training yang paling tepat untuk tugas yang ada. - -### Melatih sebuah model - -Berbekan dengan data pelatihan Anda, Anda siap untuk 'menyesuaikan' untuk membuat model. Anda akan melihat bahwa di banyak perpustakaan ML Anda akan menemukan kode 'model.fit' - saat inilah Anda mengirim variabel fitur Anda sebagai array nilai (biasanya `X`) dan variabel target (biasanya `y`). - -### Mengevaluasi model - -Setelah proses *training* selesai (ini mungkin membutuhkan banyak iterasi, atau 'epoch', untuk melatih model besar), Kamu akan dapat mengevaluasi kualitas model dengan menggunakan data tes untuk mengukur kinerjanya. Data ini merupakan subset dari data asli yang modelnya belum pernah dianalisis sebelumnya. Kamu dapat mencetak tabel metrik tentang kualitas model kamu. - -🎓 **Model fitting** - -Dalam konteks machine learning, *model fitting* mengacu pada keakuratan dari fungsi yang mendasari model saat mencoba menganalisis data yang tidak familiar. - -🎓 **Underfitting** dan **overfitting** adalah masalah umum yang menurunkan kualitas model, karena model tidak cukup akurat atau terlalu akurat. Hal ini menyebabkan model membuat prediksi yang terlalu selaras atau tidak cukup selaras dengan data trainingnya. Model overfit memprediksi data *training* terlalu baik karena telah mempelajari detail dan noise data dengan terlalu baik. Model underfit tidak akurat karena tidak dapat menganalisis data *training* atau data yang belum pernah dilihat sebelumnya secara akurat. - -![overfitting model](../images/overfitting.png) -> Infografis oleh [Jen Looper](https://twitter.com/jenlooper) - -## Parameter tuning - -Setelah *training* awal selesai, amati kualitas model dan pertimbangkan untuk meningkatkannya dengan mengubah 'hyperparameter' nya. Baca lebih lanjut tentang prosesnya [di dalam dokumentasi](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-tune-hyperparameters?WT.mc_id=academic-77952-leestott). - -## Prediksi - -Ini adalah saat di mana Kamu dapat menggunakan data yang sama sekali baru untuk menguji akurasi model kamu. Dalam setelan ML 'terapan', di mana kamu membangun aset web untuk menggunakan modelnya dalam produksi, proses ini mungkin melibatkan pengumpulan input pengguna (misalnya menekan tombol) untuk menyetel variabel dan mengirimkannya ke model untuk inferensi, atau evaluasi. - -Dalam pelajaran ini, Kamu akan menemukan cara untuk menggunakan langkah-langkah ini untuk mempersiapkan, membangun, menguji, mengevaluasi, dan memprediksi - semua gestur data scientist dan banyak lagi, seiring kemajuanmu dalam perjalanan menjadi 'full stack' ML engineer. - ---- - -## 🚀Tantangan - -Gambarlah sebuah flow chart yang mencerminkan langkah-langkah seorang praktisi ML. Di mana kamu melihat diri kamu saat ini dalam prosesnya? Di mana kamu memprediksi kamu akan menemukan kesulitan? Apa yang tampak mudah bagi kamu? - -## [Quiz Pra-Pelajaran](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/8/) - -## Ulasan & Belajar Mandiri - -Cari di Internet mengenai wawancara dengan data scientist yang mendiskusikan pekerjaan sehari-hari mereka. Ini [salah satunya](https://www.youtube.com/watch?v=Z3IjgbbCEfs). - -## Tugas - -[Wawancara dengan data scientist](assignment.id.md) diff --git a/1-Introduction/4-techniques-of-ML/translations/README.it.md b/1-Introduction/4-techniques-of-ML/translations/README.it.md deleted file mode 100644 index d43f3b52..00000000 --- a/1-Introduction/4-techniques-of-ML/translations/README.it.md +++ /dev/null @@ -1,114 +0,0 @@ -# Tecniche di Machine Learning - -Il processo di creazione, utilizzo e mantenimento dei modelli di machine learning e dei dati che utilizzano è un processo molto diverso da molti altri flussi di lavoro di sviluppo. In questa lezione si demistifica il processo, e si delineano le principali tecniche che occorre conoscere. Si dovrà: - -- Comprendere i processi ad alto livello alla base di machine learning. -- Esplorare concetti di base come "modelli", "previsioni" e "dati di addestramento". - -## [Quiz pre-lezione](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/7/?loc=it) - -## Introduzione - -Ad alto livello, il mestiere di creare processi di apprendimento automatico (ML) comprende una serie di passaggi: - -1. **Decidere circa la domanda**. La maggior parte dei processi ML inizia ponendo una domanda alla quale non è possibile ottenere risposta da un semplice programma condizionale o da un motore basato su regole. Queste domande spesso ruotano attorno a previsioni basate su una raccolta di dati. -2. **Raccogliere e preparare i dati**. Per poter rispondere alla domanda, servono dati. La qualità e, a volte, la quantità dei dati determineranno quanto bene sarà possibile rispondere alla domanda iniziale. La visualizzazione dei dati è un aspetto importante di questa fase. Questa fase include anche la suddivisione dei dati in un gruppo di addestramento (training) e test per costruire un modello. -3. **Scegliere un metodo di addestramento**. A seconda della domanda e della natura dei dati, è necessario scegliere come si desidera addestrare un modello per riflettere al meglio i dati e fare previsioni accurate su di essi. Questa è la parte del processo di ML che richiede competenze specifiche e, spesso, una notevole quantità di sperimentazione. -4. **Addestrare il modello**. Usando i dati di addestramento, si utilizzeranno vari algoritmi per addestrare un modello a riconoscere modelli nei dati. Il modello potrebbe sfruttare pesi interni che possono essere regolati per privilegiare alcune parti dei dati rispetto ad altre per costruire un modello migliore. -5. **Valutare il modello**. Si utilizzano dati mai visti prima (i dati di test) da quelli raccolti per osservare le prestazioni del modello. -6. **Regolazione dei parametri**. In base alle prestazioni del modello, si puÃ˛ ripetere il processo utilizzando parametri differenti, o variabili, che controllano il comportamento degli algoritmi utilizzati per addestrare il modello. -7. **Prevedere**. Usare nuovi input per testare la precisione del modello. - -## Che domanda fare - -I computer sono particolarmente abili nello scoprire modelli nascosti nei dati. Questa caratteristica è molto utile per i ricercatori che hanno domande su un determinato campo a cui non è possibile rispondere facilmente creando un motore di regole basato su condizioni. Dato un compito attuariale, ad esempio, un data scientist potrebbe essere in grado di costruire manualmente regole sulla mortalità dei fumatori rispetto ai non fumatori. - -Quando molte altre variabili vengono introdotte nell'equazione, tuttavia, un modello ML potrebbe rivelarsi piÚ efficiente per prevedere i tassi di mortalità futuri in base alla storia sanitaria passata. Un esempio piÚ allegro potrebbe essere fare previsioni meteorologiche per il mese di aprile in una determinata località sulla base di dati che includono latitudine, longitudine, cambiamento climatico, vicinanza all'oceano, modelli della corrente a getto e altro ancora. - -✅ Questa [presentazione](https://www2.cisl.ucar.edu/sites/default/files/2021-10/0900%20June%2024%20Haupt_0.pdf) sui modelli meteorologici offre una prospettiva storica per l'utilizzo di ML nell'analisi meteorologica. - -## Attività di pre-costruzione - -Prima di iniziare a costruire il proprio modello, ci sono diverse attività da completare. Per testare la domanda e formare un'ipotesi basata sulle previsioni di un modello, occorre identificare e configurare diversi elementi. - -### Dati - -Per poter rispondere con sicurezza alla domanda, serve una buona quantità di dati del tipo giusto. Ci sono due cose da fare a questo punto: - -- **Raccogliere dati**. Tenendo presente la lezione precedente sull'equità nell'analisi dei dati, si raccolgano i dati con cura. Ci sia consapevolezza delle fonti di questi dati, di eventuali pregiudizi intrinseci che potrebbero avere e si documenti la loro origine. -- **Preparare i dati**. Ci sono diversi passaggi nel processo di preparazione dei dati. Potrebbe essere necessario raccogliere i dati e normalizzarli se provengono da fonti diverse. Si puÃ˛ migliorare la qualità e la quantità dei dati attraverso vari metodi come la conversione di stringhe in numeri (come si fa in [Clustering](../../../5-Clustering/1-Visualize/transaltions/README.it.md)). Si potrebbero anche generare nuovi dati, basati sull'originale (come si fa in [Classificazione](../../../4-Classification/1-Introduction/translations/README.it.md)). Si possono pulire e modificare i dati (come verrà fatto prima della lezione sull'[app Web](../../../3-Web-App/translations/README.it.md) ). Infine, si potrebbe anche aver bisogno di renderli casuali e mescolarli, a seconda delle proprie tecniche di addestramento. - -✅ Dopo aver raccolto ed elaborato i propri dati, si prenda un momento per vedere se la loro forma consentirà di rispondere alla domanda prevista. Potrebbe essere che i dati non funzionino bene nello svolgere il compito assegnato, come si scopre nelle lezioni di [Clustering](../../../5-Clustering/1-Visualize/translations/README.it.md)! - -### Caratteristiche e destinazione - -Una caratteristica è una proprietà misurabile dei dati. In molti set di dati è espresso come intestazione di colonna come 'date' 'size' o 'color'. La variabile di caratteristica, solitamente rappresentata come `X` nel codice, rappresenta la variabile di input che verrà utilizzata per il training del modello. - -Un obiettivo è una cosa che stai cercando di prevedere. Target solitamente rappresentato come `y` nel codice, rappresenta la risposta alla domanda che stai cercando di porre dei tuoi dati: a dicembre, di che colore saranno le zucche piÚ economiche? a San Francisco, quali quartieri avranno il miglior prezzo immobiliare? A volte la destinazione viene anche definita attributo label. - -### Selezione della variabile caratteristica - -🎓 **Selezione ed estrazione della caratteristica** Come si fa a sapere quale variabile scegliere quando si costruisce un modello? Probabilmente si dovrà passare attraverso un processo di selezione o estrazione delle caratteristiche per scegliere le variabili giuste per il modello piÚ efficace. Tuttavia, non è la stessa cosa: "L'estrazione delle caratteristiche crea nuove caratteristiche dalle funzioni delle caratteristiche originali, mentre la selezione delle caratteristiche restituisce un sottoinsieme delle caratteristiche". ([fonte](https://it.wikipedia.org/wiki/Selezione_delle_caratteristiche)) - -### Visualizzare i dati - -Un aspetto importante del bagaglio del data scientist è la capacità di visualizzare i dati utilizzando diverse eccellenti librerie come Seaborn o MatPlotLib. Rappresentare visivamente i propri dati potrebbe consentire di scoprire correlazioni nascoste che si possono sfruttare. Le visualizzazioni potrebbero anche aiutare a scoprire pregiudizi o dati sbilanciati (come si scopre in [Classificazione](../../../4-Classification/2-Classifiers-1/translations/README.it.md)). - -### Dividere l'insieme di dati - -Prima dell'addestramento, è necessario dividere l'insieme di dati in due o piÚ parti di dimensioni diverse che rappresentano comunque bene i dati. - -- **Addestramento**. Questa parte dell'insieme di dati è adatta al proprio modello per addestrarlo. Questo insieme costituisce la maggior parte dell'insieme di dati originale. -- **Test**. Un insieme di dati di test è un gruppo indipendente di dati, spesso raccolti dai dati originali, che si utilizzano per confermare le prestazioni del modello creato. -- **Convalida**. Un insieme di convalida è un gruppo indipendente piÚ piccolo di esempi da usare per ottimizzare gli iperparametri, o architettura, del modello per migliorarlo. A seconda delle dimensioni dei propri dati e della domanda che si sta ponendo, si potrebbe non aver bisogno di creare questo terzo insieme (come si nota in [Previsione delle Serie Temporali](../../../7-TimeSeries/1-Introduction/translations/README.it.md)). - -## Costruire un modello - -Utilizzando i dati di addestramento, l'obiettivo è costruire un modello o una rappresentazione statistica dei propri dati, utilizzando vari algoritmi per **addestrarlo** . L'addestramento di un modello lo espone ai dati e consente di formulare ipotesi sui modelli percepiti che scopre, convalida e accetta o rifiuta. - -### Decidere un metodo di addestramento - -A seconda della domanda e della natura dei dati, si sceglierà un metodo per addestrarlo. Passando attraverso [la documentazione di Scikit-learn](https://scikit-learn.org/stable/user_guide.html), che si usa in questo corso, si possono esplorare molti modi per addestrare un modello. A seconda della propria esperienza, si potrebbe dover provare diversi metodi per creare il modello migliore. È probabile che si attraversi un processo in cui i data scientist valutano le prestazioni di un modello fornendogli dati non visti, verificandone l'accuratezza, i pregiudizi e altri problemi che degradano la qualità e selezionando il metodo di addestramento piÚ appropriato per l'attività da svolgere. - -### Allenare un modello - -Armati dei tuoi dati di allenamento, sei pronto a "adattarlo" per creare un modello. Noterai che in molte librerie ML troverai il codice "model.fit" - è in questo momento che invii la tua variabile di funzionalità come matrice di valori (in genere `X`) e una variabile di destinazione (di solito `y`). - -### Valutare il modello - -Una volta completato il processo di addestramento (potrebbero essere necessarie molte iterazioni, o "epoche", per addestrare un modello di grandi dimensioni), si sarà in grado di valutare la qualità del modello utilizzando i dati di test per valutarne le prestazioni. Questi dati sono un sottoinsieme dei dati originali che il modello non ha analizzato in precedenza. Si puÃ˛ stampare una tabella di metriche sulla qualità del proprio modello. - -🎓 **Adattamento del modello** - -Nel contesto di machine learning, l'adattamento del modello si riferisce all'accuratezza della funzione sottostante del modello mentre tenta di analizzare dati con cui non ha familiarità. - -🎓 **Inadeguatezza** o **sovraadattamento** sono problemi comuni che degradano la qualità del modello, poichÊ il modello non si adatta abbastanza bene o troppo bene. CiÃ˛ fa sÃŦ che il modello esegua previsioni troppo allineate o troppo poco allineate con i suoi dati di addestramento. Un modello overfit (sovraaddestrato) prevede troppo bene i dati di addestramento perchÊ ha appreso troppo bene i dettagli e il rumore dei dati. Un modello underfit (inadeguato) non è accurato in quanto non puÃ˛ nÊ analizzare accuratamente i suoi dati di allenamento nÊ i dati che non ha ancora "visto". - -![modello sovraaddestrato](../images/overfitting.png) -> Infografica di [Jen Looper](https://twitter.com/jenlooper) - -## Sintonia dei parametri - -Una volta completato l'addestramento iniziale, si osservi la qualità del modello e si valuti di migliorarlo modificando i suoi "iperparametri". Maggiori informazioni sul processo [nella documentazione](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-tune-hyperparameters?WT.mc_id=academic-77952-leestott). - -## Previsione - -Questo è il momento in cui si possono utilizzare dati completamente nuovi per testare l'accuratezza del proprio modello. In un'impostazione ML "applicata", in cui si creano risorse Web per utilizzare il modello in produzione, questo processo potrebbe comportare la raccolta dell'input dell'utente (ad esempio, la pressione di un pulsante) per impostare una variabile e inviarla al modello per l'inferenza, oppure valutazione. - -In queste lezioni si scoprirà come utilizzare questi passaggi per preparare, costruire, testare, valutare e prevedere - tutti gesti di un data scientist e altro ancora, mentre si avanza nel proprio viaggio per diventare un ingegnere ML "full stack". - ---- - -## 🚀 Sfida - -Disegnare un diagramma di flusso che rifletta i passaggi di un professionista di ML. Dove ci si vede in questo momento nel processo? Dove si prevede che sorgeranno difficoltà? Cosa sembra facile? - -## [Quiz post-lezione](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/8/?loc=it) - -## Revisione e Auto Apprendimento - -Cercare online le interviste con i data scientist che discutono del loro lavoro quotidiano. Eccone [una](https://www.youtube.com/watch?v=Z3IjgbbCEfs). - -## Compito - -[Intervista a un data scientist](assignment.it.md) diff --git a/1-Introduction/4-techniques-of-ML/translations/README.ja.md b/1-Introduction/4-techniques-of-ML/translations/README.ja.md deleted file mode 100644 index d326dc6c..00000000 --- a/1-Introduction/4-techniques-of-ML/translations/README.ja.md +++ /dev/null @@ -1,114 +0,0 @@ -# 抟æĸ°å­Ļįŋ’ぎ手æŗ• - -抟æĸ°å­Ļįŋ’ãƒĸデãƒĢやそぎãƒĸデãƒĢがäŊŋį”¨ã™ã‚‹ãƒ‡ãƒŧã‚ŋを構į¯‰ãƒģäŊŋį”¨ãƒģįŽĄį†ã™ã‚‹ãƒ—ロã‚ģ゚は、äģ–ぎ多くぎ開į™ēワãƒŧクフロãƒŧとは全くį•°ãĒるもぎです。こぎãƒŦッ゚ãƒŗでは、こぎプロã‚ģ゚を明åŋĢãĢしãĻ、įŸĨãŖãĻおくずきä¸ģãĒ手æŗ•ãŽæĻ‚čĻã‚’ぞとめぞす。あãĒたは、 - -- 抟æĸ°å­Ļįŋ’を支えるプロã‚ģã‚šã‚’éĢ˜ã„æ°´æē–でį†č§Ŗしぞす。 -- 「ãƒĸデãƒĢ」「äēˆæ¸Ŧã€ã€Œč¨“įˇ´ãƒ‡ãƒŧã‚ŋ」ãĒおぎåŸēæœŦįš„ãĒæĻ‚åŋĩをčĒŋずぞす。 - -## [čŦ›įžŠå‰ãŽå°ãƒ†ã‚šãƒˆ](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/7?loc=ja) - -## 導å…Ĩ - -大ぞかãĢč¨€ã†ã¨ã€æŠŸæĸ°å­Ļįŋ’ (Machine Learning: ML) プロã‚ģã‚šã‚’äŊœæˆã™ã‚‹æŠ€čĄ“はいくつかぎ゚テップで構成されãĻいぞす。 - -1. **čŗĒ問をæąēめる**。ãģとんおぎ抟æĸ°å­Ļįŋ’プロã‚ģ゚は、単į´”ãĒæĄäģļぎプログナムやãƒĢãƒŧãƒĢベãƒŧ゚ぎエãƒŗジãƒŗではį­”えられãĒいようãĒčŗĒ問をすることから始ぞりぞす。こぎようãĒčŗĒ問は、デãƒŧã‚ŋぎ集合をäŊŋãŖたäēˆæ¸Ŧを中åŋƒãĢされることが多いです。 -2. **デãƒŧã‚ŋを集めãĻæē–備する**。čŗĒ問ãĢį­”えるためãĢはデãƒŧã‚ŋがåŋ…čĻã§ã™ã€‚デãƒŧã‚ŋぎčŗĒと、ときãĢは量が、最初ぎčŗĒ問ãĢおれだけうぞくį­”えられるかをæąēめぞす。デãƒŧã‚ŋぎ可čĻ–化がこぎフェãƒŧã‚ēぎ重čĻãĒ側éĸです。ãƒĸデãƒĢを構į¯‰ã™ã‚‹ãŸã‚ãĢデãƒŧã‚ŋã‚’č¨“įˇ´ã‚°ãƒĢãƒŧプとテ゚トグãƒĢãƒŧプãĢ分けることもこぎフェãƒŧã‚ēãĢåĢãŋぞす。 -3. **å­Ļįŋ’æ–šæŗ•ã‚’選ãļ**。čŗĒ問ぎ内厚やデãƒŧã‚ŋぎ性čŗĒãĢåŋœã˜ãĻ、デãƒŧã‚ŋã‚’æœ€ã‚‚č‰¯ãåæ˜ ã—ãĻæ­ŖįĸēãĢäēˆæ¸ŦできるãƒĸデãƒĢを、おぎようãĢå­Ļįŋ’するかを選ãļåŋ…čĻãŒã‚りぞす。これは抟æĸ°å­Ļįŋ’プロã‚ģ゚ぎ中でも、į‰šåŽšãŽå°‚é–€įŸĨč­˜ã¨ã€å¤šããŽå ´åˆã¯ã‹ãĒりぎčŠĻčĄŒå›žæ•°ãŒåŋ…čĻãĢãĒる部分です。 -4. **ãƒĸデãƒĢをå­Ļįŋ’する**。デãƒŧã‚ŋぎパã‚ŋãƒŧãƒŗをčĒč­˜ã™ã‚‹ãƒĸデãƒĢをå­Ļįŋ’するためãĢã€č¨“įˇ´ãƒ‡ãƒŧã‚ŋと様々ãĒã‚ĸãƒĢゴãƒĒã‚ēムをäŊŋいぞす。ãƒĸデãƒĢã¯ã‚ˆã‚Šč‰¯ã„ãƒĸデãƒĢを構į¯‰ã™ã‚‹ãŸã‚ãĢ、デãƒŧã‚ŋぎį‰šåŽšãŽéƒ¨åˆ†ã‚’å„Ē先するようãĢčĒŋ整できる内部ぎ重ãŋをæ´ģį”¨ã™ã‚‹ã‹ã‚‚しれぞせん。 -5. **ãƒĸデãƒĢã‚’čŠ•äžĄã™ã‚‹**。ãƒĸデãƒĢがおぎようãĢ動äŊœã—ãĻいるかをįĸēčĒã™ã‚‹ãŸã‚ãĢ、集めたデãƒŧã‚ŋぎ中からぞだčĻ‹ãŸã“とぎãĒいもぎīŧˆãƒ†ã‚šãƒˆãƒ‡ãƒŧã‚ŋīŧ‰ã‚’äŊŋいぞす。 -6. **ãƒ‘ãƒŠãƒĄãƒŧã‚ŋチãƒĨãƒŧニãƒŗグ**。ãƒĸデãƒĢぎ性čƒŊãĢよãŖãĻは、ãƒĸデãƒĢをå­Ļįŋ’するためãĢäŊŋわれる、各ã‚ĸãƒĢゴãƒĒã‚ēムぎ挙動をåˆļåžĄã™ã‚‹ãƒ‘ãƒŠãƒĄãƒŧã‚ŋや変数を変更しãĻプロã‚ģã‚šã‚’ã‚„ã‚Šį›´ã™ã“ともできぞす。 -7. **äēˆæ¸Ŧする**。ãƒĸデãƒĢぎį˛žåēĻをテ゚トするためãĢ新しいå…Ĩ力をäŊŋいぞす。 - -## おぎようãĒčŗĒå•ã‚’ã™ã‚Œã°č‰¯ã„ã‹ - -ã‚ŗãƒŗピãƒĨãƒŧã‚ŋはデãƒŧã‚ŋぎ中ãĢ隠れãĻいるパã‚ŋãƒŧãƒŗをčĻ‹ã¤ã‘ることがとãĻも垗意です。こぎ有į”¨æ€§ã¯ã€æĄäģļベãƒŧ゚ぎãƒĢãƒŧãƒĢエãƒŗジãƒŗをäŊœãŖãĻもį°Ąå˜ãĢはį­”えられãĒいようãĒ、į‰šåŽšãŽé ˜åŸŸãĢé–ĸするčŗĒ問を持ãŖãĻいるį ”įŠļ者ãĢとãŖãĻ非常ãĢåŊšįĢ‹ãĄãžã™ã€‚たとえば、あるäŋé™ē数į†ãŽå•éĄŒãŒã‚ãŖたとしãĻ、デãƒŧã‚ŋã‚ĩイエãƒŗテã‚Ŗ゚トはå–Ģį…™č€…と非å–Ģį…™č€…ぎæ­ģäēĄįŽ‡ãĢé–ĸするæŗ•å‰‡ã‚’č‡Ē分ぎ手だけでもäŊœã‚Œã‚‹ã‹ã‚‚しれぞせん。 - -しかし、äģ–ãĢも多くぎ変数が斚į¨‹åŧãĢåĢぞれる場合、過åŽģぎåĨåēˇįŠļ態から将æĨぎæ­ģäēĄįŽ‡ã‚’äēˆæ¸Ŧする抟æĸ°å­Ļįŋ’ãƒĸデãƒĢぎ斚が劚įŽ‡įš„かもしれぞせん。もãŖと明るいテãƒŧマぎ䞋としãĻは、įˇ¯åēĻ、įĩŒåēĻ、気候変動、æĩˇã¸ãŽčŋ‘さ、ジェット気æĩãŽãƒ‘ã‚ŋãƒŧãƒŗãĒおぎデãƒŧã‚ŋãĢåŸēãĨいãĻ、į‰šåŽšãŽå ´æ‰€ãĢおける4月ぎ夊気をäēˆæ¸Ŧすることができぞす。 - -✅ æ°—čąĄãƒĸデãƒĢãĢé–ĸするこぎ [゚ナイド](https://www2.cisl.ucar.edu/sites/default/files/2021-10/0900%20June%2024%20Haupt_0.pdf) ã¯ã€æ°—čąĄč§Ŗ析ãĢ抟æĸ°å­Ļįŋ’ã‚’äŊŋã†éš›ãŽæ­´å˛įš„ãĒč€ƒãˆæ–šã‚’į¤ēしãĻいぞす。 - -## 構į¯‰å‰ãŽã‚ŋ゚ク - -ãƒĸデãƒĢぎ構į¯‰ã‚’始める前ãĢ、いくつかぎã‚ŋ゚クを厌äē†ã•ã›ã‚‹åŋ…čĻãŒã‚りぞす。čŗĒ問をテ゚トしたりãƒĸデãƒĢぎäēˆæ¸ŦãĢåŸēãĨいたäģŽčĒŦをįĢ‹ãĻたりするためãĢは、いくつかぎčĻį´ ã‚’į‰šåŽšã—ãĻč¨­åŽšã™ã‚‹åŋ…čĻãŒã‚りぞす。 - -### デãƒŧã‚ŋ - -čŗĒ問ãĢįĸē原ãĢį­”えるためãĢは、遊切ãĒį¨ŽéĄžãŽãƒ‡ãƒŧã‚ŋが大量ãĢåŋ…čĻãĢãĒりぞす。ここではやるずきことが2つありぞす。 - -- **デãƒŧã‚ŋを集める**。デãƒŧã‚ŋč§Ŗ析ãĢおけるå…Ŧåšŗ性ãĢé–ĸする前回ぎčŦ›įžŠã‚’思いå‡ēしãĒがら、慎重ãĢデãƒŧã‚ŋを集めãĻください。į‰šåŽšãŽãƒã‚¤ã‚ĸ゚を持ãŖãĻいるかもしれãĒいデãƒŧã‚ŋぎã‚Ŋãƒŧã‚šãĢæŗ¨æ„ã—ã€ãã‚Œã‚’č¨˜éŒ˛ã—ãĻおいãĻください。 -- **デãƒŧã‚ŋをæē–備する**。デãƒŧã‚ŋをæē–備するプロã‚ģã‚šãĢはいくつかぎ゚テップがありぞす。į•°ãĒるã‚Ŋãƒŧ゚からデãƒŧã‚ŋを集めた場合、į…§åˆã¨æ­ŖčĻåŒ–がåŋ…čĻãĢãĒるかもしれぞせん。īŧˆ[クナ゚ã‚ŋãƒĒãƒŗグ](../../../5-Clustering/1-Visualize/README.md) ã§čĄŒãŖãĻいるようãĢ、īŧ‰æ–‡å­—列を数値ãĢ変換するãĒおぎ様々ãĒæ–šæŗ•ã§ãƒ‡ãƒŧã‚ŋぎčŗĒと量を向上させることができぞす。īŧˆ[åˆ†éĄž](../../../4-Classification/1-Introduction/README.md) ã§čĄŒãŖãĻいるようãĢ、īŧ‰å…ƒãŽãƒ‡ãƒŧã‚ŋから新しいデãƒŧã‚ŋをį”Ÿæˆã™ã‚‹ã“ともできぞす。īŧˆ[Webã‚ĸプãƒĒ](../../../3-Web-App/README.md) ぎčŦ›įžŠãŽå‰ãĢčĄŒã†ã‚ˆã†ãĢ、īŧ‰ãƒ‡ãƒŧã‚ŋをクãƒĒãƒŧニãƒŗグしたりįˇ¨é›†ã—たりすることができぞす。最垌ãĢ、å­Ļįŋ’ぎ手æŗ•ãĢよãŖãĻは、ナãƒŗダムãĢã—ãŸã‚Šã‚ˇãƒŖッフãƒĢしたりするåŋ…čĻã‚‚あるかもしれぞせん。 - -✅ デãƒŧã‚ŋを集めãĻå‡Ļį†ã—た垌は、そぎåŊĸで意å›ŗしたčŗĒ問ãĢ寞åŋœã§ãã‚‹ã‹ãŠã†ã‹ã‚’įĸēčĒã—ãĻãŋぞしょう。[クナ゚ã‚ŋãƒĒãƒŗグ](../../../5-Clustering/1-Visualize/README.md) ぎčŦ›įžŠã§ã‚ã‹ã‚‹ã‚ˆã†ãĢ、デãƒŧã‚ŋは与えられたã‚ŋ゚クãĢ寞しãĻ上手く抟čƒŊしãĒいかもしれぞせんīŧ - -### 抟čƒŊとã‚ŋãƒŧã‚˛ãƒƒãƒˆ - -フã‚ŖãƒŧチãƒŖは、デãƒŧã‚ŋぎæ¸Ŧ厚可čƒŊãĒプロパテã‚Ŗです。多くぎデãƒŧã‚ŋã‚ģットでは、'æ—Ĩäģ˜' 'ã‚ĩイã‚ē' や '色' ぎようãĒ列čĻ‹å‡ēしとしãĻ襨įžã•ã‚Œãžã™ã€‚通常、ã‚ŗãƒŧドでは `X` としãĻčĄ¨ã•ã‚Œã‚‹ãƒ•ã‚ŖãƒŧチãƒŖ変数は、ãƒĸデãƒĢぎトãƒŦãƒŧニãƒŗグãĢäŊŋį”¨ã•ã‚Œã‚‹å…ĨåŠ›å¤‰æ•°ã‚’čĄ¨ã—ãžã™ - -ã‚ŋãƒŧã‚˛ãƒƒãƒˆã¯ã€äēˆæ¸ŦしようとしãĻいるもぎです。ã‚ŋãƒŧã‚˛ãƒƒãƒˆã¯é€šå¸¸ã€ã‚ŗãƒŧドで`y`としãĻčĄ¨ã•ã‚Œã€ã‚ãĒたぎデãƒŧã‚ŋを尋ねようとしãĻいるčŗĒ問ãĢ寞するį­”ãˆã‚’čĄ¨ã—ãžã™:12月ãĢã€ãŠãŽč‰˛ãŽã‚ĢボチãƒŖが最も厉くãĒりぞすか?ã‚ĩãƒŗフナãƒŗã‚ˇã‚šã‚ŗでは、おぎ地域が最éĢ˜ãŽä¸å‹•į”Ŗ䞥æ ŧを持つでしょうか?ã‚ŋãƒŧã‚˛ãƒƒãƒˆã¯ãƒŠãƒ™ãƒĢåąžæ€§ã¨ã‚‚å‘ŧばれることもありぞす。 - -### į‰šåž´é‡ãŽé¸æŠž - -🎓 **į‰šåž´é¸æŠžã¨į‰šåž´æŠŊå‡ē** ãƒĸデãƒĢを構į¯‰ã™ã‚‹éš›ãĢおぎ変数を選ãļずきかは、おうすればわかるでしょうかīŧŸæœ€ã‚‚性čƒŊぎéĢ˜ã„ãƒĸデãƒĢぎためãĢは、遊した変数を選択するį‰šåž´é¸æŠžã‚„į‰šåž´æŠŊå‡ēぎプロã‚ģ゚をたおることãĢãĒるでしょう。しかし、これらは同じもぎではありぞせん。「į‰šåž´æŠŊå‡ēは元ぎį‰šåž´ãŽæŠŸčƒŊから新しいį‰šåž´ã‚’äŊœæˆã™ã‚‹ãŽãĢ寞し、į‰šåž´é¸æŠžã¯į‰šåž´ãŽä¸€éƒ¨ã‚’čŋ”すもぎです。」 ([å‡ē典](https://wikipedia.org/wiki/Feature_selection)) - -### デãƒŧã‚ŋを可čĻ–化する - -デãƒŧã‚ŋã‚ĩイエãƒŗテã‚Ŗã‚šãƒˆãŽé“å…ˇãĢé–ĸする重čĻãĒ側éĸは、Seaborn や MatPlotLib ãĒおぎå„ĒれたナイブナãƒĒをäŊŋãŖãĻデãƒŧã‚ŋを可čĻ–化する力です。デãƒŧã‚ŋをčĻ–čĻšįš„ãĢ襨įžã™ã‚‹ã“とで、隠れたį›¸é–ĸé–ĸäŋ‚ã‚’čĻ‹ã¤ã‘ãĻæ´ģį”¨ã§ãã‚‹ã‹ã‚‚しれぞせん。ぞた、īŧˆ[åˆ†éĄž](../../../4-Classification/2-Classifiers-1/README.md) でわかるようãĢ、īŧ‰čĻ–čĻšåŒ–することで、バイã‚ĸ゚やバナãƒŗã‚ˇãƒŗグされãĻいãĒいデãƒŧã‚ŋをčĻ‹ã¤ã‘られるかもしれぞせん。 - -### デãƒŧã‚ŋã‚ģãƒƒãƒˆã‚’åˆ†å‰˛ã™ã‚‹ - -å­Ļįŋ’ぎ前ãĢデãƒŧã‚ŋã‚ģットを2つäģĨ上ãĢåˆ†å‰˛ã—ãĻ、それぞれがデãƒŧã‚ŋã‚’čĄ¨ã™ãŽãĢ十分かつ不均į­‰ãĒ大きさãĢするåŋ…čĻãŒã‚りぞす。 - -- **å­Ļįŋ’**。デãƒŧã‚ŋã‚ģットぎこぎ部分は、ãƒĸデãƒĢをå­Ļįŋ’するためãĢ遊合させぞす。これは元ぎデãƒŧã‚ŋã‚ģットぎ大部分を占めぞす。 -- **テ゚ト**。テ゚トデãƒŧã‚ŋã‚ģットとは、構į¯‰ã—たãƒĸデãƒĢぎ性čƒŊをįĸēčĒã™ã‚‹ãŸã‚ãĢäŊŋį”¨ã™ã‚‹į‹ŦįĢ‹ã—たデãƒŧã‚ŋグãƒĢãƒŧプぎことで、多くぎ場合は元ぎデãƒŧã‚ŋから集められぞす。 -- **検č¨ŧ**。検č¨ŧã‚ģットとは、さらãĢ小さくãĻį‹ŦįĢ‹ã—たã‚ĩãƒŗプãƒĢぎ集合ぎことで、ãƒĸデãƒĢを攚善するためãĢハイパãƒŧãƒ‘ãƒŠãƒĄãƒŧã‚ŋや構造をčĒŋ整する際ãĢäŊŋį”¨ã•ã‚Œãžã™ã€‚īŧˆ[時įŗģ列äēˆæ¸Ŧ](../../../7-TimeSeries/1-Introduction/README.md) ãĢ記čŧ‰ã—ãĻいるようãĢ、īŧ‰ãƒ‡ãƒŧã‚ŋぎ大きさやčŗĒ問ぎ内厚ãĢよãŖãĻは、こぎ3つį›ŽãŽã‚ģットをäŊœã‚‹åŋ…čĻã¯ã‚りぞせん。 - -## ãƒĸデãƒĢぎ構į¯‰ - -訓įˇ´ãƒ‡ãƒŧã‚ŋと様々ãĒã‚ĸãƒĢゴãƒĒã‚ēムをäŊŋãŖた **å­Ļįŋ’** ãĢよãŖãĻ、ãƒĸデãƒĢもしくはデãƒŧã‚ŋぎįĩąč¨ˆįš„ãĒ襨įžã‚’構į¯‰ã™ã‚‹ã“とがį›Žæ¨™ã§ã™ã€‚ãƒĸデãƒĢをå­Ļįŋ’することで、デãƒŧã‚ŋã‚’æ‰ąãˆã‚‹ã‚ˆã†ãĢãĒãŖたり、į™ēčĻ‹ã€æ¤œč¨ŧã€č‚¯åŽšãžãŸã¯åĻ厚したパã‚ŋãƒŧãƒŗãĢé–ĸするäģŽčĒŦをįĢ‹ãĻることができたりしぞす。 - -### å­Ļįŋ’æ–šæŗ•ã‚’æąēめる - -čŗĒ問ぎ内厚やデãƒŧã‚ŋぎ性čŗĒãĢåŋœã˜ãĻ、ãƒĸデãƒĢをå­Ļįŋ’する斚æŗ•ã‚’選択しぞす。こぎã‚ŗãƒŧ゚でäŊŋį”¨ã™ã‚‹ [Scikit-learn ぎドキãƒĨãƒĄãƒŗト](https://scikit-learn.org/stable/user_guide.html) をčĻ‹ã‚‹ã¨ã€ãƒĸデãƒĢをå­Ļįŋ’する様々ãĒæ–šæŗ•ã‚’čĒŋずられぞす。įĩŒé¨“æŦĄįŦŦでは、最遊ãĒãƒĸデãƒĢを構į¯‰ã™ã‚‹ãŸã‚ãĢいくつかぎį•°ãĒã‚‹æ–šæŗ•ã‚’čŠĻすåŋ…čĻãŒã‚るかもしれぞせん。ぞた、ãƒĸデãƒĢがčĻ‹ãŸã“とぎãĒいデãƒŧã‚ŋを与えたり、čŗĒを下げãĻã„ã‚‹å•éĄŒã€į˛žåēĻ、バイã‚ĸã‚šãĢついãĻčĒŋずたり、ã‚ŋ゚クãĢ寞しãĻ最遊ãĒå­Ļįŋ’æ–šæŗ•ã‚’選んだりすることで、デãƒŧã‚ŋã‚ĩイエãƒŗテã‚Ŗã‚šãƒˆãŒčĄŒãŖãĻいる、ãƒĸデãƒĢぎ性čƒŊã‚’čŠ•äžĄã™ã‚‹ãƒ—ãƒ­ã‚ģã‚šã‚’č¸ã‚€ã“ã¨ãĢãĒるでしょう。 - -### ãƒĸデãƒĢをå­Ļįŋ’する - -トãƒŦãƒŧニãƒŗグデãƒŧã‚ŋをäŊŋį”¨ã—ãĻ、ãƒĸデãƒĢをäŊœæˆã™ã‚‹ãŸã‚ãĢ「フã‚Ŗット」するæē–備が整いぞした。多くぎ ML ナイブナãƒĒでは、ã‚ŗãƒŧド 'model.fit' がčĻ‹ã¤ã‹ã‚Šãžã™ - こぎ時į‚šã§ã€å€¤ãŽé…åˆ— (通常は `X`) とã‚ŋãƒŧã‚˛ãƒƒãƒˆå¤‰æ•° (通常は `y`) としãĻ抟čƒŊ変数を送äŋĄã—ぞす。 - -### ãƒĸデãƒĢã‚’čŠ•äžĄã™ã‚‹ - -īŧˆå¤§ããĒãƒĸデãƒĢをå­Ļįŋ’するãĢは多くぎ反垊īŧˆã‚¨ãƒãƒƒã‚¯īŧ‰ãŒåŋ…čĻãĢãĒりぞすが、īŧ‰å­Ļįŋ’プロã‚ģ゚が厌äē†ã—たら、テ゚トデãƒŧã‚ŋをäŊŋãŖãĻãƒĸデãƒĢぎčŗĒã‚’čŠ•äžĄã™ã‚‹ã“ã¨ãŒã§ããžã™ã€‚ã“ãŽãƒ‡ãƒŧã‚ŋは元ぎデãƒŧã‚ŋãŽã†ãĄã€ãƒĸデãƒĢがそれぞでãĢ分析しãĻいãĒいもぎです。ãƒĸデãƒĢぎčŗĒã‚’čĄ¨ã™æŒ‡æ¨™ãŽčĄ¨ã‚’å‡ē力することができぞす。 - -🎓 **ãƒĸデãƒĢフã‚Ŗッテã‚Ŗãƒŗグ** - -抟æĸ°å­Ļįŋ’ãĢおけるãƒĸデãƒĢフã‚Ŗッテã‚Ŗãƒŗグは、ãƒĸデãƒĢがぞだįŸĨらãĒいデãƒŧã‚ŋを分析する際ぎ栚æœŦįš„ãĒ抟čƒŊぎį˛žåēĻを参į…§ã—ぞす。 - -🎓 **æœĒå­Ļįŋ’** と **過å­Ļįŋ’** はãƒĸデãƒĢぎčŗĒを下げる一čˆŦįš„ãĒå•éĄŒã§ã€ãƒĸデãƒĢが十分ãĢ遊合しãĻいãĒいか、ぞたは遊合しすぎãĻいぞす。これãĢよãŖãĻãƒĸデãƒĢã¯č¨“įˇ´ãƒ‡ãƒŧã‚ŋãĢčŋ‘すぎたり遠すぎたりするäēˆæ¸Ŧã‚’čĄŒã„ãžã™ã€‚éŽå­Ļįŋ’ãƒĸデãƒĢは、デãƒŧã‚ŋぎčŠŗį´°ã‚„ノイã‚ēもよくå­Ļįŋ’しãĻã„ã‚‹ãŸã‚ã€č¨“įˇ´ãƒ‡ãƒŧã‚ŋを上手くäēˆæ¸ŦしすぎãĻしぞいぞす。æœĒå­Ļįŋ’ãƒĸデãƒĢã¯ã€č¨“įˇ´ãƒ‡ãƒŧã‚ŋやぞだ「čĻ‹ãŸã“とぎãĒい」デãƒŧã‚ŋをæ­ŖįĸēãĢ分析することができãĒいため、į˛žåēĻがéĢ˜ããĒいです。 - -![過å­Ļįŋ’ãƒĸデãƒĢ](../images/overfitting.png) -> [Jen Looper](https://twitter.com/jenlooper) さんãĢよるč§ŖčĒŦį”ģ像 - -## ãƒ‘ãƒŠãƒĄãƒŧã‚ŋチãƒĨãƒŧニãƒŗグ - -最初ぎトãƒŦãƒŧニãƒŗグが厌äē†ã—たら、ãƒĸデãƒĢぎčŗĒをčĻŗ察しãĻ、「ハイパãƒŧãƒ‘ãƒŠãƒĄãƒŧã‚ŋ」ぎčĒŋ整ãĢよるãƒĸデãƒĢãŽæ”šå–„ã‚’æ¤œč¨Žã—ãžã—ã‚‡ã†ã€‚ã“ãŽãƒ—ãƒ­ã‚ģã‚šãĢついãĻは [ドキãƒĨãƒĄãƒŗト](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-tune-hyperparameters?WT.mc_id=academic-77952-leestott) をčĒ­ã‚“でください。 - -## äēˆæ¸Ŧ - -全く新しいデãƒŧã‚ŋをäŊŋãŖãĻãƒĸデãƒĢぎį˛žåēĻをテ゚トするįžŦ間です。æœŦį•Ēį’°åĸƒã§ãƒĸデãƒĢをäŊŋį”¨ã™ã‚‹ãŸã‚ãĢWebã‚ĸã‚ģットを構į¯‰ã™ã‚‹ã‚ˆã†ã€ŒéŠį”¨ã•ã‚ŒãŸã€æŠŸæĸ°å­Ļįŋ’ãŽč¨­åŽšãĢおいãĻは、推čĢ–ã‚„čŠ•äžĄãŽãŸã‚ãĢãƒĸデãƒĢãĢæ¸Ąã—ãŸã‚Šã€å¤‰æ•°ã‚’č¨­åŽšã—ãŸã‚Šã™ã‚‹ãŸã‚ãĢãƒĻãƒŧã‚ļぎå…Ĩ力īŧˆãƒœã‚ŋãƒŗぎæŠŧ下ãĒおīŧ‰ã‚’収集することがこぎプロã‚ģã‚šãĢåĢぞれるかもしれぞせん。 - -こぎčŦ›įžŠã§ã¯ã€ã€Œãƒ•ãƒĢã‚šã‚ŋック」ぎ抟æĸ°å­Ļįŋ’エãƒŗジニã‚ĸãĢãĒるためぎ旅をしãĒがら、æē–å‚™ãƒģ構į¯‰ãƒģテ゚トãƒģ評価ãƒģäēˆæ¸ŦãĒおぎデãƒŧã‚ŋã‚ĩイエãƒŗテã‚Ŗã‚šãƒˆãŒčĄŒã†ã™ãšãĻぎ゚テップぎäŊŋい斚をå­Ļãŗぞす。 - ---- - -## đŸš€ãƒãƒŖãƒŦãƒŗジ - -抟æĸ°å­Ļįŋ’ぎå­Ļįŋ’č€…ãŽã‚šãƒ†ãƒƒãƒ—ã‚’åæ˜ ã—ãŸãƒ•ãƒ­ãƒŧチãƒŖãƒŧトを描いãĻください。äģŠãŽč‡Ē分はこぎプロã‚ģ゚ぎおこãĢいると思いぞすかīŧŸãŠã“ãĢ困é›ŖがあるとäēˆæƒŗしぞすかīŧŸã‚ãĒたãĢとãŖãĻį°Ąå˜ãã†ãĒことはäŊ•ã§ã™ã‹īŧŸ - -## [čŦ›įžŠåžŒãŽå°ãƒ†ã‚šãƒˆ](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/8?loc=ja) - -## 振りčŋ”りとč‡Ēä¸ģå­Ļįŋ’ - -デãƒŧã‚ŋã‚ĩイエãƒŗテã‚Ŗ゚トがæ—Ĩ々ぎäģ•äē‹ãĢついãĻčŠąã—ãĻいるイãƒŗã‚ŋビãƒĨãƒŧをネットで検į´ĸしãĻãŋãžã—ã‚‡ã†ã€‚ã˛ã¨ã¤ã¯ [これ](https://www.youtube.com/watch?v=Z3IjgbbCEfs) です。 - -## čĒ˛éĄŒ - -[デãƒŧã‚ŋã‚ĩイエãƒŗテã‚Ŗ゚トãĢイãƒŗã‚ŋビãƒĨãƒŧする](assignment.ja.md) diff --git a/1-Introduction/4-techniques-of-ML/translations/README.ko.md b/1-Introduction/4-techniques-of-ML/translations/README.ko.md deleted file mode 100644 index 5b67f6ad..00000000 --- a/1-Introduction/4-techniques-of-ML/translations/README.ko.md +++ /dev/null @@ -1,114 +0,0 @@ -# 머ė‹ ëŸŦ닝ė˜ 기ėˆ  - -머ė‹ ëŸŦ닝 ëĒ¨ë¸ęŗŧ ė´ëĨŧ ė‚ŦėšŠí•˜ëŠ” 데ė´í„°ëĨŧ ęĩŦėļ•, ė‚ŦėšŠ, ꡸ëĻŦęŗ  관ëĻŦ하는 프로ė„¸ėŠ¤ëŠ” 많ė€ 타 개발 ė›ŒíŦ플로ėš°ė™€ 매ėš° 다ëĨ¸ 프로ė„¸ėŠ¤ėž…니다. ė´ 강ė˜ė—ė„œ, 프로ė„¸ėŠ¤ëĨŧ ė´í•´í•˜ęŗ , ė•Œė•„ė•ŧ 할 ėŖŧėš” 기ėˆ ė„ 간단히 ė„¤ëĒ…핊니다: - -- 머ė‹ ëŸŦ닝ė„ 받ėŗėŖŧ는 프로ė„¸ėŠ¤ëĨŧ ęŗ ėˆ˜ė¤€ė—ė„œ ė´í•´í•Šë‹ˆë‹¤. -- 'models', 'predictions', ꡸ëĻŦęŗ  'training data'ė™€ 같ė€ 기ė´ˆ 개념ė„ 탐ėƒ‰í•Šë‹ˆë‹¤. - -## [강ė˜ ė „ 퀴ėĻˆ](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/7/) - -## ė†Œę°œ - -ęŗ ėˆ˜ė¤€ė—ė„œ, 머ė‹ ëŸŦ닝 (ML) 프로ė„¸ėŠ¤ëĨŧ 만드는 기ėˆ ė€ ė—ŦëŸŦ 단ęŗ„ëĄœ ęĩŦė„ąëŠë‹ˆë‹¤: - -1. **ė§ˆëŦ¸ 결ė •í•˜ę¸°**. 대ëļ€ëļ„ ML 프로ė„¸ėŠ¤ëŠ” 간단 ėĄ°ęą´ 프로그램 또는 ëŖ°-베ė´ėŠ¤ ė—”ė§„ėœŧ로 대ë‹ĩ할 ėˆ˜ ė—†ëŠ” ė§ˆëŦ¸ė„ 하는 것ėœŧ로 ė‹œėž‘핊니다. ė´ ė§ˆëŦ¸ė€ 가끔 데ė´í„° ė…‹ė„ 기반ėœŧ로 한 ė˜ˆė¸Ąė„ ė¤‘ė‹Ŧėœŧ로 ė§„행됊니다. -2. **데ė´í„° ėˆ˜ė§‘ 및 ė¤€ëš„í•˜ę¸°**. ė§ˆëŦ¸ė— 대ë‹ĩ하려면, 데ė´í„°ę°€ 필ėš”핊니다. 데ė´í„°ė˜ 품ė§ˆęŗŧ, 때때로, ė–‘ė— 따ëŧ ė´ˆę¸° ė§ˆëŦ¸ė— ėž˜ 대ë‹ĩ할 ėˆ˜ ėžˆëŠ” ė§€ 결ė •ëŠë‹ˆë‹¤. 데ė´í„° ė‹œę°í™”는 ė´ ė¸ĄëŠ´ė—ė„œ ė¤‘ėš”핊니다. ė´ 단ęŗ„ė—ė„œ 데ė´í„°ëĨŧ 훈련ęŗŧ 테ėŠ¤íŠ¸ ꡸ëŖšėœŧ로 ëļ„할하ė—Ŧ ëĒ¨ë¸ė„ ęĩŦėļ•í•˜ëŠ” 게 íŦ함됩니다. -3. **학ėŠĩ ë°Šė‹ ė„ íƒí•˜ę¸°**. ė§ˆëŦ¸ęŗŧ 데ė´í„°ė˜ 특ė„ąė— 따ëŧ, 데ė´í„°ëĨŧ 가ėžĨ ėž˜ 반ė˜í•˜ęŗ  ė •í™•í•œ ė˜ˆė¸Ąė„ 할 ėˆ˜ ėžˆę˛Œ 훈련하는 방법ė„ ė„ íƒí•´ė•ŧ 합니다. 특ė • ė „ëŦ¸ ė§€ė‹ęŗŧ, ė§€ė†ė ėœŧ로, 많ė€ ė‹¤í—˜ė´ 필ėš”í•œ ML 프로ė„¸ėŠ¤ė˜ ėŧëļ€ëļ„ėž…니다. -4. **ëĒ¨ë¸ 학ėŠĩ하기**. 학ėŠĩ 데ė´í„°ëĄœ, 다ė–‘í•œ ė•Œęŗ ëĻŦėĻ˜ė„ ė‚ŦėšŠí•˜ė—Ŧ 데ė´í„°ė˜ 패턴ė„ ė¸ė‹í•˜ę˛Œ ëĒ¨ë¸ė„ 학ėŠĩė‹œí‚ĩ니다. ëĒ¨ë¸ė„ 더 ėĸ‹ę˛Œ 만들기 ėœ„하ė—Ŧ 데ė´í„°ė˜ 특ė • ëļ€ëļ„ė„ 타 ëļ€ëļ„ëŗ´ë‹¤ ë¨ŧė € 하도록 ėĄ°ė •í•  ėˆ˜ ėžˆë„록 내ëļ€ 가ė¤‘ėš˜ëĨŧ 활ėšŠí•  ėˆ˜ ėžˆėŠĩ니다. -5. **ëĒ¨ë¸ 평가하기**. ėˆ˜ė§‘í•œ ė…‹ė—ė„œ ė´ė „ė— ëŗ¸ ė  ė—†ëŠ” 데ė´í„° (테ėŠ¤íŠ¸ 데ė´í„°)로 ëĒ¨ë¸ė˜ ė„ąëŠĨė„ 확ė¸í•Šë‹ˆë‹¤. -6. **파ëŧ미터 튜닝하기**. ëĒ¨ë¸ė˜ ė„ąëŠĨė„ 기반해ė„œ, ëĒ¨ë¸ 학ėŠĩėœŧ로 ė•Œęŗ ëĻŦėĻ˜ė˜ 동ėž‘ė„ ėģ¨íŠ¸ëĄ¤í•˜ëŠ” 다ëĨ¸ 파ëŧ미터, 또는 ëŗ€ėˆ˜ëĨŧ, ė‚ŦėšŠí•´ė„œ 프로ė„¸ėŠ¤ëĨŧ 다ė‹œ ė‹¤í–‰í•  ėˆ˜ ėžˆėŠĩ니다. -7. **ė˜ˆė¸Ąí•˜ę¸°**. ëĒ¨ë¸ė˜ ė •í™•ė„ąė„ ėƒˆëĄœėš´ ėž…ë Ĩėœŧ로 테ėŠ¤íŠ¸í•Šë‹ˆë‹¤. - -## ëŦŧė–´ëŗŧ ė§ˆëŦ¸í•˜ę¸° - -ėģ´í“¨í„°ëŠ” 데ė´í„°ė—ė„œ ėˆ¨ę˛¨ė§„ 패턴 ė°žëŠ” 것ė„ ėž˜í•Šë‹ˆë‹¤. ėœ í‹¸ëĻŦ티는 ėĄ°ęą´-기반 ëŖ° ė—”ė§„ė„ 만들ė–´ė„œ ė‰Ŋ게 ë‹ĩ할 ėˆ˜ ė—†ëŠ” 도메ė¸ė— 대해 ė§ˆëŦ¸í•˜ëŠ” ė—°ęĩŦė›ė—ę˛Œ 매ėš° 도ė›€ė´ 됩니다. ė˜ˆëĨŧ 들ė–´ė„œ, actuarial ėž‘ė—…ė´ ėŖŧė–´ė§€ëŠ´, 데ė´í„° ė‚Ŧė´ė–¸í‹°ėŠ¤íŠ¸ëŠ” 흡ė—°ėžė™€ 비흡ė—°ėžė˜ ė‚Ŧ망ëĨ ė— 대하ė—Ŧ ėˆ˜ėž‘ė—… ëŖ°ė„ ėž‘ė„ąí•  ėˆ˜ ėžˆėŠĩ니다. - -많ė€ 다ëĨ¸ ëŗ€ėˆ˜ę°€ ë°Šė •ė‹ė— íŦ함되면, ML ëĒ¨ë¸ė´ ęŗŧęą° 건강기록ė„ 기반ėœŧ로 미래 ė‚Ŧ망ëĨ ė„ ė˜ˆė¸Ąí•˜ëŠ” 데ė— 효ėœ¨ė ė´ëŧęŗ  검ėĻí•  ėˆ˜ ėžˆėŠĩ니다. ėœ ėžŒí•œ ė˜ˆė‹œëĄœ ėœ„도, ę˛Ŋ도, 기후 ëŗ€í™”, proximity to the ocean, ė œíŠ¸ 기ëĨ˜ė˜ 패턴ė„ íŦ함한 데ė´í„° 기반ėœŧ로 ėŖŧė–´ė§„ ėœ„ėš˜ė—ė„œ 4ė›”ė˜ 날ė”¨ëĨŧ ė˜ˆė¸Ąí•˜ëŠ” 것ėž…니다. - -✅ 날ė”¨ ëĒ¨ë¸ė— 대한 [slide deck](https://www2.cisl.ucar.edu/sites/default/files/2021-10/0900%20June%2024%20Haupt_0.pdf)ė€ 날ė”¨ ëļ„ė„ė—ė„œ MLė„ ė‚ŦėšŠí•œ ė—­ė‚Ŧė  관ė ė„ ė œęŗĩ합니다. - -## ėž‘ė—… ė‚Ŧė „-ęĩŦėļ•í•˜ę¸° - -ëĒ¨ë¸ė„ 만들기 ė „ė—, ė™„ëŖŒí•´ė•ŧ 할 ëĒ‡ę°€ė§€ ėž‘ė—…ė´ 더 ėžˆėŠĩ니다. ė§ˆëŦ¸ė„ 테ėŠ¤íŠ¸í•˜ęŗ  ëĒ¨ë¸ ė˜ˆė¸Ąė„ 기반ėœŧ로 가ė„¤ ęĩŦė„ąí•˜ë ¤ëŠ´, ė—ŦëŸŦ ėš”ė†ŒëĨŧ ė‹ëŗ„하ęŗ  ęĩŦė„ąí•´ė•ŧ 합니다. - -### 데ė´í„° - -ė–´ë– í•œ ėĸ…ëĨ˜ė˜ ė§ˆëŦ¸ė„ 대ë‹ĩ하려면, ė˜Ŧ바ëĨ¸ 타ėž…ė˜ 데ė´í„°ę°€ 필ėš”핊니다. ė´ íŦė¸íŠ¸ė—ė„œ 필ėš”í•œ 두 가ė§€ę°€ ėžˆėŠĩ니다: - -- **데ė´í„° ėˆ˜ė§‘**. 데ė´í„° ëļ„ė„ė˜ ęŗĩė •ë„ëĨŧ ė„¤ëĒ…í•œ ė´ė „ 강ė˜ëĨŧ 기ė–ĩ하ęŗ , 데ė´í„°ëĨŧ ėĄ°ė‹Ŧ히 ėˆ˜ė§‘핊니다. 데ė´í„°ė˜ ėļœė˛˜ė™€, 내ėžŦė  편ę˛Ŧė„ ė•Œęŗ , ėļœė˛˜ëĨŧ ëŦ¸ė„œí™”핊니다. -- **데ė´í„° ė¤€ëš„**. 데ė´í„° ė¤€ëš„ 프로ė„¸ėŠ¤ëŠ” ė—ŦëŸŦ 단ęŗ„ę°€ ėžˆėŠĩ니다. 데ė´í„°ę°€ 다ė–‘í•œ ė†ŒėŠ¤ė—ė„œ ė œęŗĩ되는 ę˛Ŋėš°ė—ëŠ” ė •ë Ŧ하ęŗ  노멀ëŧė´ėĻˆí•´ė•ŧ 할 ėˆ˜ ėžˆėŠĩ니다. ([Clustering](../../../5-Clustering/1-Visualize/README.md)ęŗŧ 같ė´) ëŦ¸ėžė—´ė„ ėˆĢėžëĄœ 바꾸는 ë°Šė‹ė˛˜ëŸŧ 다ė–‘í•œ ë°Šė‹ė„ í†ĩ하ė—Ŧ 데ė´í„°ė˜ 품ė§ˆęŗŧ ė–‘ė„ í–Ĩėƒė‹œí‚Ŧ ėˆ˜ ėžˆėŠĩ니다. ([Classification](../../../4-Classification/1-Introduction/README.md)ęŗŧ 같ė´) ė›ëŗ¸ 기반ėœŧ로, ėƒˆëĄœėš´ 데ė´í„°ëĨŧ ėƒė„ąí•  ėˆ˜ ėžˆėŠĩ니다. ([Web App](../../../3-Web-App/README.md) 강ė˜ ė´ė „ė˛˜ëŸŧ) 데ė´í„°ëĨŧ ė •ëĻŦ하ęŗ  ëŗ€ę˛Ŋ할 ėˆ˜ ėžˆėŠĩ니다. 마ė§€ë§‰ėœŧ로, 훈련하는 기ėˆ ė— 따ëŧė„œ, ëŦ´ėž‘ėœ„ëĄœ ė„žė–´ė•ŧ 할 ėˆ˜ ėžˆėŠĩ니다. - -✅ 데ė´í„°ëĨŧ ėˆ˜ė§‘하ęŗ  ė˛˜ëĻŦ하면, ꡸ ëĒ¨ė–‘ė´ ė˜ë„í•œ ė§ˆëŦ¸ė„ 해결할 ėˆ˜ ėžˆëŠ” ė§€ ėž ė‹œ 봅니다. [Clustering](../../5-Clustering/1-Visualize/README.md) 강ė˜ė—ė„œ ëŗ¸ 것ė˛˜ëŸŧ, 데ė´í„°ę°€ ėŖŧė–´ė§„ ėž‘ė—…ė—ė„œ ėž˜ ėˆ˜í–‰í•˜ė§€ ëĒģ할 ėˆ˜ ėžˆėŠĩ니다! - -### Featuresė™€ 타겟 - -feature는 데ė´í„°ė˜ ė¸Ąė •í•  ėˆ˜ ėžˆëŠ” ė†ė„ąėž…니다. 많ė€ 데ė´í„°ė…‹ė—ė„œ 'date' 'size' 또는 'color'ė˛˜ëŸŧ ė—´ ė œëĒŠėœŧ로 표현합니다. ėŧ반ė ėœŧ로 ėŊ”ë“œė—ė„œ X로 ëŗ´ė—Ŧė§€ëŠ” feature ëŗ€ėˆ˜ëŠ”, ëĒ¨ë¸ė„ 훈련할 때 ė‚ŦėšŠë˜ëŠ” ėž…ë Ĩ ëŗ€ėˆ˜ëĄœ 나타냅니다. - -타겟ė€ ė˜ˆė¸Ąí•˜ë ¤ęŗ  ė‹œë„í•œ 것ėž…니다. ėŊ”ë“œė—ė„œ X로 표ė‹œí•˜ëŠ” ëŗ´í†ĩ 타겟ė€, 데ė´í„°ė— ëŦŧė–´ëŗ´ë ¤ëŠ” ė§ˆëŦ¸ė˜ 대ë‹ĩė„ 나타냅니다: 12ė›”ė—, ė–´ë–¤ ėƒ‰ė˜ 호박ė´ 가ėžĨ ėŒ€ęšŒėš”? San Francisco ęˇŧė˛˜ė˜ ėĸ‹ė€ 토ė§€ ė‹¤ė œ 거래가는 ė–´ë””ė¸ę°€ėš”? 가끔ė€ 타겟ė„ ëŧ벨 ė†ė„ąė´ëŧęŗ  ëļ€ëĨ´ę¸°ë„ 합니다. - -### feature ëŗ€ėˆ˜ ė„ íƒí•˜ę¸° - -🎓 **Feature Selectionęŗŧ Feature Extraction** ëĒ¨ë¸ė„ 만들 때 ė„ íƒí•  ëŗ€ėˆ˜ëĨŧ ė–´ë–ģ게 ė•Œ ėˆ˜ ėžˆė„ęšŒėš”? 가ėžĨ ė„ąëŠĨė´ ėĸ‹ė€ ëĒ¨ë¸ė— ė˜Ŧ바ëĨ¸ ëŗ€ėˆ˜ëĨŧ ė„ íƒí•˜ę¸° ėœ„하ė—Ŧ Feature Selection 또는 Feature Extraction 프로ė„¸ėŠ¤ëĨŧ ęą°ėš˜ę˛Œ 됩니다. ꡸ëŸŦ나, 같ė€ 내ėšŠė´ ė•„닙니다: "Feature extraction creates new features from functions of the original features, whereas feature selection returns a subset of the features." ([source](https://wikipedia.org/wiki/Feature_selection)) - -### 데ė´í„° ė‹œę°í™”í•˜ę¸° - -데ė´í„° ė‚Ŧė´ė–¸í‹°ėŠ¤íŠ¸ė˜ 툴킷ė—ė„œ ė¤‘ėš”í•œ ė¸ĄëŠ´ė€ Seaborn 또는 MatPlotLibęŗŧ 같ė´ ė—ŦëŸŦ가ė§€ 뛰ė–´ë‚œ ëŧė´ë¸ŒëŸŦëĻŦ로 데ė´í„° ė‹œę°í™”하는 파ė›Œėž…니다. 데ė´í„°ëĨŧ ė‹œę°í™”ëĄœ ëŗ´ė—ŦėŖŧ늴 ėˆ¨ę˛¨ė§„ correlationsëĨŧ ė°žė•„ė„œ 활ėšŠí•  ėˆ˜ ėžˆėŠĩ니다. ([Classification](../../../4-Classification/2-Classifiers-1/README.md)ė—ė„œ 발ę˛Ŧ한대로) ė‹œę°í™”는 편í–Ĩė ė´ęą°ë‚˜ 균형ė ė´ė§€ ė•Šė€ 데ė´í„°ëĨŧ ė°žëŠ” 데 도ė›€ė´ 될 ėˆ˜ ėžˆėŠĩ니다. - -### 데ė´í„°ė…‹ 나누기 - -훈련하기 ė „, 데ė´í„°ëĨŧ ėž˜ 나타ë‚ŧ íŦ기로 2개 ė´ėƒė˜ 데ė´í„° ė…‹ė„ 나눌 필ėš”ę°€ ėžˆėŠĩ니다. - -- **학ėŠĩ**. 데ė´í„°ė…‹ė˜ 파트는 ëĒ¨ë¸ė„ 학ėŠĩ할 때 ė ë‹ší•Šë‹ˆë‹¤. ė´ ė…‹ė€ ëŗ¸ 데ė´í„°ė…‹ė˜ 대ëļ€ëļ„ė„ ė°¨ė§€í•Šë‹ˆë‹¤. -- **테ėŠ¤íŠ¸**. 테ėŠ¤íŠ¸ 데ė´í„°ė…‹ė€ 독ëĻŊė ė¸ 데ė´í„°ė˜ ꡸ëŖšė´ė§€ë§Œ, 미ëĻŦ 만들ė–´ė§„ ëĒ¨ë¸ė˜ ė„ąëŠĨė„ 확ė¸í•  때ė—, 가끔 ëŗ¸ 데ė´í„°ė—ė„œë„ ėˆ˜ė§‘됊니다. -- **검ėĻ**. 검ėĻ ė…‹ė€ ëĒ¨ë¸ė„ 개ė„ í•˜ëŠ° ëĒ¨ë¸ė˜ hyperparameters, 또는 architectureëĨŧ 튜닝할 때, ė‚ŦėšŠí•˜ëŠ” ėž‘ė€ 독ëĻŊ된 ė˜ˆė‹œ ꡸ëŖšėž…니다. ([Time Series Forecasting](../../../7-TimeSeries/1-Introduction/README.md)ė—ė„œ ė–¸ę¸‰í•˜ë“¯) 데ė´í„°ė˜ íŦ기ė™€ ė§ˆëŦ¸ė— 따ëŧė„œ ė„¸ë˛ˆė§¸ ė…‹ė„ 만들 ė´ėœ ę°€ ė—†ėŠĩ니다. - -## ëĒ¨ë¸ ęĩŦėļ•í•˜ę¸° - -훈련하ęŗ  ėžˆëŠ” 데ė´í„°ëĨŧ ė‚ŦėšŠí•˜ė—Ŧ, **학ėŠĩ**할 다ė–‘í•œ ė•Œęŗ ëĻŦėĻ˜ėœŧ로, ëĒ¨ë¸ 또는, 데ė´í„°ė˜ í†ĩęŗ„ė  표현ė„ 만드는 게 ëĒŠí‘œėž…니다. ëĒ¨ë¸ė„ 학ėŠĩ하면ė„œ 데ė´í„°ė— 노ėļœë˜ëŠ´ 발ę˛Ŧ, 검ėĻ, ꡸ëĻŦęŗ  ėŠšė¸í•˜ęą°ë‚˜ ęą°ëļ€ë˜ëŠ” perceived patternsė— 대하ė—Ŧ 가ė„¤ė„ ė„¸ėš¸ ėˆ˜ ėžˆėŠĩ니다. - -### 학ėŠĩ ë°Šė‹ 결ė •í•˜ę¸° - -ė§ˆëŦ¸ęŗŧ 데ė´í„°ė˜ 특ė„ąė— 따ëŧė„œ, ė–´ë–ģ게 학ėŠĩ할 ė§€ ė„ íƒí•Šë‹ˆë‹¤. [Scikit-learn's documentation](https://scikit-learn.org/stable/user_guide.html)ė„ - ė´ ėŊ”ėŠ¤ė—ė„œ - 단ęŗ„ëŗ„ëĄœ ëŗ´ëŠ´ ëĒ¨ë¸ė´ 학ėŠĩ하는 많ė€ ë°Šė‹ė„ ė°žė„ ėˆ˜ ėžˆėŠĩ니다. ėˆ™ë ¨ë„ė— 따ëŧė„œ, ėĩœęŗ ė˜ ëĒ¨ë¸ė„ 만들기 ėœ„하ė—Ŧ 다ëĨ¸ ë°Šė‹ė„ 해ëŗŧ ėˆ˜ ėžˆėŠĩ니다. 데ė´í„° ė‚Ŧė´ė–¸í‹°ėŠ¤íŠ¸ę°€ ëŗŧ ėˆ˜ ė—†ëŠ” 데ė´í„°ëĨŧ ėŖŧęŗ  ė •í™•ë„, 편í–Ĩė , 품ė§ˆ-ė €í•˜ ė´ėŠˆëĨŧ ė ę˛€í•´ė„œ, 현ėžŦ ėž‘ė—…ė— 가ėžĨ ė ë‹ší•œ 학ėŠĩ ë°Šė‹ė„ ė„ íƒí•˜ė—Ŧ ëĒ¨ë¸ė˜ ė„ąëŠĨė„ 평가하는 프로ė„¸ėŠ¤ëĨŧ ęą°ėš˜ę˛Œ 될 ė˜ˆė •ėž…니다. - -### ëĒ¨ë¸ 학ėŠĩ하기 - -훈련 데ė´í„°ëĄœ 감ė‹¸ëŠ´, ëĒ¨ë¸ė„ 만들 'fit'ė´ ė¤€ëš„ 되ė—ˆėŠĩ니다. 많ė€ ML ëŧė´ë¸ŒëŸŦëĻŦė—ė„œ 'model.fit' ėŊ”ë“œëĨŧ ė°žė„ ėˆ˜ ėžˆėŠĩ니다. - ė´ ėˆœę°„ė— 값ė˜ ë°°ė—´ (ëŗ´í†ĩ 'X')ęŗŧ feature ëŗ€ėˆ˜ (ëŗ´í†ĩ 'y')로 데ė´í„°ëĨŧ ëŗ´ë‚´ę˛Œ 됩니다. - -### ëĒ¨ë¸ 평가하기 - -훈련 프로ė„¸ėŠ¤ę°€ ė™„ëŖŒë˜ëŠ´ (큰 ëĒ¨ë¸ė„ 훈련하기 ėœ„í•´ė„œ 많ė´ 반ëŗĩ하거나 'epochs'가 ėš”ęĩŦ), 테ėŠ¤íŠ¸ 데ė´í„°ëĄœ ëĒ¨ë¸ė˜ ė„ąëŠĨė„ ė¸Ąė •í•´ė„œ 품ė§ˆė„ 평가할 ėˆ˜ ėžˆėŠĩ니다. 데ė´í„°ëŠ” ëĒ¨ë¸ė´ ė´ė „ė— ëļ„ė„í•˜ė§€ ė•Šė•˜ë˜ ëŗ¸ 데ė´í„°ė˜ ė„œë¸Œė…‹ėž…니다. ëĒ¨ë¸ė˜ 품ė§ˆė— 대한 ė§€í‘œ 테ė´ë¸”ė„ ėļœë Ĩ할 ėˆ˜ ėžˆėŠĩ니다. - -🎓 **ëĒ¨ë¸ í”ŧ팅** - -머ė‹ ëŸŦ닝ė˜ ėģ¨í…ėŠ¤íŠ¸ė—ė„œ, ëĒ¨ë¸ í”ŧ팅ė€ ėšœęˇŧ하ė§€ ė•Šė€ 데ė´í„°ëĨŧ ëļ„ė„í•˜ë ¤ęŗ  ė‹œë„하는 ėˆœę°„ė— ëĒ¨ë¸ 기ëŗ¸ 기ëŠĨė˜ ė •í™•ë„ëĨŧ ëŗ´ėž…니다. - -🎓 **Underfitting** ęŗŧ **overfitting**ė€ ëĒ¨ë¸ 핏ė´ ėļŠëļ„하ė§€ ė•Šęą°ë‚˜ 너ëŦ´ 많ė„ 때, ëĒ¨ë¸ė˜ 품ė§ˆė´ 낮ė•„ė§€ëŠ” ėŧ반ė ė¸ ė´ėŠˆėž…니다. ė´ëŸŦ한 ė´ėœ ëŠ” ëĒ¨ë¸ė´ 훈련 데ė´í„°ė™€ 너ëŦ´ ęˇŧė ‘í•˜ę˛Œ ė–ŧëŧė¸ë˜ęą°ë‚˜ 너ëŦ´ 느ėŠ¨í•˜ę˛Œ ė–ŧëŧė¸ëœ ė˜ˆė¸Ąė„ 합니다. overfit ëĒ¨ë¸ė€ 데ė´í„°ė˜ 디테ėŧęŗŧ 노ė´ėĻˆëĨŧ 너ëŦ´ ėž˜ ë°°ė› ę¸°ė— 훈련 데ė´í„°ëĄœ 너ëŦ´ë‚˜ ėž˜ ė˜ˆė¸Ąí•Šë‹ˆë‹¤. underfit ëĒ¨ë¸ė€ 훈련 데ė´í„° 또는 ė•„ė§ ëŗŧ ėˆ˜ ė—†ë˜ 데ė´í„°ëĨŧ ėž˜ ëļ„ė„í•  ėˆ˜ ė—†ėœŧë¯€ëĄœ ė •í™•í•˜ė§€ ė•ŠėŠĩ니다. - -![overfitting model](../images/overfitting.png) -> Infographic by [Jen Looper](https://twitter.com/jenlooper) - -## 파ëŧ미터 튜닝 - -ė´ˆë°˜ 훈련ė´ 마ëŦ´ëĻŦ 될 때, ëĒ¨ë¸ė˜ 품ė§ˆė„ ė‚´íŽ´ëŗ´ęŗ  'hyperparameters'ëĨŧ 트ėœ…í•´ė„œ 개ė„ í•˜ëŠ” 것ė„ ęŗ ë ¤í•Šë‹ˆë‹¤. [in the documentation](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-tune-hyperparameters?WT.mc_id=academic-77952-leestott) 프로ė„¸ėŠ¤ė— 대하ė—Ŧ ė•Œė•„봅니다. - -## ė˜ˆė¸Ą - -ė™„ė „히 ėƒˆ 데ė´í„°ëĄœ ëĒ¨ë¸ė˜ ė •í™•ë„ëĨŧ 테ėŠ¤íŠ¸í•  ėˆ˜ ėžˆëŠ” ėˆœę°„ėž…니다. 프로덕ė…˜ė—ė„œ ëĒ¨ë¸ė„ ė“°ę¸° ėœ„í•´ė„œ ė›š ė–´ė…‹ė„ 만들며, 'ė ėšŠí•œ' ML ė„¸íŒ…ė—, 프로ė„¸ėŠ¤ëŠ” ëŗ€ėˆ˜ëĨŧ ė„¤ė •í•˜ęŗ  ėļ”ëĄ í•˜ęą°ë‚˜, 평가하ęŗ ėž ė‚ŦėšŠėž ėž…ë Ĩ(ė˜ˆëĨŧ 들면, 버íŠŧ ėž…ë Ĩ)ė„ ėˆ˜ė§‘í•´ ëĒ¨ë¸ëĄœ ëŗ´ë‚ŧ ėˆ˜ ėžˆėŠĩ니다. - -ė´ 강ė˜ė—ė„œëŠ”, 'full stack' ML ė—”ė§€ë‹ˆė–´ę°€ 되기 ėœ„하ė—Ŧ ė—Ŧ행ė„ 떠나는 ęŗŧė •ė´ëŠ°, ė´ 단ęŗ„ė— - 데ė´í„° ė‚Ŧė´ė–¸í‹°ėŠ¤íŠ¸ė˜ ëĒ¨ë“  ė œėŠ¤ėŗę°€ ėžˆėœŧ늰 ė¤€ëš„, 빌드, 테ėŠ¤íŠ¸, 평가ė™€ ė˜ˆė¸Ą ë°Šė‹ė„ ëŗ´ę˛Œ 됩니다. - ---- - -## 🚀 도ė „ - -ML ė‹¤ëŦ´ėžė˜ 단ęŗ„ëĨŧ 반ė˜í•œ 플로ėš°ëĨŧ ꡸려ëŗ´ė„¸ėš”. 프로ė„¸ėŠ¤ė—ė„œ ė§€ę¸ˆ ė–´ë””ė— ėžˆëŠ” ė§€ ëŗ´ė´ë‚˜ėš”? ė–´ë ¤ėš´ 내ėšŠė„ ė˜ˆėƒí•  ėˆ˜ ėžˆë‚˜ėš”? ė–´ë–¤ę˛Œ ė‰Ŧėš¸ęšŒėš”? - -## [강ė˜ 후 퀴ėĻˆ](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/8/) - -## 검토 & ėžę¸°ėŖŧ도 학ėŠĩ - -ėŧėƒ ė—…ëŦ´ëĨŧ ė´ė•ŧ기하는 데ė´í„° ė‚Ŧė´ė–¸í‹°ėŠ¤íŠ¸ ė¸í„°ëˇ°ëĨŧ ė˜¨ëŧė¸ėœŧ로 검ėƒ‰í•Šë‹ˆë‹¤. ė—Ŧ기 [one](https://www.youtube.com/watch?v=Z3IjgbbCEfs) ėžˆėŠĩ니다. - -## ęŗŧė œ - -[Interview a data scientist](../assignment.md) diff --git a/1-Introduction/4-techniques-of-ML/translations/README.pt-br.md b/1-Introduction/4-techniques-of-ML/translations/README.pt-br.md deleted file mode 100644 index 8b3af3cc..00000000 --- a/1-Introduction/4-techniques-of-ML/translations/README.pt-br.md +++ /dev/null @@ -1,114 +0,0 @@ -# TÊcnicas de Machine Learning - -O processo de construçÃŖo, uso e manutençÃŖo de modelos de machine learning e os dados que eles usam Ê um processo muito diferente de muitos outros fluxos de trabalho de desenvolvimento. Nesta liçÃŖo, vamos desmistificar o processo e delinear as principais tÊcnicas que vocÃĒ precisa saber. VocÃĒ irÃĄ: - -- Compreender os processos que sustentam o aprendizado de mÃĄquina em alto nível. -- Explorar conceitos bÃĄsicos como 'modelos', 'previsÃĩes' e 'dados de treinamento'.. - -## [QuestionÃĄrio prÊ-aula](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/7?loc=ptbr) - -## IntroduçÃŖo - -Em um alto nível, a arte de criar processos de machine learning (ML) Ê composta por uma sÊrie de etapas: - -1. **Decida sobre a questÃŖo**. A maioria dos processos de ML começa fazendo uma pergunta que nÃŖo pode ser respondida por um simples programa condicional ou mecanismo baseado em regras. Essas questÃĩes geralmente giram em torno de previsÃĩes baseadas em uma coleçÃŖo de dados. -2. **Colete e prepare dados**. Para responder à sua pergunta, vocÃĒ precisa de dados. A qualidade e, às vezes, a quantidade de seus dados determinarÃŖo o quÃŖo bem vocÃĒ pode responder à sua pergunta inicial. A visualizaçÃŖo de dados Ê um aspecto importante desta fase. Esta fase tambÊm inclui a divisÃŖo dos dados em um grupo de treinamento e teste para construir um modelo. -3. **Escolha um mÊtodo de treinamento**. Dependendo da sua pergunta e da natureza dos seus dados, vocÃĒ precisa escolher como deseja treinar um modelo para melhor refletir seus dados e fazer previsÃĩes precisas em relaçÃŖo a eles. Esta Ê a parte do seu processo de ML que requer conhecimentos específicos e, muitas vezes, uma quantidade considerÃĄvel de experimentaçÃŖo. -4. **Treine o modelo**. Usando seus dados de treinamento, vocÃĒ usarÃĄ vÃĄrios algoritmos para treinar um modelo para reconhecer padrÃĩes nos dados. O modelo pode alavancar pesos internos que podem ser ajustados para privilegiar certas partes dos dados sobre outras para construir um modelo melhor. -5. **Avalie o modelo**. VocÃĒ usa dados nunca antes vistos (seus dados de teste) de seu conjunto coletado para ver como o modelo estÃĄ se saindo. -6. **Ajuste de parÃĸmetros**. Com base no desempenho do seu modelo, vocÃĒ pode refazer o processo usando diferentes parÃĸmetros, ou variÃĄveis, que controlam o comportamento dos algoritmos usados para treinar o modelo. -7. **Preveja**. Use novas entradas para testar a precisÃŖo do seu modelo. - -## Que pergunta fazer - -Os computadores sÃŖo particularmente adeptos da descoberta de padrÃĩes ocultos nos dados. Esse recurso Ê muito Ãētil para pesquisadores que tÃĒm dÃēvidas sobre um determinado campo que nÃŖo podem ser respondidas facilmente criando um mecanismo de regras baseado em condiçÃĩes. Dada uma tarefa atuarial, por exemplo, um cientista de dados pode ser capaz de construir manualmente regras sobre a mortalidade de fumantes versus nÃŖo fumantes. - -Quando muitas outras variÃĄveis ​​sÃŖo introduzidas na equaçÃŖo, no entanto, um modelo de ML pode ser mais eficiente para prever as taxas de mortalidade futuras com base no histÃŗrico de saÃēde anterior. Um exemplo mais alegre seria fazer previsÃĩes do tempo de abril para um determinado local com base em dados que incluem latitude, longitude, mudança climÃĄtica, proximidade do oceano, padrÃĩes de fluxo de jato e muito mais. - -✅ Esta [apresentaçÃŖo](https://www2.cisl.ucar.edu/sites/default/files/2021-10/0900%20June%2024%20Haupt_0.pdf) sobre modelos meteorolÃŗgicos oferece uma perspectiva histÃŗrica do uso do ML na anÃĄlise meteorolÃŗgica. - -## Tarefas de prÊ-construçÃŖo - -Antes de começar a construir seu modelo, hÃĄ vÃĄrias tarefas que vocÃĒ precisa concluir. Para testar sua pergunta e formar uma hipÃŗtese com base nas previsÃĩes de um modelo, vocÃĒ precisa identificar e configurar vÃĄrios elementos. - -### Dados - -Para poder responder à sua pergunta com qualquer tipo de certeza, vocÃĒ precisa de uma boa quantidade de dados do tipo certo. HÃĄ duas coisas que vocÃĒ precisa fazer neste momento: - -- **Coletar dados**. Tendo em mente a liçÃŖo anterior sobre justiça na anÃĄlise de dados, colete seus dados com cuidado. Esteja ciente das fontes desses dados, de quaisquer tendÃĒncias inerentes que possam ter e documente sua origem. -- **Prepare os dados**. Existem vÃĄrias etapas no processo de preparaçÃŖo de dados. Pode ser necessÃĄrio agrupar dados e normalizÃĄ-los se vierem de fontes diversas. VocÃĒ pode melhorar a qualidade e a quantidade dos dados por meio de vÃĄrios mÊtodos, como a conversÃŖo de strings em nÃēmeros (como fazemos em [Clustering](../../../5-Clustering/1-Visualize/README.md)). VocÃĒ tambÊm pode gerar novos dados, com base no original (como fazemos em [ClassificaçÃŖo](../../../4-Classification/1-Introduction/README.md)). VocÃĒ pode limpar e editar os dados (como faremos antes da liçÃŖo[Web App](../../../3-Web-App/README.md)). Finalmente, vocÃĒ tambÊm pode precisar randomizÃĄ-lo e embaralhÃĄ-lo, dependendo de suas tÊcnicas de treinamento. - -✅ Depois de coletar e processar seus dados, reserve um momento para ver se o formato permitirÃĄ que vocÃĒ responda à pergunta pretendida. Pode ser que os dados nÃŖo funcionem bem em sua tarefa, como descobrimos em nossas liçÃĩes de [Clustering](../../../5-Clustering/1-Visualize/README.md)! - -### Recursos e Alvo - -Um [recurso](https://www.datasciencecentral.com/profiles/blogs/an-introduction-to-variable-and-feature-selection) Ê uma propriedade mensurÃĄvel de seus dados. Em muitos conjuntos de dados, Ê expresso como um cabeçalho de coluna como 'data', 'tamanho' ou 'cor'. Sua variÃĄvel de recurso, geralmente representada como `X` no cÃŗdigo, representa a variÃĄvel de entrada que serÃĄ usada para treinar o modelo. - -Um alvo Ê algo que vocÃĒ estÃĄ tentando prever. Alvo geralmente representado como `y` no cÃŗdigo, representa a resposta à pergunta que vocÃĒ estÃĄ tentando fazer sobre seus dados: em Dezembro, quais abÃŗboras de **cor**serÃŖo mais baratas? em SÃŖo Francisco, quais bairros terÃŖo o melhor **preço** imobiliÃĄrio? Às vezes, o destino tambÊm Ê conhecido como atributo de rÃŗtulo. - -### Selecionando sua variÃĄvel de característica - -🎓 **SeleçÃŖo e extraçÃŖo de recursos** Como vocÃĒ sabe qual variÃĄvel escolher ao construir um modelo? VocÃĒ provavelmente passarÃĄ por um processo de seleçÃŖo ou extraçÃŖo de recursos para escolher as variÃĄveis certas para o modelo de melhor desempenho. Eles nÃŖo sÃŖo a mesma coisa, no entanto: "A extraçÃŖo de recursos cria novos recursos a partir de funçÃĩes dos recursos originais, enquanto a seleçÃŖo de recursos retorna um subconjunto dos recursos." ([fonte](https://wikipedia.org/wiki/Feature_selection)) - -### Visualize seus dados - -Um aspecto importante do kit de ferramentas de uma pessoa cientista de dados Ê o poder de visualizar dados usando vÃĄrias bibliotecas excelentes, como Seaborn ou MatPlotLib. A representaçÃŖo visual de seus dados pode permitir que vocÃĒ descubra correlaçÃĩes ocultas que vocÃĒ pode explorar. As visualizaçÃĩes tambÊm podem ajudar a descobrir distorçÃĩes ou dados desequilibrados (como encontrado em[ClassificaçÃŖo](../../../4-Classification/2-Classifiers-1/README.md)). - -### Divida seu conjunto de dados - -Antes do treinamento, vocÃĒ precisa dividir seu conjunto de dados em duas ou mais partes de tamanhos desiguais que ainda representam bem os dados. - -- **Treinamento**. Esta parte do conjunto de dados Ê adequada ao seu modelo para treinÃĄ-lo. Este conjunto constitui a maior parte do conjunto de dados original. -- **Teste**. Um conjunto de dados de teste Ê um grupo independente de dados, geralmente coletado dos dados originais, que vocÃĒ usa para confirmar o desempenho do modelo construído. -- **Validando**. Um conjunto de validaçÃŖo Ê um grupo menor independente de exemplos que vocÃĒ usa para ajustar os hiperparÃĸmetros do modelo, ou arquitetura, para melhorar o modelo. Dependendo do tamanho dos seus dados e da pergunta que vocÃĒ estÃĄ fazendo, pode nÃŖo ser necessÃĄrio construir este terceiro conjunto (como observamos em [PrevisÃŖo de sÊrie temporal](../../../7-TimeSeries/1-Introduction/README.md)). - -## Construindo um modelo - -Usando seus dados de treinamento, sua meta Ê construir um modelo, ou uma representaçÃŖo estatística de seus dados, usando vÃĄrios algoritmos para **treinÃĄ-los**. O treinamento de um modelo o expÃĩe aos dados e permite que ele faça suposiçÃĩes sobre os padrÃĩes percebidos que descobre, valida e aceita ou rejeita. - -### Decidir sobre um mÊtodo de treinamento - -Desvendando da sua pergunta e da natureza dos seus dados, vocÃĒ escolherÃĄ um mÊtodo para treinÃĄ-los. Percorrendo a [documentaçÃŖo do Scikit-learn](https://scikit-learn.org/stable/user_guide.html) - que usamos neste curso - vocÃĒ pode explorar muitas maneiras de treinar um modelo. Dependendo da sua experiÃĒncia, pode ser necessÃĄrio tentar vÃĄrios mÊtodos diferentes para construir o melhor modelo. É provÃĄvel que vocÃĒ passe por um processo pelo qual os cientistas de dados avaliam o desempenho de um modelo, alimentando-o com dados invisíveis, verificando a precisÃŖo, o viÊs e outros problemas que degradam a qualidade e selecionando o mÊtodo de treinamento mais apropriado para a tarefa em questÃŖo. - -### Treine um modelo - -Armado com seus dados de treinamento, vocÃĒ estÃĄ pronto para 'ajustÃĄ-los' para criar um modelo. VocÃĒ notarÃĄ que em muitas bibliotecas de ML vocÃĒ encontrarÃĄ o cÃŗdigo 'model.fit' - Ê neste momento que vocÃĒ envia sua variÃĄvel de recurso como uma matriz de valores (geralmente 'X') e uma variÃĄvel de destino (geralmente 'y'). - -### Avalie o modelo - -Assim que o processo de treinamento for concluído (pode levar muitas iteraçÃĩes, ou 'epochs', para treinar um modelo grande), vocÃĒ poderÃĄ avaliar a qualidade do modelo usando dados de teste para avaliar seu desempenho. Esses dados sÃŖo um subconjunto dos dados originais que o modelo nÃŖo analisou anteriormente. VocÃĒ pode imprimir uma tabela de mÊtricas sobre a qualidade do seu modelo. - -🎓 **AdaptaçÃŖo do modelo** - -No contexto do machine learning, o ajuste do modelo refere-se à precisÃŖo da funçÃŖo subjacente do modelo à medida que tenta analisar dados com os quais nÃŖo estÃĄ familiarizado. - -🎓 **Underfitting** e **overfitting** sÃŖo problemas comuns que degradam a qualidade do modelo, pois o modelo nÃŖo se ajusta bem o suficiente ou se ajusta muito bem. Isso faz com que o modelo faça previsÃĩes muito alinhadas ou muito vagamente alinhadas com seus dados de treinamento. Um modelo de ajuste excessivo prevÃĒ os dados de treinamento muito bem porque aprendeu os detalhes e o ruído dos dados muito bem. Um modelo insuficiente nÃŖo Ê preciso, pois nÃŖo pode analisar com precisÃŖo seus dados de treinamento, nem os dados que ainda nÃŖo foram 'visto'. - -![modelo de overfitting](../images/overfitting.png) -> InfogrÃĄfico por [Jen Looper](https://twitter.com/jenlooper) - -## Ajuste de parÃĸmetro - -Quando o treinamento inicial estiver concluído, observe a qualidade do modelo e considere melhorÃĄ-lo ajustando seus 'hiperparÃĸmetros'. Leia mais sobre o processo [na documentaçÃŖo](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-tune-hyperparameters?WT.mc_id=academic-77952-leestott). - -## PrediçÃŖo - -Este Ê o momento em que vocÃĒ pode usar dados completamente novos para testar a precisÃŖo do seu modelo. Em uma configuraçÃŖo de ML 'aplicada', onde vocÃĒ estÃĄ construindo ativos da web para usar o modelo na produçÃŖo, este processo pode envolver a coleta de entrada do usuÃĄrio (um pressionamento de botÃŖo, por exemplo) para definir uma variÃĄvel e enviÃĄ-la ao modelo para inferÃĒncia, ou avaliaçÃŖo. - -Nessas liçÃĩes, vocÃĒ descobrirÃĄ como usar essas etapas para preparar, criar, testar, avaliar e prever - todos os gestos de uma pessoa cientista de dados e muito mais, conforme vocÃĒ avança em sua jornada para se tornar um engenheiro de ML de 'full stack'. - ---- - -## 🚀Desafio - -Desenhe um fluxograma refletindo as etapas de um praticante de ML. Onde vocÃĒ se vÃĒ agora no processo? Onde vocÃĒ prevÃĒ que encontrarÃĄ dificuldade? O que parece fÃĄcil para vocÃĒ? - -## [QuestionÃĄrio pÃŗs-aula](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/8?loc=ptbr) - -## RevisÃŖo e Autoestudo - -Procure por entrevistas online com pessoas cientistas de dados que discutem seu trabalho diÃĄrio. Aqui estÃĄ [uma](https://www.youtube.com/watch?v=Z3IjgbbCEfs). - -## Tarefa - -[Entreviste uma pessoa cientista de dados](assignment.pt-br.md) \ No newline at end of file diff --git a/1-Introduction/4-techniques-of-ML/translations/README.zh-cn.md b/1-Introduction/4-techniques-of-ML/translations/README.zh-cn.md deleted file mode 100644 index d135b596..00000000 --- a/1-Introduction/4-techniques-of-ML/translations/README.zh-cn.md +++ /dev/null @@ -1,112 +0,0 @@ - -# æœē器å­Ļ䚠技术 - -构åģē、äŊŋį”¨å’Œįģ´æŠ¤æœē器å­Ļäš æ¨Ąåž‹åŠå…ļäŊŋį”¨įš„数捎įš„čŋ‡į¨‹ä¸ŽčŽ¸å¤šå…ļäģ–åŧ€å‘åˇĨäŊœæĩį¨‹æˆĒį„ļ不同。 在æœŦč¯žä¸­īŧŒæˆ‘äģŦ将揭åŧ€č¯Ĩčŋ‡į¨‹įš„įĨžį§˜éĸįēąīŧŒåšļæĻ‚čŋ°äŊ éœ€čĻäē†č§Ŗįš„ä¸ģčĻæŠ€æœ¯ã€‚ äŊ äŧšīŧš - -- 在éĢ˜åą‚æŦĄä¸Šį†č§Ŗ支持æœē器å­Ļäš įš„čŋ‡į¨‹ã€‚ -- æŽĸį´ĸåŸēæœŦæĻ‚åŋĩīŧŒäž‹åĻ‚â€œæ¨Ąåž‹â€ã€â€œéĸ„æĩ‹â€å’Œâ€œčŽ­įģƒæ•°æŽâ€ã€‚ - -## [č¯žå‰æĩ‹éĒŒ](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/7/) -## äģ‹įģ - -åœ¨čžƒéĢ˜įš„åą‚æŦĄä¸ŠīŧŒåˆ›åģēæœē器å­Ļäš īŧˆMLīŧ‰čŋ‡į¨‹įš„åˇĨč‰ē包æ‹ŦčŽ¸å¤šæ­ĨéĒ¤īŧš - -1. **å†ŗ厚闎éĸ˜**。 大多数æœē器å­Ļäš čŋ‡į¨‹éƒŊ是äģŽæå‡ē一ä¸ĒįŽ€å•įš„æĄäģļį¨‹åēæˆ–åŸēäēŽč§„则įš„åŧ•æ“Žæ— æŗ•å›žį­”įš„é—Žéĸ˜åŧ€å§‹įš„。 čŋ™äē›é—Žéĸ˜é€šå¸¸å›´įģ•åŸēäēŽæ•°æŽé›†åˆįš„éĸ„æĩ‹åą•åŧ€ã€‚ -2. **æ”ļ集和准备数捎**。ä¸ēäē†čƒŊ够回į­”äŊ įš„é—Žéĸ˜īŧŒäŊ éœ€čĻæ•°æŽã€‚数捎įš„č´¨é‡īŧˆæœ‰æ—ļ是数量īŧ‰å°†å†ŗ厚äŊ å›žį­”最初闎éĸ˜įš„čƒŊåŠ›ã€‚å¯č§†åŒ–æ•°æŽæ˜¯čŋ™ä¸Ēé˜ļæŽĩįš„一ä¸Ē重čĻæ–šéĸ。此é˜ļæŽĩčŋ˜åŒ…æ‹Ŧ将数捎拆分ä¸ē莭įģƒå’Œæĩ‹č¯•įģ„äģĨ构åģēæ¨Ąåž‹ã€‚ -3. **选拊一į§čŽ­įģƒæ–šæŗ•**。栚捎äŊ įš„é—Žéĸ˜å’Œæ•°æŽįš„æ€§č´¨īŧŒäŊ éœ€čĻé€‰æ‹ŠåĻ‚äŊ•čŽ­įģƒæ¨Ąåž‹äģĨ最åĨŊ地反映äŊ įš„数捎åšļ寚å…ļčŋ›čĄŒå‡†įĄŽéĸ„æĩ‹ã€‚čŋ™æ˜¯äŊ įš„MLčŋ‡į¨‹įš„一部分īŧŒéœ€čĻį‰šåŽšįš„专业įŸĨč¯†īŧŒåšļ且通常需čĻå¤§é‡įš„厞éĒŒã€‚ -4. **莭įģƒæ¨Ąåž‹**。äŊŋį”¨äŊ įš„莭įģƒæ•°æŽīŧŒäŊ å°†äŊŋį”¨å„į§įŽ—æŗ•æĨ莭įģƒæ¨Ąåž‹äģĨč¯†åˆĢ数捎中įš„æ¨Ąåŧã€‚č¯Ĩæ¨Ąåž‹å¯čƒŊäŧšåˆŠį”¨å¯äģĨč°ƒæ•´įš„内部权重æĨäŊŋ数捎įš„某äē›éƒ¨åˆ†äŧ˜äēŽå…ļäģ–部分īŧŒäģŽč€Œæž„åģē更åĨŊįš„æ¨Ąåž‹ã€‚ -5. **č¯„äŧ°æ¨Ąåž‹**。äŊ äŊŋį”¨æ”ļ集到įš„集合中äģŽæœĒ见čŋ‡įš„数捎īŧˆäŊ įš„æĩ‹č¯•æ•°æŽīŧ‰æĨæŸĨįœ‹æ¨Ąåž‹įš„性čƒŊ。 -6. **å‚æ•°č°ƒæ•´**ã€‚æ šæŽæ¨Ąåž‹įš„性čƒŊīŧŒäŊ å¯äģĨäŊŋį”¨ä¸åŒįš„参数或变量重做č¯Ĩčŋ‡į¨‹īŧŒčŋ™äē›å‚数或变量控åˆļį”¨äēŽčŽ­įģƒæ¨Ąåž‹įš„įŽ—æŗ•įš„čĄŒä¸ē。 -7. **éĸ„æĩ‹**。äŊŋį”¨æ–°čž“å…ĨæĨæĩ‹č¯•æ¨Ąåž‹įš„准įĄŽæ€§ã€‚ - -## čĻé—Žäģ€äšˆé—Žéĸ˜ - -莥įŽ—æœēį‰šåˆĢ擅é•ŋ发įŽ°æ•°æŽä¸­įš„éšč—æ¨Ąåŧã€‚此厞į”¨į¨‹åēå¯šäēŽå¯šįģ™åŽšéĸ†åŸŸæœ‰į–‘é—Žįš„į ”įŠļäēē员非常有帎劊īŧŒčŋ™äē›é—Žéĸ˜æ— æŗ•é€ščŋ‡åˆ›åģēåŸēäēŽæĄäģļįš„č§„åˆ™åŧ•æ“ŽæĨčŊģ杞回į­”。䞋åĻ‚īŧŒįģ™åŽšä¸€éĄšį˛žįŽ—äģģåŠĄīŧŒæ•°æŽį§‘å­ĻåŽļ可čƒŊčƒŊ够围įģ•å¸įƒŸč€…与非吸įƒŸč€…įš„æ­ģäēĄįŽ‡æž„åģē手åˇĨč§„åˆ™ã€‚ - -į„ļ而īŧŒåŊ“å°†čŽ¸å¤šå…ļäģ–变量įēŗå…Ĩį­‰åŧæ—ļīŧŒMLæ¨Ąåž‹å¯čƒŊäŧšæ›´æœ‰æ•ˆåœ°æ šæŽčŋ‡åŽģįš„åĨåēˇå˛éĸ„æĩ‹æœĒæĨįš„æ­ģäēĄįŽ‡ã€‚一ä¸Ē更äģ¤äēē愉åŋĢįš„䞋子可čƒŊ是栚捎包æ‹ŦįēŦåēĻ、įģåēĻ、气候变化、与æĩˇæ´‹įš„æŽĨčŋ‘į¨‹åēĻ、æ€Ĩæĩæ¨Ąåŧį­‰åœ¨å†…įš„数捎寚įģ™åŽšäŊįŊŽįš„4月äģŊčŋ›čĄŒå¤Šæ°”éĸ„æŠĨ。 - -✅ čŋ™ä¸Ēå…ŗäēŽå¤Šæ°”æ¨Ąåž‹įš„[åšģį¯į‰‡](https://www2.cisl.ucar.edu/sites/default/files/2021-10/0900%20June%2024%20Haupt_0.pdf)ä¸ē在夊气分析中äŊŋį”¨æœē器å­Ļ䚠提䞛äē†ä¸€ä¸ĒåŽ†å˛č§†č§’ã€‚ - -## éĸ„æž„åģēäģģåŠĄ - -在åŧ€å§‹æž„åģēæ¨Ąåž‹äš‹å‰īŧŒäŊ éœ€čĻåŽŒæˆå¤šéĄšäģģåŠĄã€‚čĻæĩ‹č¯•äŊ įš„é—Žéĸ˜åšļæ šæŽæ¨Ąåž‹įš„éĸ„æĩ‹åŊĸæˆå‡čŽžīŧŒäŊ éœ€čĻč¯†åˆĢ和配įŊŽå¤šä¸Ē元į´ ã€‚ - -### Data - -ä¸ēäē†čƒŊ够įĄŽåŽšåœ°å›žį­”äŊ įš„é—Žéĸ˜īŧŒäŊ éœ€čĻå¤§é‡æ­ŖįĄŽįąģ型įš„数捎。 æ­¤æ—ļäŊ éœ€čĻåšä¸¤äģļäē‹īŧš - -- **æ”ļ集数捎**ã€‚čŽ°äŊäš‹å‰å…ŗäēŽæ•°æŽåˆ†æžå…Ŧåšŗ性įš„č¯žį¨‹īŧŒå°åŋƒæ”ļé›†æ•°æŽã€‚č¯ˇæŗ¨æ„æ­¤æ•°æŽįš„æĨæēã€åŽƒå¯čƒŊå…ˇæœ‰įš„äģģäŊ•å›ēæœ‰åč§īŧŒåšļ莰åŊ•å…ļæĨæēã€‚ -- **准备数捎**。数捎准备čŋ‡į¨‹æœ‰å‡ ä¸Ēæ­ĨéĒ¤ã€‚åĻ‚果数捎æĨč‡Ē不同įš„æĨæēīŧŒäŊ å¯čƒŊ需čĻæ•´į†æ•°æŽåšļ寚å…ļčŋ›čĄŒæ ‡å‡†åŒ–。äŊ å¯äģĨ通čŋ‡å„į§æ–šæŗ•æéĢ˜æ•°æŽįš„č´¨é‡å’Œæ•°é‡īŧŒäž‹åĻ‚将字įŦĻ串čŊŦæĸä¸ē数字īŧˆå°ąåƒæˆ‘äģŦ在[聚įąģ](../../../5-Clustering/1-Visualize/README.md)中所做įš„é‚Ŗæ ˇīŧ‰ã€‚äŊ čŋ˜å¯äģĨ栚捎原始数捎į”Ÿæˆæ–°æ•°æŽīŧˆæ­ŖåĻ‚我äģŦ在[分įąģ](../../../4-Classification/1-Introduction/README.md)中所做įš„é‚Ŗæ ˇīŧ‰ã€‚äŊ å¯äģĨ清į†å’Œįŧ–čž‘æ•°æŽīŧˆå°ąåƒæˆ‘äģŦ在 [Web App](../../3-Web-App/README.md)č¯žį¨‹äš‹å‰æ‰€åšįš„é‚Ŗæ ˇīŧ‰ã€‚最后īŧŒäŊ å¯čƒŊčŋ˜éœ€čĻå¯šå…ļčŋ›čĄŒéšæœēåŒ–å’Œæ‰“äšąīŧŒå…ˇäŊ“取å†ŗäēŽäŊ įš„莭įģƒæŠ€æœ¯ã€‚ - -✅ 在æ”ļ集和处į†äŊ įš„数捎后īŧŒčŠąį‚šæ—ļ间įœ‹įœ‹åŽƒįš„åŊĸįŠļ是åĻčƒŊ莊äŊ č§Ŗå†ŗäŊ įš„éĸ„期闎éĸ˜ã€‚æ­ŖåĻ‚我äģŦ在[聚įąģ](../../../5-Clustering/1-Visualize/README.md)č¯žį¨‹ä¸­å‘įŽ°įš„é‚Ŗæ ˇīŧŒæ•°æŽå¯čƒŊ在äŊ įš„įģ™åŽšäģģåŠĄä¸­čĄ¨įŽ°ä¸äŊŗīŧ - -### 功čƒŊ和į›Žæ ‡ - -功čƒŊ是数捎įš„可æĩ‹é‡åąžæ€§ã€‚åœ¨čŽ¸å¤šæ•°æŽé›†ä¸­īŧŒåŽƒčĄ¨į¤ēä¸ē标éĸ˜ä¸ē"æ—Ĩ期""大小"或"éĸœč‰˛"įš„列。您įš„功čƒŊ变量īŧˆé€šå¸¸åœ¨äģŖį ä¸­čĄ¨į¤ēä¸ē `X`īŧ‰čĄ¨į¤ēį”¨äēŽčŽ­įģƒæ¨Ąåž‹įš„čž“å…Ĩ变量。 - -į›Žæ ‡å°ąæ˜¯äŊ č¯•å›žéĸ„æĩ‹įš„äē‹æƒ…。į›Žæ ‡é€šå¸¸čĄ¨į¤ēä¸ēäģŖį ä¸­įš„ `y`īŧŒäģŖčĄ¨æ‚¨č¯•å›žč¯ĸ闎数捎įš„é—Žéĸ˜įš„į­”æĄˆīŧšåœ¨ 12 月īŧŒäģ€äšˆéĸœč‰˛įš„南į“œæœ€äžŋ厜īŧŸåœ¨æ—§é‡‘åąąīŧŒå“Ēäē›čĄ—åŒēįš„æˆŋ地äē§äģˇæ ŧ最åĨŊīŧŸæœ‰æ—ļį›Žæ ‡äšŸį§°ä¸ē标į­žåąžæ€§ã€‚ - -### 选拊į‰šåžå˜é‡ - -🎓 **į‰šåžé€‰æ‹Šå’Œį‰šåžæå–** 构åģēæ¨Ąåž‹æ—ļåĻ‚äŊ•įŸĨ道选拊å“Ēä¸Ē变量īŧŸäŊ å¯čƒŊäŧšįģåŽ†ä¸€ä¸Ēį‰šåžé€‰æ‹Šæˆ–į‰šåžæå–įš„čŋ‡į¨‹īŧŒäģĨäžŋä¸ē性čƒŊ最åĨŊįš„æ¨Ąåž‹é€‰æ‹Šæ­ŖįĄŽįš„变量。į„ļ而īŧŒåŽƒäģŦ不是一回äē‹īŧšâ€œį‰šåžæå–是äģŽåŸēäēŽåŽŸå§‹į‰šåžįš„å‡Ŋ数中创åģē新į‰šåžīŧŒč€Œį‰šåžé€‰æ‹Ščŋ”回į‰šåžįš„一ä¸Ē子集。”īŧˆ[æĨæē](https://wikipedia.org/wiki/Feature_selection)īŧ‰ -### å¯č§†åŒ–æ•°æŽ - -数捎į§‘å­ĻåŽļåˇĨå…ˇåŒ…įš„一ä¸Ē重čĻæ–šéĸ是čƒŊ够äŊŋį”¨å¤šä¸Ēäŧ˜į§€įš„åē“īŧˆäž‹åĻ‚ Seaborn 或 MatPlotLibīŧ‰å°†æ•°æŽå¯č§†åŒ–。į›´č§‚åœ°čĄ¨į¤ēäŊ įš„数捎可čƒŊäŧščŽŠäŊ å‘įŽ°å¯äģĨ刊į”¨įš„éšč—å…ŗč”ã€‚ äŊ įš„å¯č§†åŒ–čŋ˜å¯äģĨ帎劊äŊ å‘įŽ°åč§æˆ–不åšŗ襥įš„数捎īŧˆæ­ŖåĻ‚我äģŦ在 [分įąģ](../../../4-Classification/2-Classifiers-1/README.md)中发įŽ°įš„é‚Ŗæ ˇīŧ‰ã€‚ -### 拆分数捎集 - -åœ¨čŽ­įģƒäš‹å‰īŧŒäŊ éœ€čĻå°†æ•°æŽé›†æ‹†åˆ†ä¸ē两ä¸Ē或多ä¸Ē大小不į­‰äŊ†äģčƒŊ垈åĨŊ地äģŖčĄ¨æ•°æŽįš„部分。 - -- **莭įģƒ**。čŋ™éƒ¨åˆ†æ•°æŽé›†é€‚合äŊ įš„æ¨Ąåž‹čŋ›čĄŒčŽ­įģƒã€‚čŋ™ä¸Ē集合构成äē†åŽŸå§‹æ•°æŽé›†įš„大部分。 -- **æĩ‹č¯•**。æĩ‹č¯•æ•°æŽé›†æ˜¯ä¸€įģ„į‹ŦįĢ‹įš„数捎īŧŒé€šå¸¸äģŽåŽŸå§‹æ•°æŽä¸­æ”ļ集īŧŒį”¨äēŽįĄŽčŽ¤æž„åģēæ¨Ąåž‹įš„性čƒŊ。 -- **éĒŒč¯**。éĒŒč¯é›†æ˜¯ä¸€ä¸Ēčžƒå°įš„į‹ŦįĢ‹į¤ē例įģ„īŧŒį”¨äēŽč°ƒæ•´æ¨Ąåž‹įš„čļ…参数或æžļ构īŧŒäģĨ攚čŋ›æ¨Ąåž‹ã€‚栚捎äŊ įš„数捎大小和äŊ æå‡ēįš„é—Žéĸ˜īŧŒäŊ å¯čƒŊ不需čĻæž„åģēįŦŦ三įģ„īŧˆæ­ŖåĻ‚我äģŦ在[æ—ļ间åēåˆ—éĸ„æĩ‹](../../../7-TimeSeries/1-Introduction/README.md)中所čŋ°īŧ‰ã€‚ - -## åģēįĢ‹æ¨Ąåž‹ - -äŊŋį”¨äŊ įš„莭įģƒæ•°æŽīŧŒäŊ įš„į›Žæ ‡æ˜¯æž„åģēæ¨Ąåž‹æˆ–æ•°æŽįš„įģŸčŽĄčĄ¨į¤ēīŧŒåšļäŊŋį”¨å„į§įŽ—æŗ•å¯šå…ļčŋ›čĄŒ**莭įģƒ**ã€‚čŽ­įģƒæ¨Ąåž‹å°†å…ļæš´éœ˛įģ™æ•°æŽīŧŒåšļå…čŽ¸åŽƒå¯šå…ļ发įŽ°ã€éĒŒč¯å’ŒæŽĨ受或拒įģįš„æ„ŸįŸĨæ¨Ąåŧåšå‡ēå‡čŽžã€‚ - -### å†ŗ厚一į§čŽ­įģƒæ–šæŗ• - -栚捎äŊ įš„é—Žéĸ˜å’Œæ•°æŽįš„æ€§č´¨īŧŒäŊ å°†é€‰æ‹Šä¸€į§æ–šæŗ•æĨ莭įģƒåŽƒã€‚逐æ­Ĩ厌成 [Scikit-learnįš„æ–‡æĄŖ](https://scikit-learn.org/stable/user_guide.html) - 我äģŦ在æœŦč¯žį¨‹ä¸­äŊŋį”¨ - äŊ å¯äģĨæŽĸį´ĸ多į§čŽ­įģƒæ¨Ąåž‹įš„æ–šæŗ•ã€‚ 栚捎äŊ įš„įģéĒŒīŧŒäŊ å¯čƒŊ需čĻå°č¯•å¤šį§ä¸åŒįš„æ–šæŗ•æĨ构åģē最äŊŗæ¨Ąåž‹ã€‚äŊ å¯čƒŊäŧšįģåŽ†ä¸€ä¸Ēčŋ‡į¨‹īŧŒåœ¨č¯Ĩčŋ‡į¨‹ä¸­īŧŒæ•°æŽį§‘å­ĻåŽļ通čŋ‡æäž›æœĒ见čŋ‡įš„数捎æĨč¯„äŧ°æ¨Ąåž‹įš„性čƒŊīŧŒæŖ€æŸĨ准įĄŽæ€§ã€ååˇŽå’Œå…ļäģ–降äŊŽč´¨é‡įš„é—Žéĸ˜īŧŒåšļä¸ē手头įš„äģģåŠĄé€‰æ‹Šæœ€åˆé€‚įš„莭įģƒæ–šæŗ•ã€‚ - -### 莭įģƒæ¨Ąåž‹ - -有äē†æ‚¨įš„åŸščŽ­æ•°æŽīŧŒæ‚¨å°ąå¯äģĨ"适åē”"厃æĨ创åģēæ¨Ąåž‹ã€‚æ‚¨äŧšæŗ¨æ„åˆ°īŧŒåœ¨čŽ¸å¤š ML åē“中īŧŒæ‚¨äŧšå‘įŽ°äģŖį "model.fit"-æ­¤æ—ļīŧŒæ‚¨å°†åŠŸčƒŊ变量äŊœä¸ē一įŗģ列å€ŧīŧˆé€šå¸¸æ˜¯`X`īŧ‰å’Œį›Žæ ‡å˜é‡īŧˆé€šå¸¸æ˜¯`y`īŧ‰å‘送。 - -### č¯„äŧ°æ¨Ąåž‹ - -莭įģƒčŋ‡į¨‹åŽŒæˆåŽīŧˆčŽ­įģƒå¤§åž‹æ¨Ąåž‹å¯čƒŊ需čĻå¤šæŦĄčŋ­äģŖ或“æ—ļ期”īŧ‰īŧŒäŊ å°†čƒŊ够通čŋ‡äŊŋį”¨æĩ‹č¯•æ•°æŽæĨčĄĄé‡æ¨Ąåž‹įš„性čƒŊæĨč¯„äŧ°æ¨Ąåž‹įš„č´¨é‡ã€‚æ­¤æ•°æŽæ˜¯æ¨Ąåž‹å…ˆå‰æœĒ分析įš„原始数捎įš„子集。 äŊ å¯äģĨ打印å‡ē有å…ŗæ¨Ąåž‹č´¨é‡įš„æŒ‡æ ‡čĄ¨ã€‚ - -🎓 **æ¨Ąåž‹æ‹Ÿåˆ** - -在æœē器å­Ļäš įš„čƒŒæ™¯ä¸‹īŧŒæ¨Ąåž‹æ‹Ÿåˆæ˜¯æŒ‡æ¨Ąåž‹åœ¨å°č¯•åˆ†æžä¸į†Ÿæ‚‰įš„数捎æ—ļå…ļåē•åą‚功čƒŊįš„准įĄŽæ€§ã€‚ - -🎓 **æŦ æ‹Ÿåˆ**和**čŋ‡æ‹Ÿåˆ**是降äŊŽæ¨Ąåž‹č´¨é‡įš„å¸¸č§é—Žéĸ˜īŧŒå› ä¸ēæ¨Ąåž‹æ‹Ÿåˆåž—ä¸å¤ŸåĨŊ或å¤ĒåĨŊ。čŋ™äŧšå¯ŧč‡´æ¨Ąåž‹åšå‡ē与å…ļ莭įģƒæ•°æŽčŋ‡äēŽį´§å¯†å¯šéŊæˆ–čŋ‡äēŽæžæ•Ŗ寚éŊįš„éĸ„æĩ‹ã€‚ čŋ‡æ‹Ÿåˆæ¨Ąåž‹å¯ščŽ­įģƒæ•°æŽįš„éĸ„æĩ‹å¤ĒåĨŊīŧŒå› ä¸ēåŽƒåˇ˛įģåžˆåĨŊ地äē†č§Ŗäē†æ•°æŽįš„įģ†čŠ‚å’Œå™ĒåŖ°ã€‚æŦ æ‹Ÿåˆæ¨Ąåž‹åšļ不准įĄŽīŧŒå› ä¸ē厃æ—ĸ不čƒŊ准įĄŽåˆ†æžå…ļ莭įģƒæ•°æŽīŧŒäšŸä¸čƒŊ准įĄŽåˆ†æžå°šæœĒ“įœ‹åˆ°â€įš„数捎。 - -![čŋ‡æ‹Ÿåˆæ¨Ąåž‹ ](../images/overfitting.png) -> äŊœč€… [Jen Looper](https://twitter.com/jenlooper) - -## å‚æ•°č°ƒäŧ˜ - -åˆå§‹čŽ­įģƒåŽŒæˆåŽīŧŒč§‚å¯Ÿæ¨Ąåž‹įš„č´¨é‡åšļ考虑通čŋ‡č°ƒæ•´å…ļ“čļ…参数”æĨ攚čŋ›åŽƒã€‚[在此文æĄŖ中](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-tune-hyperparameters?WT.mc_id=academic-77952-leestott)阅č¯ģ有å…ŗč¯Ĩčŋ‡į¨‹įš„更多äŋĄæ¯ã€‚ - -## éĸ„æĩ‹ - -čŋ™æ˜¯äŊ å¯äģĨäŊŋį”¨å…¨æ–°æ•°æŽæĨæĩ‹č¯•æ¨Ąåž‹å‡†įĄŽæ€§įš„æ—ļåˆģ。在“åē”į”¨â€ML莞įŊŽä¸­īŧŒäŊ æ­Ŗ在构åģēWebčĩ„æēäģĨ在į”Ÿäē§ä¸­äŊŋį”¨æ¨Ąåž‹īŧŒæ­¤čŋ‡į¨‹å¯čƒŊæļ‰åŠæ”ļ集į”¨æˆˇčž“å…Ĩīŧˆäž‹åĻ‚按下按钎īŧ‰äģĨ莞įŊŽå˜é‡åšļ将å…ļå‘é€åˆ°æ¨Ąåž‹čŋ›čĄŒæŽ¨į†īŧŒæˆ–č€…č¯„äŧ°ã€‚ - -在čŋ™äē›č¯žį¨‹ä¸­īŧŒäŊ å°†äē†č§ŖåĻ‚äŊ•äŊŋį”¨čŋ™äē›æ­ĨéĒ¤æĨ准备、构åģē、æĩ‹č¯•ã€č¯„äŧ°å’Œéĸ„æĩ‹â€”所有čŋ™äē›éƒŊ是数捎į§‘å­ĻåŽļįš„å§ŋ态īŧŒč€Œä¸”随į€äŊ åœ¨æˆä¸ē一名“全栈”MLåˇĨį¨‹å¸ˆįš„æ—…į¨‹ä¸­å–åž—čŋ›åą•īŧŒäŊ å°†äē†č§Ŗ更多。 - ---- - -## đŸš€æŒ‘æˆ˜ - -į”ģ一ä¸Ēæĩį¨‹å›žīŧŒåæ˜ MLįš„æ­ĨéĒ¤ã€‚在čŋ™ä¸Ēčŋ‡į¨‹ä¸­īŧŒäŊ čŽ¤ä¸ēč‡ĒåˇąįŽ°åœ¨åœ¨å“Ē里īŧŸäŊ éĸ„æĩ‹äŊ åœ¨å“Ē里äŧšé‡åˆ°å›°éšžīŧŸäģ€äšˆå¯šäŊ æĨč¯´åžˆåŽšæ˜“īŧŸ - -## [阅č¯ģ后æĩ‹éĒŒ](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/8/) - -## 复䚠与č‡Ēå­Ļ - -在įēŋ搜į´ĸå¯ščŽ¨čŽēæ—Ĩ常åˇĨäŊœįš„数捎į§‘å­ĻåŽļįš„采čŽŋ。 čŋ™æ˜¯[å…ļ中之一](https://www.youtube.com/watch?v=Z3IjgbbCEfs)。 - -## äģģåŠĄ - -[采čŽŋ一名数捎į§‘å­ĻåŽļ](assignment.zh-cn.md) diff --git a/1-Introduction/4-techniques-of-ML/translations/README.zh-tw.md b/1-Introduction/4-techniques-of-ML/translations/README.zh-tw.md deleted file mode 100644 index 38d56d56..00000000 --- a/1-Introduction/4-techniques-of-ML/translations/README.zh-tw.md +++ /dev/null @@ -1,111 +0,0 @@ - -# 抟器學įŋ’æŠ€čĄ“ - -構åģē、äŊŋį”¨å’Œįļ­č­ˇæŠŸå™¨å­¸įŋ’æ¨Ąåž‹åŠå…ļäŊŋį”¨įš„數據įš„過į¨‹čˆ‡č¨ąå¤šå…ļäģ–é–‹į™ŧåˇĨäŊœæĩį¨‹æˆĒį„ļ不同。 在æœŦčĒ˛ä¸­īŧŒæˆ‘å€‘å°‡æ­é–‹čŠ˛éŽį¨‹įš„įĨžį§˜éĸį´—īŧŒä¸ĻæĻ‚čŋ°äŊ éœ€čĻäē†č§Ŗįš„ä¸ģčĻæŠ€čĄ“。 äŊ æœƒīŧš - -- 在éĢ˜åą¤æŦĄä¸Šį†č§Ŗ支持抟器學įŋ’įš„過į¨‹ã€‚ -- æŽĸį´ĸåŸēæœŦæĻ‚åŋĩīŧŒäž‹åĻ‚ã€Œæ¨Ąåž‹ã€ã€ã€Œé æ¸Ŧã€å’Œã€Œč¨“įˇ´æ•¸æ“šã€ã€‚ - -## [čĒ˛å‰æ¸Ŧ驗](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/7/) -## äģ‹į´š - -在čŧƒéĢ˜įš„åą¤æŦĄä¸ŠīŧŒå‰ĩåģē抟器學įŋ’īŧˆMLīŧ‰éŽį¨‹įš„åˇĨč—åŒ…æ‹Ŧč¨ąå¤šæ­Ĩ驟īŧš - -1. **æąēåŽšå•éĄŒ**。 大多數抟器學įŋ’過į¨‹éƒŊ是垞提å‡ē一個į°Ąå–Žįš„æĸäģļį¨‹åēæˆ–åŸēæ–ŧčĻå‰‡įš„åŧ•æ“Žį„Ąæŗ•å›žį­”įš„å•éĄŒé–‹å§‹įš„。 這äē›å•éĄŒé€šå¸¸åœįšžåŸēæ–ŧ數據集合įš„預æ¸Ŧåą•é–‹ã€‚ -2. **æ”ļ集和æē–備數據**。į‚ēäē†čƒŊ夠回į­”äŊ įš„å•éĄŒīŧŒäŊ éœ€čĻæ•¸æ“šã€‚數據įš„čŗĒ量īŧˆæœ‰æ™‚是數量īŧ‰å°‡æąē厚äŊ å›žį­”æœ€åˆå•éĄŒįš„čƒŊ力。可čĻ–化數據是這個階æŽĩįš„一個重čĻæ–šéĸ。此階æŽĩ還包æ‹Ŧ將數據拆分į‚ē訓įˇ´å’Œæ¸ŦčŠĻįĩ„äģĨ構åģēæ¨Ąåž‹ã€‚ -3. **選擇一į¨Žč¨“įˇ´æ–šæŗ•**。栚據äŊ įš„å•éĄŒå’Œæ•¸æ“šįš„性čŗĒīŧŒäŊ éœ€čĻé¸æ“‡åĻ‚äŊ•č¨“įˇ´æ¨Ąåž‹äģĨ最åĨŊ地反映äŊ įš„數據ä¸Ļ對å…ļ進行æē–įĸē預æ¸Ŧ。這是äŊ įš„ML過į¨‹įš„一部分īŧŒéœ€čĻį‰šåŽšįš„å°ˆæĨ­įŸĨ識īŧŒä¸Ļ且通常需čĻå¤§é‡įš„å¯Ļ銗。 -4. **訓įˇ´æ¨Ąåž‹**。äŊŋį”¨äŊ įš„訓įˇ´æ•¸æ“šīŧŒäŊ å°‡äŊŋį”¨å„į¨ŽįŽ—æŗ•äž†č¨“įˇ´æ¨Ąåž‹äģĨ識åˆĨ數據中įš„æ¨Ąåŧã€‚čŠ˛æ¨Ąåž‹å¯čƒŊ會刊į”¨å¯äģĨčĒŋ整įš„內部æŦŠé‡äž†äŊŋ數據įš„某äē›éƒ¨åˆ†å„Ēæ–ŧå…ļäģ–部分īŧŒåžžč€Œæ§‹åģē更åĨŊįš„æ¨Ąåž‹ã€‚ -5. **評äŧ°æ¨Ąåž‹**。äŊ äŊŋį”¨æ”ļ集到įš„集合中垞æœĒčĻ‹éŽįš„數據īŧˆäŊ įš„æ¸ŦčŠĻ數據īŧ‰äž†æŸĨįœ‹æ¨Ąåž‹įš„性čƒŊ。 -6. **參數čĒŋ整**ã€‚æ šæ“šæ¨Ąåž‹įš„性čƒŊīŧŒäŊ å¯äģĨäŊŋį”¨ä¸åŒįš„åƒæ•¸æˆ–čŽŠé‡é‡åščŠ˛éŽį¨‹īŧŒé€™äē›åƒæ•¸æˆ–čŽŠé‡æŽ§čŖŊį”¨æ–ŧ訓įˇ´æ¨Ąåž‹įš„įŽ—æŗ•įš„čĄŒį‚ē。 -7. **預æ¸Ŧ**。äŊŋį”¨æ–°čŧ¸å…Ĩ來æ¸ŦčŠĻæ¨Ąåž‹įš„æē–įĸē性。 - -## čĻå•äģ€éēŊå•éĄŒ - -計įŽ—抟į‰šåˆĨæ“…é•ˇį™ŧįžæ•¸æ“šä¸­įš„éšąč—æ¨Ąåŧã€‚æ­¤å¯Ļį”¨į¨‹åēå°æ–ŧ對įĩĻ厚領域有į–‘問įš„į ”įŠļäēēå“Ąéžå¸¸æœ‰åšĢ劊īŧŒé€™äē›å•éĄŒį„Ąæŗ•é€šéŽå‰ĩåģēåŸēæ–ŧæĸäģļįš„čĻå‰‡åŧ•æ“Žäž†čŧ•æžå›žį­”。䞋åĻ‚īŧŒįĩĻ厚一項į˛žįŽ—äģģ務īŧŒæ•¸æ“šį§‘å­¸åŽļ可čƒŊčƒŊ夠圍įšžå¸į…™č€…čˆ‡éžå¸į…™č€…įš„æ­ģäēĄįŽ‡æ§‹åģē手åˇĨčĻå‰‡ã€‚ - -į„ļ而īŧŒį•ļå°‡č¨ąå¤šå…ļäģ–čŽŠé‡į´å…Ĩį­‰åŧæ™‚īŧŒMLæ¨Ąåž‹å¯čƒŊ會更有效地栚據過åŽģįš„åĨåēˇå˛é æ¸ŦæœĒ來įš„æ­ģäēĄįŽ‡ã€‚一個更äģ¤äēē愉åŋĢįš„䞋子可čƒŊ是栚據包æ‹Ŧįˇ¯åēĻ、įļ“åēĻ、æ°Ŗå€™čŽŠåŒ–ã€čˆ‡æĩˇæ´‹įš„æŽĨčŋ‘į¨‹åēĻ、æ€Ĩæĩæ¨Ąåŧį­‰åœ¨å…§įš„數據對įĩĻ厚äŊįŊŽįš„4月äģŊé€˛čĄŒå¤Šæ°Ŗé å ąã€‚ - -✅ 這個關æ–ŧ夊æ°Ŗæ¨Ąåž‹įš„[åšģį‡ˆį‰‡](https://www2.cisl.ucar.edu/sites/default/files/2021-10/0900%20June%2024%20Haupt_0.pdf)į‚ē在夊æ°Ŗ分析中äŊŋį”¨æŠŸå™¨å­¸įŋ’提䞛äē†ä¸€å€‹æ­ˇå˛čĻ–č§’ã€‚ - -## 預構åģēäģģ務 - -在開始構åģēæ¨Ąåž‹äš‹å‰īŧŒäŊ éœ€čĻåŽŒæˆå¤šé …äģģ務。čĻæ¸ŦčŠĻäŊ įš„å•éĄŒä¸Ļæ šæ“šæ¨Ąåž‹įš„預æ¸ŦåŊĸæˆå‡č¨­īŧŒäŊ éœ€čĻč­˜åˆĨ和配įŊŽå¤šå€‹å…ƒį´ ã€‚ - -### Data - -į‚ēäē†čƒŊ夠įĸē厚地回į­”äŊ įš„å•éĄŒīŧŒäŊ éœ€čĻå¤§é‡æ­ŖįĸēéĄžåž‹įš„數據。 此時äŊ éœ€čĻåšå…Šäģļäē‹īŧš - -- **æ”ļ集數據**ã€‚č¨˜äŊäš‹å‰é—œæ–ŧ數據分析å…Ŧåšŗ性įš„čĒ˛į¨‹īŧŒå°åŋƒæ”ļ集數據。čĢ‹č¨ģ意此數據įš„䞆æēã€åŽƒå¯čƒŊå…ˇæœ‰įš„äģģäŊ•å›ē有偏čĻ‹īŧŒä¸Ļ記錄å…ļ來æēã€‚ -- **æē–備數據**。數據æē–備過į¨‹æœ‰åšžå€‹æ­Ĩ銟。åĻ‚果數據䞆č‡Ē不同įš„䞆æēīŧŒäŊ å¯čƒŊ需čĻæ•´į†æ•¸æ“šä¸Ļ對å…ļé€˛čĄŒæ¨™æē–化。äŊ å¯äģĨ通過各į¨Žæ–šæŗ•æéĢ˜æ•¸æ“šįš„čŗĒ量和數量īŧŒäž‹åĻ‚將字įŦĻ串čŊ‰æ›į‚ē數字īŧˆå°ąåƒæˆ‘們在[聚類](../../../5-Clustering/1-Visualize/README.md)中所做įš„é‚Ŗæ¨Ŗīŧ‰ã€‚äŊ é‚„可äģĨ栚據原始數據į”Ÿæˆæ–°æ•¸æ“šīŧˆæ­ŖåĻ‚我們在[åˆ†éĄž](../../../4-Classification/1-Introduction/README.md)中所做įš„é‚Ŗæ¨Ŗīŧ‰ã€‚äŊ å¯äģĨ清į†å’Œįˇ¨čŧ¯æ•¸æ“šīŧˆå°ąåƒæˆ‘們在 [Web App](../../3-Web-App/README.md)čĒ˛į¨‹äš‹å‰æ‰€åšįš„é‚Ŗæ¨Ŗīŧ‰ã€‚最垌īŧŒäŊ å¯čƒŊ還需čĻå°å…ļé€˛čĄŒéš¨æŠŸåŒ–å’Œæ‰“äē‚īŧŒå…ˇéĢ”取æąēæ–ŧäŊ įš„訓įˇ´æŠ€čĄ“。 - -✅ 在æ”ļé›†å’Œč™•į†äŊ įš„數據垌īŧŒčŠąéģžæ™‚é–“įœ‹įœ‹åŽƒįš„åŊĸį‹€æ˜¯åĻčƒŊ讓äŊ č§ŖæąēäŊ įš„é æœŸå•éĄŒã€‚æ­ŖåĻ‚我們在[聚類](../../../5-Clustering/1-Visualize/README.md)čĒ˛į¨‹ä¸­į™ŧįžįš„é‚Ŗæ¨ŖīŧŒæ•¸æ“šå¯čƒŊ在äŊ įš„įĩĻ厚äģģå‹™ä¸­čĄ¨įžä¸äŊŗīŧ - -### 功čƒŊ和į›Žæ¨™ - -功čƒŊ是數據įš„可æ¸Ŧ量åąŦæ€§ã€‚åœ¨č¨ąå¤šæ•¸æ“šé›†ä¸­īŧŒåŽƒčĄ¨į¤ēį‚ēæ¨™éĄŒį‚ē"æ—Ĩ期""大小"或"顏色"įš„列。您įš„功čƒŊ變量īŧˆé€šå¸¸åœ¨äģŖįĸŧ中襨į¤ēį‚ē `X`īŧ‰čĄ¨į¤ēį”¨æ–ŧ訓įˇ´æ¨Ąåž‹įš„čŧ¸å…ĨčŽŠé‡ã€‚ - -į›Žæ¨™å°ąæ˜¯äŊ čŠĻ圖預æ¸Ŧįš„äē‹æƒ…。į›Žæ¨™é€šå¸¸čĄ¨į¤ēį‚ēäģŖįĸŧ中įš„ `y`īŧŒäģŖčĄ¨æ‚¨čŠĻ圖čŠĸ問數據įš„å•éĄŒįš„į­”æĄˆīŧšåœ¨ 12 月īŧŒäģ€éēŊ顏色įš„南į“œæœ€äžŋ厜īŧŸåœ¨čˆŠé‡‘åąąīŧŒå“Ēäē›čĄ—區įš„æˆŋ地į”ĸ僚æ ŧ最åĨŊīŧŸæœ‰æ™‚į›Žæ¨™äšŸį¨ąį‚ē標į°ŊåąŦ性。 - -### 選擇į‰šåžčŽŠé‡ - -🎓 **į‰šåžé¸æ“‡å’Œį‰šåžæå–** 構åģēæ¨Ąåž‹æ™‚åĻ‚äŊ•įŸĨ道選擇å“Ēå€‹čŽŠé‡īŧŸäŊ å¯čƒŊ會įļ“æ­ˇä¸€å€‹į‰šåžé¸æ“‡æˆ–į‰šåžæå–įš„過į¨‹īŧŒäģĨäžŋį‚ē性čƒŊ最åĨŊįš„æ¨Ąåž‹é¸æ“‡æ­Ŗįĸēįš„čŽŠé‡ã€‚į„ļ而īŧŒåŽƒå€‘不是一回äē‹īŧšã€Œį‰šåžæå–是垞åŸēæ–ŧ原始į‰šåžįš„å‡Ŋ數中å‰ĩåģē新į‰šåžīŧŒč€Œį‰šåžé¸æ“‡čŋ”回į‰šåžįš„一個子集。」īŧˆ[來æē](https://wikipedia.org/wiki/Feature_selection)īŧ‰ -### 可čĻ–化數據 - -數據į§‘å­¸åŽļåˇĨå…ˇåŒ…įš„一個重čĻæ–šéĸ是čƒŊ夠äŊŋį”¨å¤šå€‹å„Ēį§€įš„åēĢīŧˆäž‹åĻ‚ Seaborn 或 MatPlotLibīŧ‰å°‡æ•¸æ“šå¯čĻ–化。į›´č§€åœ°čĄ¨į¤ēäŊ įš„數據可čƒŊæœƒčŽ“äŊ į™ŧįžå¯äģĨ刊į”¨įš„éšąč—é—œč¯ã€‚ äŊ įš„可čĻ–化還可äģĨåšĢ劊äŊ į™ŧįžåčĻ‹æˆ–不åšŗ襥įš„數據īŧˆæ­ŖåĻ‚我們在 [åˆ†éĄž](../../../4-Classification/2-Classifiers-1/README.md)中į™ŧįžįš„é‚Ŗæ¨Ŗīŧ‰ã€‚ -### 拆分數據集 - -åœ¨č¨“įˇ´äš‹å‰īŧŒäŊ éœ€čĻå°‡æ•¸æ“šé›†æ‹†åˆ†į‚ē兊個或多個大小不į­‰äŊ†äģčƒŊ垈åĨŊ地äģŖčĄ¨æ•¸æ“šįš„部分。 - -- **訓įˇ´**。這部分數據集遊合äŊ įš„æ¨Ąåž‹é€˛čĄŒč¨“įˇ´ã€‚這個集合構成äē†åŽŸå§‹æ•¸æ“šé›†įš„大部分。 -- **æ¸ŦčŠĻ**。æ¸ŦčŠĻ數據集是一įĩ„į¨įĢ‹įš„數據īŧŒé€šå¸¸åžžåŽŸå§‹æ•¸æ“šä¸­æ”ļ集īŧŒį”¨æ–ŧįĸēčĒæ§‹åģēæ¨Ąåž‹įš„性čƒŊ。 -- **驗證**ã€‚éŠ—č­‰é›†æ˜¯ä¸€å€‹čŧƒå°įš„į¨įĢ‹į¤ē例įĩ„īŧŒį”¨æ–ŧčĒŋæ•´æ¨Ąåž‹įš„čļ…參數或æžļ構īŧŒäģĨæ”šé€˛æ¨Ąåž‹ã€‚æ šæ“šäŊ įš„數據大小和äŊ æå‡ēįš„å•éĄŒīŧŒäŊ å¯čƒŊ不需čĻæ§‹åģēįŦŦ三įĩ„īŧˆæ­ŖåĻ‚我們在[時間åēåˆ—預æ¸Ŧ](../../../7-TimeSeries/1-Introduction/README.md)中所čŋ°īŧ‰ã€‚ - -## åģēįĢ‹æ¨Ąåž‹ - -äŊŋį”¨äŊ įš„訓įˇ´æ•¸æ“šīŧŒäŊ įš„į›Žæ¨™æ˜¯æ§‹åģēæ¨Ąåž‹æˆ–æ•¸æ“šįš„įĩąč¨ˆčĄ¨į¤ēīŧŒä¸ĻäŊŋį”¨å„į¨ŽįŽ—æŗ•å°å…ļ進行**訓įˇ´**ã€‚č¨“įˇ´æ¨Ąåž‹å°‡å…ļæš´éœ˛įĩĻ數據īŧŒä¸Ļå…č¨ąåŽƒå°å…ļį™ŧįžã€éŠ—č­‰å’ŒæŽĨ受或拒įĩ•įš„æ„ŸįŸĨæ¨Ąåŧåšå‡ēå‡č¨­ã€‚ - -### æąē厚一į¨Žč¨“įˇ´æ–šæŗ• - -æ šæ“šäŊ įš„å•éĄŒå’Œæ•¸æ“šįš„性čŗĒīŧŒäŊ å°‡é¸æ“‡ä¸€į¨Žæ–šæŗ•äž†č¨“įˇ´åŽƒã€‚逐æ­Ĩ厌成 [Scikit-learnįš„æ–‡æĒ”](https://scikit-learn.org/stable/user_guide.html) - 我們在æœŦčĒ˛į¨‹ä¸­äŊŋį”¨ - äŊ å¯äģĨæŽĸį´ĸ多į¨Žč¨“įˇ´æ¨Ąåž‹įš„æ–šæŗ•ã€‚ æ šæ“šäŊ įš„įļ“銗īŧŒäŊ å¯čƒŊ需čĻå˜—čŠĻ多į¨Žä¸åŒįš„æ–šæŗ•äž†æ§‹åģē最äŊŗæ¨Ąåž‹ã€‚äŊ å¯čƒŊ會įļ“æ­ˇä¸€å€‹éŽį¨‹īŧŒåœ¨čŠ˛éŽį¨‹ä¸­īŧŒæ•¸æ“šį§‘å­¸åŽļ通過提䞛æœĒčĻ‹éŽįš„æ•¸æ“šäž†čŠ•äŧ°æ¨Ąåž‹įš„性čƒŊīŧŒæĒĸæŸĨæē–įĸēæ€§ã€ååˇŽå’Œå…ļäģ–降äŊŽčŗĒ量įš„å•éĄŒīŧŒä¸Ļį‚ē手頭įš„äģģ務選擇最合遊įš„訓įˇ´æ–šæŗ•ã€‚ - -### 訓įˇ´æ¨Ąåž‹ - -有äē†æ‚¨įš„åŸšč¨“æ•¸æ“šīŧŒæ‚¨å°ąå¯äģĨ"遊應"厃䞆å‰ĩåģēæ¨Ąåž‹ã€‚æ‚¨æœƒč¨ģ意到īŧŒåœ¨č¨ąå¤š ML åēĢ中īŧŒæ‚¨æœƒį™ŧįžäģŖįĸŧ"model.fit"-此時īŧŒæ‚¨å°‡åŠŸčƒŊ變量äŊœį‚ē一įŗģ列å€ŧīŧˆé€šå¸¸æ˜¯`X`īŧ‰å’Œį›Žæ¨™čŽŠé‡īŧˆé€šå¸¸æ˜¯`y`īŧ‰į™ŧ送。 - -### 評äŧ°æ¨Ąåž‹ - -訓įˇ´éŽį¨‹åŽŒæˆåžŒīŧˆč¨“įˇ´å¤§åž‹æ¨Ąåž‹å¯čƒŊ需čĻå¤šæŦĄå äģŖ或「時期」īŧ‰īŧŒäŊ å°‡čƒŊ夠通過äŊŋį”¨æ¸ŦčŠĻæ•¸æ“šäž†čĄĄé‡æ¨Ąåž‹įš„性čƒŊ來評äŧ°æ¨Ąåž‹įš„čŗĒé‡ã€‚æ­¤æ•¸æ“šæ˜¯æ¨Ąåž‹å…ˆå‰æœĒ分析įš„原始數據įš„子集。 äŊ å¯äģĨ打印å‡ēæœ‰é—œæ¨Ąåž‹čŗĒ量įš„æŒ‡æ¨™čĄ¨ã€‚ - -🎓 **æ¨Ąåž‹æ“Ŧ合** - -在抟器學įŋ’įš„čƒŒæ™¯ä¸‹īŧŒæ¨Ąåž‹æ“Ŧåˆæ˜¯æŒ‡æ¨Ąåž‹åœ¨å˜—čŠĻ分析不į†Ÿæ‚‰įš„數據時å…ļåē•åą¤åŠŸčƒŊįš„æē–įĸē性。 - -🎓 **æŦ æ“Ŧ合**和**過æ“Ŧ合**是降äŊŽæ¨Ąåž‹čŗĒ量įš„常čĻ‹å•éĄŒīŧŒå› į‚ēæ¨Ąåž‹æ“Ŧ合垗不夠åĨŊ或å¤ĒåĨŊã€‚é€™æœƒå°Žč‡´æ¨Ąåž‹åšå‡ē與å…ļ訓įˇ´æ•¸æ“šéŽæ–ŧįˇŠå¯†å°éŊŠæˆ–過æ–ŧ杞æ•Ŗ對éŊŠįš„預æ¸Ŧ。 過æ“Ŧåˆæ¨Ąåž‹å°č¨“įˇ´æ•¸æ“šįš„預æ¸Ŧå¤ĒåĨŊīŧŒå› į‚ēåŽƒåˇ˛įļ“垈åĨŊ地äē†č§Ŗäē†æ•¸æ“šįš„į´°į¯€å’Œå™Ēč˛ã€‚æŦ æ“Ŧåˆæ¨Ąåž‹ä¸Ļ不æē–įĸēīŧŒå› į‚ē厃æ—ĸ不čƒŊæē–įĸē分析å…ļ訓įˇ´æ•¸æ“šīŧŒäšŸä¸čƒŊæē–įĸē分析尚æœĒ「įœ‹åˆ°ã€įš„數據。 - -![過æ“Ŧåˆæ¨Ąåž‹ ](../images/overfitting.png) -> äŊœč€… [Jen Looper](https://twitter.com/jenlooper) -## 參數čĒŋå„Ē - -åˆå§‹č¨“įˇ´åŽŒæˆåžŒīŧŒč§€å¯Ÿæ¨Ąåž‹įš„čŗĒ量ä¸Ļč€ƒæ…Žé€šéŽčĒŋ整å…ļ「čļ…åƒæ•¸ã€äž†æ”šé€˛åŽƒã€‚[在此文æĒ”中](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-tune-hyperparameters?WT.mc_id=academic-77952-leestott)é–ąčŽ€æœ‰é—œčŠ˛éŽį¨‹įš„更多äŋĄæ¯ã€‚ - -## 預æ¸Ŧ - -這是äŊ å¯äģĨäŊŋį”¨å…¨æ–°æ•¸æ“šäž†æ¸ŦčŠĻæ¨Ąåž‹æē–įĸē性įš„時åˆģ。在「應į”¨ã€ML設įŊŽä¸­īŧŒäŊ æ­Ŗ在構åģēWebčŗ‡æēäģĨ在į”Ÿį”ĸ中äŊŋį”¨æ¨Ąåž‹īŧŒæ­¤éŽį¨‹å¯čƒŊæļ‰åŠæ”ļ集į”¨æˆļčŧ¸å…Ĩīŧˆäž‹åĻ‚按下按鈕īŧ‰äģĨ設įŊŽčŽŠé‡ä¸Ļ將å…ļį™ŧé€åˆ°æ¨Ąåž‹é€˛čĄŒæŽ¨į†īŧŒæˆ–者芕äŧ°ã€‚ - -在這äē›čĒ˛į¨‹ä¸­īŧŒäŊ å°‡äē†č§ŖåĻ‚äŊ•äŊŋį”¨é€™äē›æ­Ĩ驟來æē–備、構åģē、æ¸ŦčŠĻã€čŠ•äŧ°å’Œé æ¸Ŧ—所有這äē›éƒŊ是數據į§‘å­¸åŽļįš„å§ŋ態īŧŒč€Œä¸”隨著äŊ åœ¨æˆį‚ē一名「全æŖ§ã€MLåˇĨį¨‹å¸Ģįš„æ—…į¨‹ä¸­å–åž—é€˛åą•īŧŒäŊ å°‡äē†č§Ŗ更多。 - ---- - -## đŸš€æŒ‘æˆ° - -į•Ģ一個æĩį¨‹åœ–īŧŒåæ˜ MLįš„æ­Ĩ銟。在這個過į¨‹ä¸­īŧŒäŊ čĒį‚ēč‡Ēåˇąįžåœ¨åœ¨å“ĒčŖīŧŸäŊ é æ¸ŦäŊ åœ¨å“ĒčŖæœƒé‡åˆ°å›°é›ŖīŧŸäģ€éēŊ對äŊ äž†čĒĒ垈厚易īŧŸ - -## [é–ąčŽ€åžŒæ¸Ŧ驗](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/8/) - -## 垊įŋ’čˆ‡č‡Ēå­¸ - -在įˇšæœį´ĸå°č¨ŽčĢ–æ—Ĩ常åˇĨäŊœįš„數據į§‘å­¸åŽļįš„采č¨Ē。 這是[å…ļ中之一](https://www.youtube.com/watch?v=Z3IjgbbCEfs)。 - -## äģģ務 - -[采č¨Ē一名數據į§‘å­¸åŽļ](assignment.zh-tw.md) \ No newline at end of file diff --git a/1-Introduction/4-techniques-of-ML/translations/assignment.es.md b/1-Introduction/4-techniques-of-ML/translations/assignment.es.md deleted file mode 100644 index 2e931f8c..00000000 --- a/1-Introduction/4-techniques-of-ML/translations/assignment.es.md +++ /dev/null @@ -1,11 +0,0 @@ -# Entrevista a un científico de datos - -## Instrucciones - -En tu compaÃąÃ­a, en un grupo de usuarios, o entre tus amigos o compaÃąeros de estudio, habla con alguien que trabaje profesionalmente como científico de datos. Escribe un artículo corto (500 palabras) acerca de sus ocupaciones diarias. ÂŋSon ellos especialistas, o trabajan como 'full stack'? - -## RÃēbrica - -| Criterio | Ejemplar | Adecuado | Necesita mejorar | -| -------- | ------------------------------------------------------------------------------------ | ------------------------------------------------------------------ | --------------------- | -| | Un ensayo de la longitud correcta, con fuentes atribuidas, es presentado como un archivo .doc | El ensayo es pobremente atribuido o mÃĄs corto que la longitud requerida | No se presentÃŗ el ensayo | diff --git a/1-Introduction/4-techniques-of-ML/translations/assignment.id.md b/1-Introduction/4-techniques-of-ML/translations/assignment.id.md deleted file mode 100644 index 9f7b23be..00000000 --- a/1-Introduction/4-techniques-of-ML/translations/assignment.id.md +++ /dev/null @@ -1,11 +0,0 @@ -# Wawancara seorang data scientist - -## Instruksi - -Di perusahaan Kamu, dalam user group, atau di antara teman atau sesama siswa, berbicaralah dengan seseorang yang bekerja secara profesional sebagai data scientist. Tulis makalah singkat (500 kata) tentang pekerjaan sehari-hari mereka. Apakah mereka spesialis, atau apakah mereka bekerja 'full stack'? - -## Rubrik - -| Kriteria | Sangat Bagus | Cukup | Perlu Peningkatan | -| -------- | ------------------------------------------------------------------------------------ | ------------------------------------------------------------------ | --------------------- | -| | Sebuah esai dengan panjang yang sesuai, dengan sumber yang dikaitkan, disajikan sebagai file .doc | Esai dikaitkan dengan buruk atau lebih pendek dari panjang yang dibutuhkan | Tidak ada esai yang disajikan | diff --git a/1-Introduction/4-techniques-of-ML/translations/assignment.it.md b/1-Introduction/4-techniques-of-ML/translations/assignment.it.md deleted file mode 100644 index 41c597f4..00000000 --- a/1-Introduction/4-techniques-of-ML/translations/assignment.it.md +++ /dev/null @@ -1,11 +0,0 @@ -# Intervista a un data scientist - -## Istruzioni - -Nella propria azienda, in un gruppo di utenti, o tra amici o compagni di studio, si parli con qualcuno che lavora professionalmente come data scientist. Si scriva un breve documento (500 parole) sulle loro occupazioni quotidiane. Sono specialisti o lavorano "full stack"? - -## Rubrica - -| Criteri | Ottimo | Adeguato | Necessita miglioramento | -| -------- | ------------------------------------------------------------------------------------ | ------------------------------------------------------------------ | --------------------- | -| | Un saggio della lunghezza corretta, con fonti attribuite, è presentato come file .doc | Il saggio è attribuito male o piÚ corto della lunghezza richiesta | Non viene presentato alcun saggio | diff --git a/1-Introduction/4-techniques-of-ML/translations/assignment.ja.md b/1-Introduction/4-techniques-of-ML/translations/assignment.ja.md deleted file mode 100644 index b3690e77..00000000 --- a/1-Introduction/4-techniques-of-ML/translations/assignment.ja.md +++ /dev/null @@ -1,11 +0,0 @@ -# デãƒŧã‚ŋã‚ĩイエãƒŗテã‚Ŗ゚トãĢイãƒŗã‚ŋビãƒĨãƒŧする - -## 指į¤ē - -äŧšį¤žãƒģãƒĻãƒŧã‚ļグãƒĢãƒŧプãƒģ友äēēãƒģå­Ļį”Ÿäģ˛é–“ぎ中で、デãƒŧã‚ŋã‚ĩイエãƒŗテã‚Ŗ゚トとしãĻ専門įš„ãĢ働いãĻいるäēēãĢčŠąã‚’čžã„ãĻãŋぞしょう。そぎäēēぎæ—Ĩ々ぎäģ•äē‹ãĢついãĻįŸ­ã„ãƒŦポãƒŧトīŧˆ500čĒžīŧ‰ã‚’書いãĻください。そぎäēēは専門åŽļでしょうかīŧŸãã‚Œã¨ã‚‚「フãƒĢã‚šã‚ŋック」としãĻ働いãĻいるでしょうかīŧŸ - -## 評価åŸēæē– - -| åŸēæē– | æ¨Ąį¯„įš„ | 十分 | čĻæ”šå–„ | -| ---- | ---------------------------------------------------------------------- | -------------------------------------------------------------- | -------------------------- | -| | å‡ēå…¸ãŒæ˜Žč¨˜ã•ã‚ŒãŸéŠåˆ‡ãĒé•ˇã•ãŽãƒŦポãƒŧトが.docãƒ•ã‚Ąã‚¤ãƒĢとしãĻ提į¤ēされãĻいる | ãƒŦポãƒŧトãĢå‡ēå…¸ãŒæ˜Žč¨˜ã•ã‚ŒãĻいãĒい、もしくはåŋ…čĻãĒé•ˇã•ã‚ˆã‚Šã‚‚įŸ­ã„ | ãƒŦポãƒŧトが提į¤ēされãĻいãĒい | diff --git a/1-Introduction/4-techniques-of-ML/translations/assignment.ko.md b/1-Introduction/4-techniques-of-ML/translations/assignment.ko.md deleted file mode 100644 index 085f723f..00000000 --- a/1-Introduction/4-techniques-of-ML/translations/assignment.ko.md +++ /dev/null @@ -1,11 +0,0 @@ -# 데ė´í„° ęŗŧ학ėžëĨŧ ė¸í„°ëˇ°í•´ 봅ė‹œë‹¤ - -## ė„¤ëĒ… - -현ėžŦ ėŧ 하는 회ė‚Ŧ 또는 ė–´ëŠ ė‚ŦėšŠėž ė§‘단ė—ė„œë‚˜, ėŖŧëŗ€ ėšœęĩŦ들 또는 동ëŖŒ 학ėƒë“¤ ė¤‘ 데ė´í„° ęŗŧ학ėžëĄœė„œ ė „ëŦ¸ė ėœŧ로 ėŧ하는 ė‚Ŧ람ęŗŧ 대화해 ëŗ´ė„¸ėš”. 대화 후 ꡸ ė‚Ŧ람ė´ 평ė†Œ ė–´ë–¤ ėŧė„ 하는ė§€ 500ėž ė´ėƒėœŧ로 ėˆ˜í•„(ė—ė„¸ė´)ė„ ėž‘ė„ąí•´ ëŗ´ė‹œę¸° 바랍니다. ꡸ ė‚Ŧ람ė€ 데ė´í„° ęŗŧ학 ëļ„ė•ŧė—ė„œ 특ė • ė—…ëŦ´ė— ė§‘ė¤‘하는 데ė´í„° ęŗŧ학 ė „ëŦ¸ę°€ė¸ę°€ėš”, ė•„니늴 ė „ë°˜ė ėœŧ로 다ė–‘í•œ ė—…ëŦ´ė— ė§‘ė¤‘하는 '풀ėŠ¤íƒ' 데ė´í„° ęŗŧ학ėžė¸ę°€ėš”? - -## 평가기ė¤€í‘œ - -| 평가기ė¤€ | ëĒ¨ë˛” | ė ė ˆ | í–Ĩėƒ 필ėš” | -| -------- | ----------------------------------------------------------------------------------------- | ----------------------------------------------------- | ------------ | -| | 500ėž ė´ėƒė˜ ė—ė„¸ė´ė´ëŠ° ė°¸ęŗ ëŦ¸í—Œė„ ė œëŒ€ëĄœ 표기했ęŗ  .doc 형ė‹ė˜ ė›Œë“œ(Microsoft Word) 파ėŧ로 ė œėļœ | 500ėž ė´ë‚´ė˜ ė—ė„¸ė´ė´ęą°ë‚˜ ė°¸ęŗ ëŦ¸í—Œė„ ė œëŒ€ëĄœ 표기하ė§€ ė•ŠėŒ | ė—ė„¸ė´ 미ė œėļœ | diff --git a/1-Introduction/4-techniques-of-ML/translations/assignment.pt-br.md b/1-Introduction/4-techniques-of-ML/translations/assignment.pt-br.md deleted file mode 100644 index 820519cc..00000000 --- a/1-Introduction/4-techniques-of-ML/translations/assignment.pt-br.md +++ /dev/null @@ -1,11 +0,0 @@ -# Entreviste uma pessoa cientista de dados - -## Instructions - -Em sua empresa, em um grupo de usuÃĄrios ou entre seus amigos ou colegas estudantes, converse com alguÊm que trabalhe profissionalmente como cientista de dados. Escreva um pequeno artigo (500 palavras) sobre suas ocupaçÃĩes diÃĄrias. Eles sÃŖo especialistas ou trabalham com 'full stack'? - -## Rubrica - -| CritÊrios | Exemplar | Adapte | Precisa Melhorar | -| -------- | ------------------------------------------------------------------------------------ | ------------------------------------------------------------------ | --------------------- | -| | Uma redaçÃŖo com a extensÃŖo correta, com fontes atribuídas, Ê apresentado em arquivo .doc | A redaçÃŖo estÃĄ mal atribuído ou Ê menor do que o comprimento exigido | Nenhuma redaçÃŖo Ê apresentado | | diff --git a/1-Introduction/4-techniques-of-ML/translations/assignment.zh-cn.md b/1-Introduction/4-techniques-of-ML/translations/assignment.zh-cn.md deleted file mode 100644 index ba28b554..00000000 --- a/1-Introduction/4-techniques-of-ML/translations/assignment.zh-cn.md +++ /dev/null @@ -1,11 +0,0 @@ -# 采čŽŋ一äŊæ•°æŽį§‘å­ĻåŽļ - -## č¯´æ˜Ž - -在äŊ įš„å…Ŧ司、äŊ æ‰€åœ¨įš„į¤žįž¤ã€æˆ–č€…åœ¨äŊ įš„朋友和同å­Ļ中īŧŒæ‰žåˆ°ä¸€äŊäģŽäē‹æ•°æŽį§‘å­Ļ专业åˇĨäŊœįš„äēēīŧŒä¸Žäģ–或åĨšäē¤æĩä¸€ä¸‹ã€‚写一į¯‡å…ŗäēŽäģ–äģŦåˇĨäŊœæ—Ĩ常įš„小įŸ­æ–‡īŧˆ500字åˇĻåŗīŧ‰ã€‚äģ–äģŦ是专åŽļīŧŒčŋ˜æ˜¯č¯´äģ–äģŦ是“全栈”åŧ€å‘者īŧŸ - -## č¯„åˆ¤æ ‡å‡† - -| 标准 | äŧ˜į§€ | 中规中įŸŠ | äģéœ€åŠĒ力 | -| -------- | ------------------------------------------------------------------------------------ | ------------------------------------------------------------------ | --------------------- | -| | 提äē¤ä¸€į¯‡æ¸…晰描čŋ°äē†čŒä¸šåąžæ€§ä¸”å­—æ•°įŦĻåˆč§„čŒƒįš„word文æĄŖ | 提äē¤įš„æ–‡æĄŖčŒä¸šåąžæ€§æčŋ°åž—ä¸æ¸…æ™°æˆ–č€…å­—æ•°ä¸åˆč§„čŒƒ | å•ĨéƒŊæ˛Ąæœ‰äē¤ | diff --git a/1-Introduction/4-techniques-of-ML/translations/assignment.zh-tw.md b/1-Introduction/4-techniques-of-ML/translations/assignment.zh-tw.md deleted file mode 100644 index 6d3d601c..00000000 --- a/1-Introduction/4-techniques-of-ML/translations/assignment.zh-tw.md +++ /dev/null @@ -1,11 +0,0 @@ -# 采č¨Ē一äŊæ•¸æ“šį§‘å­¸åŽļ - -## čĒĒ明 - -在äŊ įš„å…Ŧ司、äŊ æ‰€åœ¨įš„į¤žįž¤ã€æˆ–č€…åœ¨äŊ įš„朋友和同學中īŧŒæ‰žåˆ°ä¸€äŊåžžäē‹æ•¸æ“šį§‘學專æĨ­åˇĨäŊœįš„äēēīŧŒčˆ‡äģ–或åĨšäē¤æĩä¸€ä¸‹ã€‚å¯Ģ一į¯‡é—œæ–ŧäģ–們åˇĨäŊœæ—Ĩ常įš„小įŸ­æ–‡īŧˆ500字åˇĻåŗīŧ‰ã€‚äģ–們是專åŽļīŧŒé‚„是čĒĒäģ–們是「全æŖ§ã€é–‹į™ŧ者īŧŸ - -## čŠ•åˆ¤æ¨™æē– - -| 標æē– | å„Ēį§€ | 中čĻä¸­įŸŠ | äģéœ€åŠĒ力 | -| -------- | ------------------------------------------------------------------------------------ | ------------------------------------------------------------------ | --------------------- | -| | 提äē¤ä¸€į¯‡æ¸…晰描čŋ°äē†čˇæĨ­åąŦ性且字數įŦĻ合čĻį¯„įš„word文æĒ” | 提äē¤įš„æ–‡æĒ”聡æĨ­åąŦ性描čŋ°åž—ä¸æ¸…æ™°æˆ–č€…å­—æ•¸ä¸åˆčĻį¯„ | å•ĨéƒŊæ˛’æœ‰äē¤ | \ No newline at end of file diff --git a/1-Introduction/images/globe.jpg b/1-Introduction/images/globe.jpg deleted file mode 100644 index 75c0a660..00000000 Binary files a/1-Introduction/images/globe.jpg and /dev/null differ diff --git a/1-Introduction/translations/README.es.md b/1-Introduction/translations/README.es.md deleted file mode 100644 index a4bc59ce..00000000 --- a/1-Introduction/translations/README.es.md +++ /dev/null @@ -1,23 +0,0 @@ -# IntroducciÃŗn al machine learning - -En esta secciÃŗn del plan de estudios se le presentarÃĄn los conceptos bÃĄsicos que hay detrÃĄs del campo del "machine learning", lo que es, y aprenderemos sobre su historia y las tÊcnicas que los investigadores utilizan para trabajar con Êl. ÂĄExploremos juntos el mundo del ML! - -![globe](images/globe.jpg) -> Photo by Bill Oxford on Unsplash - -### Lecciones - -1. [IntroducciÃŗn al machine learning](1-intro-to-ML/README.md) -1. [La Historia del machine learning y la AI](2-history-of-ML/README.md) -1. [Equidad y machine learning](3-fairness/README.md) -1. [TÊcnicas de machine learning](4-techniques-of-ML/README.md) -### CrÊditos - -"IntroducciÃŗn al Machine Learning" fue escrito con â™Ĩī¸ por un equipo de personas que incluye [Muhammad Sakib Khan Inan](https://twitter.com/Sakibinan), [Ornella Altunyan](https://twitter.com/ornelladotcom) y [Jen Looper](https://twitter.com/jenlooper) - -"La Historia del Machine Learning" fue escrito con â™Ĩī¸ por [Jen Looper](https://twitter.com/jenlooper) y [Amy Boyd](https://twitter.com/AmyKateNicho) - -"Equidad y Machine Learning" fue escrito con â™Ĩī¸ por [Tomomi Imura](https://twitter.com/girliemac) - -"TÊcnicas de Machine Learning" fue escrito con â™Ĩī¸ por [Jen Looper](https://twitter.com/jenlooper) y [Chris Noring](https://twitter.com/softchris) - diff --git a/1-Introduction/translations/README.fr.md b/1-Introduction/translations/README.fr.md deleted file mode 100644 index 462dea70..00000000 --- a/1-Introduction/translations/README.fr.md +++ /dev/null @@ -1,22 +0,0 @@ -# Introduction au machine learning - -Dans cette section du programme, vous dÊcouvrirez les concepts de base sous-jacents au domaine du machine learning, ce qu’il est, et vous dÊcouvrirez son histoire et les techniques que les chercheurs utilisent pour travailler avec lui. Explorons ensemble ce nouveau monde de ML ! - -![globe](../images/globe.jpg) -> Photo par Bill Oxford sur Unsplash - -### Leçons - -1. [Introduction au machine learning](../1-intro-to-ML/translations/README.fr.md) -1. [L’histoire du machine learning et de l’IA](../2-history-of-ML/translations/README.fr.md) -1. [ÉquitÊ et machine learning](../3-fairness/translations/README.fr.md) -1. [Techniques de machine learning](../4-techniques-of-ML/translations/README.fr.md) -### CrÊdits - -"Introduction au machine learning" a ÊtÊ Êcrit avec â™Ĩī¸ par une Êquipe de personnes comprenant [Muhammad Sakib Khan Inan](https://twitter.com/Sakibinan), [Ornella Altunyan](https://twitter.com/ornelladotcom) et [Jen Looper](https://twitter.com/jenlooper) - -"L’histoire du machine learning" a ÊtÊ Êcrit avec â™Ĩī¸ par [Jen Looper](https://twitter.com/jenlooper) et [Amy Boyd](https://twitter.com/AmyKateNicho) - -"ÉquitÊ et machine learning" a ÊtÊ Êcrit avec â™Ĩī¸ par [Tomomi Imura](https://twitter.com/girliemac) - -"Techniques de machine learning" a ÊtÊ Êcrit avec â™Ĩī¸ par [Jen Looper](https://twitter.com/jenlooper) et [Chris Noring](https://twitter.com/softchris) diff --git a/1-Introduction/translations/README.hi.md b/1-Introduction/translations/README.hi.md deleted file mode 100644 index 1d7a9b7b..00000000 --- a/1-Introduction/translations/README.hi.md +++ /dev/null @@ -1,28 +0,0 @@ -# ā¤Žā¤ļāĨ€ā¤¨ ā¤˛ā¤°āĨā¤¨ā¤ŋā¤‚ā¤— ā¤•ā¤ž ā¤Ēā¤°ā¤ŋā¤šā¤¯ - -ā¤Ēā¤žā¤ āĨā¤¯ā¤•āĨā¤°ā¤Ž ā¤•āĨ‡ ā¤‡ā¤¸ ā¤­ā¤žā¤— ā¤ŽāĨ‡ā¤‚, ā¤†ā¤Ēā¤•āĨ‹ ā¤Žā¤ļāĨ€ā¤¨ ā¤˛ā¤°āĨā¤¨ā¤ŋā¤‚ā¤— ā¤•āĨ‡ ā¤•āĨā¤ˇāĨ‡ā¤¤āĨā¤° ā¤ŽāĨ‡ā¤‚ ā¤…ā¤‚ā¤¤ā¤°āĨā¤¨ā¤ŋā¤šā¤ŋā¤¤ ā¤ŦāĨā¤¨ā¤ŋā¤¯ā¤žā¤ĻāĨ€ ā¤…ā¤ĩā¤§ā¤žā¤°ā¤Ŗā¤žā¤“ā¤‚ ā¤¸āĨ‡ ā¤Ēā¤°ā¤ŋā¤šā¤ŋā¤¤ ā¤•ā¤°ā¤žā¤¯ā¤ž ā¤œā¤žā¤ā¤—ā¤ž, ā¤¯ā¤š ā¤•āĨā¤¯ā¤ž ā¤šāĨˆ, ā¤‡ā¤¸ā¤•ā¤ž ā¤‡ā¤¤ā¤ŋā¤šā¤žā¤¸ ā¤•āĨā¤¯ā¤ž ā¤šāĨˆ ā¤”ā¤° ā¤‡ā¤¸ā¤•āĨ‡ ā¤¸ā¤žā¤Ĩ ā¤•ā¤žā¤Ž ā¤•ā¤°ā¤¨āĨ‡ ā¤•āĨ‡ ā¤˛ā¤ŋā¤ ā¤ļāĨ‹ā¤§ā¤•ā¤°āĨā¤¤ā¤žā¤“ā¤‚ ā¤ĻāĨā¤ĩā¤žā¤°ā¤ž ā¤‰ā¤Ēā¤¯āĨ‹ā¤— ā¤•āĨ€ ā¤œā¤žā¤¨āĨ‡ ā¤ĩā¤žā¤˛āĨ€ ā¤¤ā¤•ā¤¨āĨ€ā¤•āĨ‹ā¤‚ ā¤•āĨ‡ ā¤Ŧā¤žā¤°āĨ‡ ā¤ŽāĨ‡ā¤‚ ā¤œā¤žā¤¨āĨ‡ā¤‚ā¤—āĨ‡āĨ¤ ā¤†ā¤‡ā¤ ā¤ā¤• ā¤¸ā¤žā¤Ĩ ā¤Žā¤ļāĨ€ā¤¨ ā¤˛ā¤°āĨā¤¨ā¤ŋā¤‚ā¤— ā¤•āĨ€ ā¤‡ā¤¸ ā¤¨ā¤ˆ ā¤ĻāĨā¤¨ā¤ŋā¤¯ā¤ž ā¤•āĨ‹ ā¤ā¤•āĨā¤¸ā¤ĒāĨā¤˛āĨ‹ā¤° ā¤•ā¤°āĨ‡ā¤‚! - -![ā¤—āĨā¤˛āĨ‹ā¤Ŧ](../images/globe.jpg) -> ā¤Ŧā¤ŋā¤˛ ā¤‘ā¤•āĨā¤¸āĨžāĨ‹ā¤°āĨā¤Ą ā¤ĻāĨā¤ĩā¤žā¤°ā¤ž ā¤¤ā¤¸āĨā¤ĩāĨ€ā¤° ā¤…ā¤¨ā¤¸āĨā¤ĒāĨ‡ā¤˛ā¤ļ ā¤Ēā¤° - -### ā¤Ēā¤žā¤  - -1. [ā¤Žā¤ļāĨ€ā¤¨ ā¤˛ā¤°āĨā¤¨ā¤ŋā¤‚ā¤— ā¤•ā¤ž ā¤Ēā¤°ā¤ŋā¤šā¤¯](../1-intro-to-ML/README.md) -1. [ā¤Žā¤ļāĨ€ā¤¨ ā¤˛ā¤°āĨā¤¨ā¤ŋā¤‚ā¤— ā¤”ā¤° ā¤.ā¤†ā¤‡. ā¤•ā¤ž ā¤‡ā¤¤ā¤ŋā¤šā¤žā¤¸ ](../2-history-of-ML/README.md) -1. [ā¤¨ā¤ŋā¤ˇāĨā¤Ēā¤•āĨā¤ˇā¤¤ā¤ž ā¤”ā¤° ā¤Žā¤ļāĨ€ā¤¨ ā¤˛ā¤°āĨā¤¨ā¤ŋā¤‚ā¤—](../3-fairness/README.md) -1. [ā¤Žā¤ļāĨ€ā¤¨ ā¤˛ā¤°āĨā¤¨ā¤ŋā¤‚ā¤— ā¤•āĨ€ ā¤¤ā¤•ā¤¨āĨ€ā¤•āĨ‡](../4-techniques-of-ML/README.md) - -### ā¤•āĨā¤°āĨ‡ā¤Ąā¤ŋā¤Ÿ - -"ā¤Žā¤ļāĨ€ā¤¨ ā¤˛ā¤°āĨā¤¨ā¤ŋā¤‚ā¤— ā¤•ā¤ž ā¤Ēā¤°ā¤ŋā¤šā¤¯" [ā¤ŽāĨā¤šā¤ŽāĨā¤Žā¤Ļ ā¤¸ā¤žā¤•ā¤ŋā¤Ŧ ā¤–ā¤žā¤¨ ā¤‡ā¤Ŗā¤žā¤‚ ](https://twitter.com/Sakibinan), [ā¤“ā¤°āĨā¤¨āĨ‡ā¤˛ā¤ž ā¤…ā¤˛ā¤ŸāĨ‚ā¤¨āĨā¤¯ā¤‚ ](https://twitter.com/ornelladotcom) ā¤”ā¤° [ā¤œāĨ‡ā¤¨ ā¤˛āĨ‚ā¤Ēā¤° ](https://twitter.com/jenlooper) ā¤ĻāĨā¤ĩā¤žā¤°ā¤ž â™Ĩ ā¤¸āĨ‡ ā¤˛ā¤ŋā¤–ā¤ž ā¤—ā¤¯ā¤ž - -"ā¤Žā¤ļāĨ€ā¤¨ ā¤˛ā¤°āĨā¤¨ā¤ŋā¤‚ā¤— ā¤”ā¤° ā¤.ā¤†ā¤‡. ā¤•ā¤ž ā¤‡ā¤¤ā¤ŋā¤šā¤žā¤¸" [ā¤œāĨ‡ā¤¨ ā¤˛āĨ‚ā¤Ēā¤° ](https://twitter.com/jenlooper) ā¤”ā¤° [ā¤ā¤ŽāĨ€ ā¤ŦāĨ‹ā¤¯ā¤Ą](https://twitter.com/AmyKateNicho) ā¤ĻāĨā¤ĩā¤žā¤°ā¤ž â™Ĩ ā¤¸āĨ‡ ā¤˛ā¤ŋā¤–ā¤ž ā¤—ā¤¯ā¤ž - -"ā¤¨ā¤ŋā¤ˇāĨā¤Ēā¤•āĨā¤ˇā¤¤ā¤ž ā¤”ā¤° ā¤Žā¤ļāĨ€ā¤¨ ā¤˛ā¤°āĨā¤¨ā¤ŋā¤‚ā¤—" [ā¤ŸāĨ‹ā¤ŽāĨ‹ā¤ŽāĨ€ ā¤ˆā¤ŽāĨā¤°ā¤ž](https://twitter.com/girliemac) ā¤ĻāĨā¤ĩā¤žā¤°ā¤ž â™Ĩ ā¤¸āĨ‡ ā¤˛ā¤ŋā¤–ā¤ž ā¤—ā¤¯ā¤ž - -"ā¤Žā¤ļāĨ€ā¤¨ ā¤˛ā¤°āĨā¤¨ā¤ŋā¤‚ā¤— ā¤•āĨ€ ā¤¤ā¤•ā¤¨āĨ€ā¤•" [ā¤œāĨ‡ā¤¨ ā¤˛āĨ‚ā¤Ēā¤°](https://twitter.com/jenlooper) ā¤”ā¤° [ā¤•āĨā¤°ā¤ŋā¤¸ ā¤¨āĨ‹ā¤°ā¤ŋā¤‚ā¤— ](https://twitter.com/softchris) ā¤ĻāĨā¤ĩā¤žā¤°ā¤ž â™Ĩ ā¤¸āĨ‡ ā¤˛ā¤ŋā¤–ā¤ž ā¤—ā¤¯ā¤ž - - - - - diff --git a/1-Introduction/translations/README.id.md b/1-Introduction/translations/README.id.md deleted file mode 100644 index 0e6cc557..00000000 --- a/1-Introduction/translations/README.id.md +++ /dev/null @@ -1,23 +0,0 @@ -# Pengantar Machine Learning - -Di bagian kurikulum ini, Kamu akan berkenalan dengan konsep yang mendasari bidang Machine Learning, apa itu Machine Learning, dan belajar mengenai -sejarah serta teknik-teknik yang digunakan oleh para peneliti. Ayo jelajahi dunia baru Machine Learning bersama! - -![bola dunia](../images/globe.jpg) -> Foto oleh Bill Oxford di Unsplash - -### Pelajaran - -1. [Pengantar Machine Learning](../1-intro-to-ML/translations/README.id.md) -1. [Sejarah dari Machine Learning dan AI](../2-history-of-ML/translations/README.id.md) -1. [Keadilan dan Machine Learning](../3-fairness/translations/README.id.md) -1. [Teknik-Teknik Machine Learning](../4-techniques-of-ML/translations/README.id.md) -### Penghargaan - -"Pengantar Machine Learning" ditulis dengan â™Ĩī¸ oleh sebuah tim yang terdiri dari [Muhammad Sakib Khan Inan](https://twitter.com/Sakibinan), [Ornella Altunyan](https://twitter.com/ornelladotcom) dan [Jen Looper](https://twitter.com/jenlooper) - -"Sejarah dari Machine Learning dan AI" ditulis dengan â™Ĩī¸ oleh [Jen Looper](https://twitter.com/jenlooper) dan [Amy Boyd](https://twitter.com/AmyKateNicho) - -"Keadilan dan Machine Learning" ditulis dengan â™Ĩī¸ oleh [Tomomi Imura](https://twitter.com/girliemac) - -"Teknik-Teknik Machine Learning" ditulis dengan â™Ĩī¸ oleh [Jen Looper](https://twitter.com/jenlooper) dan [Chris Noring](https://twitter.com/softchris) diff --git a/1-Introduction/translations/README.it.md b/1-Introduction/translations/README.it.md deleted file mode 100644 index a9460c26..00000000 --- a/1-Introduction/translations/README.it.md +++ /dev/null @@ -1,22 +0,0 @@ -# Introduzione a machine learning - -In questa sezione del programma di studi, verranno presentati i concetti di base sottostanti machine learning, di cosa si tratta, e si imparerà la sua storia e le tecniche utilizzate dai ricercatori per lavorarci. Si esplorerà insieme questo nuovo mondo di ML! - -![globo](../images/globe.jpg) -> Foto di Bill Oxford su Unsplash - -### Lezioni - -1. [Introduzione a machine learning](../1-intro-to-ML/translations/README.it.md) -1. [La storia di machine learning e dell'AI](../2-history-of-ML/translations/README.it.md) -1. [Equità e machine learning](../3-fairness/translations/README.it.md) -1. [Tecniche di machine learning](../4-techniques-of-ML/translations/README.it.md) -### Crediti - -"Introduzione a Machine Learning" scritto con â™Ĩī¸ da un team di persone tra cui [Muhammad Sakib Khan Inan](https://twitter.com/Sakibinan), [Ornella Altunyan](https://twitter.com/ornelladotcom) e [Jen Looper](https://twitter.com/jenlooper) - -"La Storia di Machine Learning" scritto con â™Ĩī¸ da [Jen Looper](https://twitter.com/jenlooper) e [Amy Boyd](https://twitter.com/AmyKateNicho) - -"Equità e Machine Learning" scritto con â™Ĩī¸ da [Tomomi Imura](https://twitter.com/girliemac) - -"Tecniche di Machine Learning" scritto con â™Ĩī¸ da [Jen Looper](https://twitter.com/jenlooper) e [Chris Noring](https://twitter.com/softchris) \ No newline at end of file diff --git a/1-Introduction/translations/README.ja.md b/1-Introduction/translations/README.ja.md deleted file mode 100644 index de7b6ff2..00000000 --- a/1-Introduction/translations/README.ja.md +++ /dev/null @@ -1,23 +0,0 @@ -# 抟æĸ°å­Ļįŋ’へぎ導å…Ĩ - -こぎã‚ģã‚¯ã‚ˇãƒ§ãƒŗでは、抟æĸ°å­Ļįŋ’ぎ分野ぎåŸēį¤Žã¨ãĒるæĻ‚åŋĩ、抟æĸ°å­Ļįŋ’とはäŊ•ã‹ã‚’į´šäģ‹ã—ã€ããŽæ­´å˛ã‚„į ”įŠļč€…ãŒæŠŸæĸ°å­Ļįŋ’ã‚’æ‰ąã†éš›ãĢäŊŋį”¨ã™ã‚‹æŠ€čĄ“ãĢついãĻå­Ļãŗぞす。 新しいMLぎ世į•Œã‚’一įˇ’ãĢæŽĸæą‚ã—ãĻいきぞしょうīŧ - -![地įƒ](../images/globe.jpg) -> UnsplashぎBill OxfordãĢよる写įœŸ - -### ãƒŦッ゚ãƒŗ - -1. [抟æĸ°å­Ļįŋ’へぎ導å…Ĩ](../1-intro-to-ML/translations/README.ja.md) -1. [抟æĸ°å­Ļįŋ’とAIãŽæ­´å˛](../2-history-of-ML/translations/README.ja.md) -1. [抟æĸ°å­Ļįŋ’ãĢおけるå…Ŧåšŗさ](../3-fairness/translations/README.ja.md) -1. [抟æĸ°å­Ļįŋ’ãŽæŠ€čĄ“](../4-techniques-of-ML/translations/README.ja.md) - -### クãƒŦジット - -"抟æĸ°å­Ļįŋ’へぎ導å…Ĩ "は、[Muhammad Sakib Khan Inan](https://twitter.com/Sakibinan)、[Ornella Altunyan](https://twitter.com/ornelladotcom)、[Jen Looper](https://twitter.com/jenlooper)ãĒおぎチãƒŧムãĢよãŖãĻåˆļäŊœã•ã‚Œãžã—た。 - -"抟æĸ°å­Ļįŋ’とAIãŽæ­´å˛" は[Jen Looper](https://twitter.com/jenlooper)、[Amy Boyd](https://twitter.com/AmyKateNicho)ãĢよãŖãĻåˆļäŊœã•ã‚Œãžã—た。 - -"å…Ŧåšŗ性と抟æĸ°å­Ļįŋ’"は[Tomomi Imura](https://twitter.com/girliemac) ãĢよãŖãĻåˆļäŊœã•ã‚Œãžã—た。 - -"抟æĸ°å­Ļįŋ’ãŽæŠ€čĄ“"は[Jen Looper](https://twitter.com/jenlooper)と[Chris Noring](https://twitter.com/softchris) ãĢよãŖãĻåˆļäŊœã•ã‚Œãžã—た。 diff --git a/1-Introduction/translations/README.ko.md b/1-Introduction/translations/README.ko.md deleted file mode 100644 index 4a5147a6..00000000 --- a/1-Introduction/translations/README.ko.md +++ /dev/null @@ -1,23 +0,0 @@ -# 머ė‹ ëŸŦ닝 ė†Œę°œí•˜ę¸° - -ėģ¤ëĻŦ큘ëŸŧė˜ ė´ ė„šė…˜ė—ė„œ, 머ė‹ ëŸŦ닝 필드ė˜ 기ė´ˆę°€ 될 기ëŗ¸ 개념, ė˜ë¯¸, ė—­ė‚Ŧė™€ ė—°ęĩŦėžę°€ ė´ėšŠí•˜ëŠ” 기ėˆ ė„ ë°°ėš¸ ė˜ˆė •ėž…니다. ėƒˆëĄœėš´ MLė˜ ė„¸ęŗ„ëĄœ 같ė´ ëĒ¨í—˜ė„ 떠납ė‹œë‹¤! - -![globe](../images/globe.jpg) -> Photo by Bill Oxford on Unsplash - -### 강ė˜ - -1. [머ė‹ ëŸŦ닝 ė†Œę°œí•˜ę¸°](../1-intro-to-ML/translations/README.ko.md) -1. [머ė‹ ëŸŦ닝ęŗŧ AIė˜ ė—­ė‚Ŧ](../2-history-of-ML/translations/README.ko.md) -1. [ęŗĩė •ė„ąęŗŧ 머ė‹ ëŸŦ닝](../3-fairness/translations/README.ko.md) -1. [머ė‹ ëŸŦ닝ė˜ 기ėˆ ](../4-techniques-of-ML/translations/README.ko.md) - -### íŦ레딧 - -"Introduction to Machine Learning" was written with â™Ĩī¸ by a team of folks including [Muhammad Sakib Khan Inan](https://twitter.com/Sakibinan), [Ornella Altunyan](https://twitter.com/ornelladotcom) and [Jen Looper](https://twitter.com/jenlooper) - -"The History of Machine Learning" was written with â™Ĩī¸ by [Jen Looper](https://twitter.com/jenlooper) and [Amy Boyd](https://twitter.com/AmyKateNicho) - -"Fairness and Machine Learning" was written with â™Ĩī¸ by [Tomomi Imura](https://twitter.com/girliemac) - -"Techniques of Machine Learning" was written with â™Ĩī¸ by [Jen Looper](https://twitter.com/jenlooper) and [Chris Noring](https://twitter.com/softchris) \ No newline at end of file diff --git a/1-Introduction/translations/README.pt-br.md b/1-Introduction/translations/README.pt-br.md deleted file mode 100644 index 317f5eda..00000000 --- a/1-Introduction/translations/README.pt-br.md +++ /dev/null @@ -1,23 +0,0 @@ -# IntroduçÃŖo ao machine learning - -Nesta seçÃŖo do curso, vocÃĒ conhecerÃĄ os conceitos bÃĄsicos do machine learning, o que ele Ê, e aprenderÃĄ sobre sua histÃŗria e as tÊcnicas que os pesquisadores usam para trabalhar com ele. Vamos explorar este novo mundo de ML juntos! - -![globe](../images/globe.jpg) -> Foto por Bill Oxford em Unsplash - -### LiçÃĩes - -1. [IntroduçÃŖo ao machine learning](../1-intro-to-ML/translations/README.pt-br.md) -2. [A histÃŗria do machine learning e AI](../2-history-of-ML/translations/README.pt-br.md) -3. [Equidade e machine learning](../3-fairness/translations/README.pt-br.md) -4. [TÊcnicas de machine learning](../4-techniques-of-ML/translations/README.pt-br.md) - -### CrÊditos - -"IntroduçÃŖo ao Machine Learning" foi escrito com â™Ĩī¸ por uma equipe de pessoas, incluindo [Muhammad Sakib Khan Inan](https://twitter.com/Sakibinan), [Ornella Altunyan](https://twitter.com/ornelladotcom) e [Jen Looper](https://twitter.com/jenlooper) - -"A histÃŗria do Machine Learning e AI" foi escrito com â™Ĩī¸ por [Jen Looper](https://twitter.com/jenlooper) e [Amy Boyd](https://twitter.com/AmyKateNicho) - -"Equidade e Machine Learning" foi escrito com â™Ĩī¸ por [Tomomi Imura](https://twitter.com/girliemac) - -"TÊcnicas de Machine Learning" foi escrito com â™Ĩī¸ por [Jen Looper](https://twitter.com/jenlooper) e [Chris Noring](https://twitter.com/softchris) \ No newline at end of file diff --git a/1-Introduction/translations/README.ru.md b/1-Introduction/translations/README.ru.md deleted file mode 100644 index 87569f68..00000000 --- a/1-Introduction/translations/README.ru.md +++ /dev/null @@ -1,22 +0,0 @@ -# ВвĐĩĐ´ĐĩĐŊиĐĩ в ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐĩ ОйŅƒŅ‡ĐĩĐŊиĐĩ - -В ŅŅ‚ĐžĐŧ Ņ€Đ°ĐˇĐ´ĐĩĐģĐĩ ŅƒŅ‡ĐĩĐąĐŊОК ĐŋŅ€ĐžĐŗŅ€Đ°ĐŧĐŧŅ‹ вŅ‹ ĐŋОСĐŊĐ°ĐēĐžĐŧиŅ‚ĐĩŅŅŒ Ņ йаСОвŅ‹Đŧи ĐēĐžĐŊŅ†ĐĩĐŋŅ†Đ¸ŅĐŧи, ĐģĐĩĐļĐ°Ņ‰Đ¸Đŧи в ĐžŅĐŊОвĐĩ ОйĐģĐ°ŅŅ‚и ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐŗĐž ОйŅƒŅ‡ĐĩĐŊиŅ; ŅƒĐˇĐŊĐ°ĐĩŅ‚Đĩ, Ņ‡Ņ‚Đž ŅŅ‚Đž Ņ‚Đ°ĐēĐžĐĩ, Đ° Ņ‚Đ°ĐēĐļĐĩ ĐĩĐŗĐž иŅŅ‚ĐžŅ€Đ¸ŅŽ и ĐŧĐĩŅ‚ОдŅ‹, ĐēĐžŅ‚ĐžŅ€Ņ‹Đĩ иŅŅĐģĐĩдОваŅ‚ĐĩĐģи иŅĐŋĐžĐģŅŒĐˇŅƒŅŽŅ‚ Đ´ĐģŅ Ņ€Đ°ĐąĐžŅ‚Ņ‹ Ņ ĐŊиĐŧ. ДавайŅ‚Đĩ вĐŧĐĩŅŅ‚Đĩ иŅŅĐģĐĩĐ´ŅƒĐĩĐŧ ŅŅ‚ĐžŅ‚ ĐŊОвŅ‹Đš ĐŧиŅ€ ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐŗĐž ОйŅƒŅ‡ĐĩĐŊиŅ! - -![ĐŗĐģОйŅƒŅ](../images/globe.jpg) -> ФОŅ‚Đž БиĐģĐģĐ° ОĐēŅŅ„ĐžŅ€Đ´Đ° ĐŊĐ° Unsplash - -### ĐŖŅ€ĐžĐēи - -1. [ВвĐĩĐ´ĐĩĐŊиĐĩ в ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐĩ ОйŅƒŅ‡ĐĩĐŊиĐĩ](../1-intro-to-ML/README.md) -1. [ИŅŅ‚ĐžŅ€Đ¸Ņ ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐŗĐž ОйŅƒŅ‡ĐĩĐŊиŅ и иŅĐēŅƒŅŅŅ‚вĐĩĐŊĐŊĐžĐŗĐž иĐŊŅ‚ĐĩĐģĐģĐĩĐēŅ‚Đ°](../2-history-of-ML/README.md) -1. [ĐĄĐŋŅ€Đ°Đ˛ĐĩĐ´ĐģивОŅŅ‚ŅŒ и ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐĩ ОйŅƒŅ‡ĐĩĐŊиĐĩ](../3-fairness/README.md) -1. [ПŅ€Đ¸ĐĩĐŧŅ‹ ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐŗĐž ОйŅƒŅ‡ĐĩĐŊиŅ](../4-techniques-of-ML/README.md) -### БĐģĐ°ĐŗОдаŅ€ĐŊĐžŅŅ‚и - -ÂĢВвĐĩĐ´ĐĩĐŊиĐĩ в ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐĩ ОйŅƒŅ‡ĐĩĐŊиĐĩÂģ ĐąŅ‹ĐģĐž ĐŊĐ°ĐŋиŅĐ°ĐŊĐž Ņ â™Ĩ ī¸ĐŗŅ€ŅƒĐŋĐŋОК ĐģŅŽĐ´ĐĩĐš, вĐēĐģŅŽŅ‡Đ°Ņ [МŅƒŅ…Đ°ĐŧĐŧĐ°Đ´ ĐĄĐ°Đēий ĐĨĐ°ĐŊ ИĐŊĐ°ĐŊ](https://twitter.com/Sakibinan), [ОŅ€ĐŊĐĩĐģĐģĐ° АĐģŅ‚ŅƒĐŊŅĐŊ](https://twitter.com/ornelladotcom) и [ДĐļĐĩĐŊ ЛŅƒĐŋĐĩŅ€](https://twitter.com/jenlooper) - -ÂĢИŅŅ‚ĐžŅ€Đ¸Ņ ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐŗĐž ОйŅƒŅ‡ĐĩĐŊиŅÂģ ĐąŅ‹ĐģĐ° ĐŊĐ°ĐŋиŅĐ°ĐŊĐ° Ņ â™Ĩ ī¸[ДĐļĐĩĐŊ ЛŅƒĐŋĐĩŅ€](https://twitter.com/jenlooper) и [Đ­Đŧи Бойд](https://twitter.com/AmyKateNicho) - -ÂĢĐĄĐŋŅ€Đ°Đ˛ĐĩĐ´ĐģивОŅŅ‚ŅŒ и ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐĩ ОйŅƒŅ‡ĐĩĐŊиĐĩÂģ ĐąŅ‹Đģи ĐŊĐ°ĐŋиŅĐ°ĐŊŅ‹ Ņ â™Ĩ ī¸[ĐĸĐžĐŧĐžĐŧи ИĐŧŅƒŅ€Đ°](https://twitter.com/girliemac) - -ÂĢМĐĩŅ‚ОдŅ‹ ĐŧĐ°ŅˆĐ¸ĐŊĐŊĐžĐŗĐž ОйŅƒŅ‡ĐĩĐŊиŅÂģ ĐąŅ‹Đģи ĐŊĐ°ĐŋиŅĐ°ĐŊŅ‹ Ņ â™Ĩ ī¸[ДĐļĐĩĐŊ ЛŅƒĐŋĐĩŅ€](https://twitter.com/jenlooper) и [КŅ€Đ¸Ņ НоŅ€Đ¸ĐŊĐŗ](https://twitter.com/softchris) diff --git a/1-Introduction/translations/README.zh-cn.md b/1-Introduction/translations/README.zh-cn.md deleted file mode 100644 index 862a5b0a..00000000 --- a/1-Introduction/translations/README.zh-cn.md +++ /dev/null @@ -1,22 +0,0 @@ -# æœē器å­Ļäš å…Ĩ门 - -č¯žį¨‹įš„æœŦįĢ čŠ‚å°†ä¸ē您äģ‹įģæœē器å­Ļäš éĸ†åŸŸčƒŒåŽįš„åŸēæœŦæĻ‚åŋĩ、äģ€äšˆæ˜¯æœē器å­Ļäš īŧŒåšļå­Ļ䚠厃įš„åŽ†å˛äģĨ及曞ä¸ē此做å‡ēč´ĄįŒŽįš„技术į ”įŠļ者äģŦã€‚čŽŠæˆ‘äģŦ一čĩˇåŧ€å§‹æŽĸį´ĸæœē器å­Ļäš įš„全新世į•Œå§īŧ - -![globe](../images/globe.jpg) -> 回į‰‡į”ą Bill Oxford 提䞛īŧŒæĨč‡Ē Unsplash - -### č¯žį¨‹åŽ‰æŽ’ - -1. [æœē器å­Ļäš įŽ€äģ‹](../1-intro-to-ML/translations/README.zh-cn.md) -1. [æœē器å­Ļäš įš„åŽ†å˛](../2-history-of-ML/translations/README.zh-cn.md) -1. [æœē器å­Ļ䚠中įš„å…Ŧåšŗ性](../3-fairness/translations/README.zh-cn.md) -1. [æœē器å­Ļ䚠技术](../4-techniques-of-ML/translations/README.zh-cn.md) -### 致č°ĸ - -"æœē器å­Ļäš įŽ€äģ‹"į”ą [Muhammad Sakib Khan Inan](https://twitter.com/Sakibinan), [Ornella Altunyan](https://twitter.com/ornelladotcom) 及 [Jen Looper](https://twitter.com/jenlooper)īŧŒå…ąåŒå€ž â™Ĩī¸ 而äŊœ - -"æœē器å­Ļ䚠及äēēåˇĨæ™ēčƒŊåŽ†å˛" į”ą [Jen Looper](https://twitter.com/jenlooper) 及 [Amy Boyd](https://twitter.com/AmyKateNicho)倞 â™Ĩī¸ 而äŊœ - -"å…Ŧåšŗ性与æœē器å­Ļäš " į”ą [Tomomi Imura](https://twitter.com/girliemac) 倞 â™Ĩī¸ 而äŊœ - -"æœē器å­Ļäš įš„技术" į”ą [Jen Looper](https://twitter.com/jenlooper) 及 [Chris Noring](https://twitter.com/softchris) 倞 â™Ĩī¸ 而äŊœ diff --git a/1-Introduction/translations/README.zh-tw.md b/1-Introduction/translations/README.zh-tw.md deleted file mode 100644 index 36359d0d..00000000 --- a/1-Introduction/translations/README.zh-tw.md +++ /dev/null @@ -1,22 +0,0 @@ -# 抟器學įŋ’å…Ĩ門 - -čĒ˛į¨‹įš„æœŦįĢ į¯€å°‡į‚ē您äģ‹į´šæŠŸå™¨å­¸įŋ’é ˜åŸŸčƒŒåžŒįš„åŸēæœŦæĻ‚åŋĩ、äģ€éēŊ是抟器學įŋ’īŧŒä¸Ļå­¸įŋ’厃įš„æ­ˇå˛äģĨ及曞į‚ē此做å‡ēč˛ĸįģįš„æŠ€čĄ“į ”įŠļč€…å€‘ã€‚čŽ“æˆ‘å€‘ä¸€čĩˇé–‹å§‹æŽĸį´ĸ抟器學įŋ’įš„全新世į•Œå§īŧ - -![globe](../images/globe.jpg) -> 圖į‰‡į”ą Bill Oxford提䞛īŧŒäž†č‡Ē Unsplash - -### čĒ˛į¨‹åŽ‰æŽ’ - -1. [抟器學įŋ’į°Ąäģ‹](../1-intro-to-ML/translations/README.zh-tw.md) -1. [抟器學įŋ’įš„æ­ˇå˛](../2-history-of-ML/translations/README.zh-tw.md) -1. [抟器學įŋ’中įš„å…Ŧåšŗ性](../3-fairness/translations/README.zh-tw.md) -1. [抟器學įŋ’æŠ€čĄ“](../4-techniques-of-ML/translations/README.zh-tw.md) -### 致čŦ - -"抟器學įŋ’į°Ąäģ‹"į”ą [Muhammad Sakib Khan Inan](https://twitter.com/Sakibinan), [Ornella Altunyan](https://twitter.com/ornelladotcom) 及 [Jen Looper](https://twitter.com/jenlooper)īŧŒå…ąåŒå‚ž â™Ĩī¸ 而äŊœ - -"抟器學įŋ’及äēēåˇĨæ™ēčƒŊæ­ˇå˛" į”ą [Jen Looper](https://twitter.com/jenlooper) 及 [Amy Boyd](https://twitter.com/AmyKateNicho)å‚ž â™Ĩī¸ 而äŊœ - -"å…Ŧåšŗæ€§čˆ‡æŠŸå™¨å­¸įŋ’" į”ą [Tomomi Imura](https://twitter.com/girliemac) å‚ž â™Ĩī¸ 而äŊœ - -"抟器學įŋ’įš„æŠ€čĄ“" į”ą [Jen Looper](https://twitter.com/jenlooper) 及 [Chris Noring](https://twitter.com/softchris) å‚ž â™Ĩī¸ 而äŊœ diff --git a/9-Real-World/2-Debugging-ML-Models/images/ceos.png b/9-Real-World/2-Debugging-ML-Models/images/ceos.png deleted file mode 100644 index 358bfca2..00000000 Binary files a/9-Real-World/2-Debugging-ML-Models/images/ceos.png and /dev/null differ diff --git a/9-Real-World/2-Debugging-ML-Models/images/fairness.png b/9-Real-World/2-Debugging-ML-Models/images/fairness.png deleted file mode 100644 index ad6c370c..00000000 Binary files a/9-Real-World/2-Debugging-ML-Models/images/fairness.png and /dev/null differ diff --git a/9-Real-World/2-Debugging-ML-Models/images/gender-bias-translate-en-tr.png b/9-Real-World/2-Debugging-ML-Models/images/gender-bias-translate-en-tr.png deleted file mode 100644 index 652278bd..00000000 Binary files a/9-Real-World/2-Debugging-ML-Models/images/gender-bias-translate-en-tr.png and /dev/null differ diff --git a/9-Real-World/2-Debugging-ML-Models/images/gender-bias-translate-tr-en.png b/9-Real-World/2-Debugging-ML-Models/images/gender-bias-translate-tr-en.png deleted file mode 100644 index eee8dedc..00000000 Binary files a/9-Real-World/2-Debugging-ML-Models/images/gender-bias-translate-tr-en.png and /dev/null differ diff --git a/9-Real-World/2-Debugging-ML-Models/translations/README.es.md b/9-Real-World/2-Debugging-ML-Models/translations/README.es.md deleted file mode 100644 index e69de29b..00000000 diff --git a/9-Real-World/2-Debugging-ML-Models/translations/README.fr.md b/9-Real-World/2-Debugging-ML-Models/translations/README.fr.md deleted file mode 100644 index e69de29b..00000000 diff --git a/9-Real-World/2-Debugging-ML-Models/translations/README.id.md b/9-Real-World/2-Debugging-ML-Models/translations/README.id.md deleted file mode 100644 index e69de29b..00000000 diff --git a/9-Real-World/2-Debugging-ML-Models/translations/README.it.md b/9-Real-World/2-Debugging-ML-Models/translations/README.it.md deleted file mode 100644 index e69de29b..00000000 diff --git a/9-Real-World/2-Debugging-ML-Models/translations/README.ja.md b/9-Real-World/2-Debugging-ML-Models/translations/README.ja.md deleted file mode 100644 index e69de29b..00000000 diff --git a/9-Real-World/2-Debugging-ML-Models/translations/README.ko.md b/9-Real-World/2-Debugging-ML-Models/translations/README.ko.md deleted file mode 100644 index e69de29b..00000000 diff --git a/9-Real-World/2-Debugging-ML-Models/translations/README.pt-br.md b/9-Real-World/2-Debugging-ML-Models/translations/README.pt-br.md deleted file mode 100644 index e69de29b..00000000 diff --git a/9-Real-World/2-Debugging-ML-Models/translations/README.zh-cn.md b/9-Real-World/2-Debugging-ML-Models/translations/README.zh-cn.md deleted file mode 100644 index e69de29b..00000000 diff --git a/9-Real-World/2-Debugging-ML-Models/translations/README.zh-tw.md b/9-Real-World/2-Debugging-ML-Models/translations/README.zh-tw.md deleted file mode 100644 index e69de29b..00000000 diff --git a/9-Real-World/2-Debugging-ML-Models/translations/assignment.fr.md b/9-Real-World/2-Debugging-ML-Models/translations/assignment.fr.md deleted file mode 100644 index e69de29b..00000000 diff --git a/9-Real-World/2-Debugging-ML-Models/translations/assignment.id.md b/9-Real-World/2-Debugging-ML-Models/translations/assignment.id.md deleted file mode 100644 index e69de29b..00000000 diff --git a/9-Real-World/2-Debugging-ML-Models/translations/assignment.it.md b/9-Real-World/2-Debugging-ML-Models/translations/assignment.it.md deleted file mode 100644 index e69de29b..00000000 diff --git a/9-Real-World/2-Debugging-ML-Models/translations/assignment.ja.md b/9-Real-World/2-Debugging-ML-Models/translations/assignment.ja.md deleted file mode 100644 index e69de29b..00000000 diff --git a/9-Real-World/2-Debugging-ML-Models/translations/assignment.ko.md b/9-Real-World/2-Debugging-ML-Models/translations/assignment.ko.md deleted file mode 100644 index e69de29b..00000000 diff --git a/9-Real-World/2-Debugging-ML-Models/translations/assignment.pt-br.md b/9-Real-World/2-Debugging-ML-Models/translations/assignment.pt-br.md deleted file mode 100644 index e69de29b..00000000 diff --git a/9-Real-World/2-Debugging-ML-Models/translations/assignment.zh-cn.md b/9-Real-World/2-Debugging-ML-Models/translations/assignment.zh-cn.md deleted file mode 100644 index e69de29b..00000000 diff --git a/9-Real-World/2-Debugging-ML-Models/translations/assignment.zh-tw.md b/9-Real-World/2-Debugging-ML-Models/translations/assignment.zh-tw.md deleted file mode 100644 index e69de29b..00000000 diff --git a/.gitignore b/Example project - Github_pages/.gitignore similarity index 100% rename from .gitignore rename to Example project - Github_pages/.gitignore diff --git a/2-Regression/1-Tools/README.md b/Example project - Github_pages/2-Regression/1-Tools/README.md similarity index 100% rename from 2-Regression/1-Tools/README.md rename to Example project - Github_pages/2-Regression/1-Tools/README.md diff --git a/2-Regression/1-Tools/assignment.md b/Example project - Github_pages/2-Regression/1-Tools/assignment.md similarity index 100% rename from 2-Regression/1-Tools/assignment.md rename to Example project - Github_pages/2-Regression/1-Tools/assignment.md diff --git a/2-Regression/1-Tools/images/encouRage.jpg b/Example project - Github_pages/2-Regression/1-Tools/images/encouRage.jpg similarity index 100% rename from 2-Regression/1-Tools/images/encouRage.jpg rename to Example project - Github_pages/2-Regression/1-Tools/images/encouRage.jpg diff --git a/2-Regression/1-Tools/images/notebook.jpg b/Example project - Github_pages/2-Regression/1-Tools/images/notebook.jpg similarity index 100% rename from 2-Regression/1-Tools/images/notebook.jpg rename to Example project - Github_pages/2-Regression/1-Tools/images/notebook.jpg diff --git a/2-Regression/1-Tools/images/scatterplot.png b/Example project - Github_pages/2-Regression/1-Tools/images/scatterplot.png similarity index 100% rename from 2-Regression/1-Tools/images/scatterplot.png rename to Example project - Github_pages/2-Regression/1-Tools/images/scatterplot.png diff --git a/2-Regression/1-Tools/notebook.ipynb b/Example project - Github_pages/2-Regression/1-Tools/notebook.ipynb similarity index 100% rename from 2-Regression/1-Tools/notebook.ipynb rename to Example project - Github_pages/2-Regression/1-Tools/notebook.ipynb diff --git a/2-Regression/1-Tools/solution/Julia/README.md b/Example project - Github_pages/2-Regression/1-Tools/solution/Julia/README.md similarity index 100% rename from 2-Regression/1-Tools/solution/Julia/README.md rename to Example project - Github_pages/2-Regression/1-Tools/solution/Julia/README.md diff --git a/2-Regression/1-Tools/solution/R/lesson_1-R.ipynb b/Example project - Github_pages/2-Regression/1-Tools/solution/R/lesson_1-R.ipynb similarity index 100% rename from 2-Regression/1-Tools/solution/R/lesson_1-R.ipynb rename to Example project - Github_pages/2-Regression/1-Tools/solution/R/lesson_1-R.ipynb diff --git a/2-Regression/1-Tools/solution/R/lesson_1.Rmd b/Example project - Github_pages/2-Regression/1-Tools/solution/R/lesson_1.Rmd similarity index 100% rename from 2-Regression/1-Tools/solution/R/lesson_1.Rmd rename to Example project - Github_pages/2-Regression/1-Tools/solution/R/lesson_1.Rmd diff --git a/2-Regression/1-Tools/solution/R/lesson_1.html b/Example project - Github_pages/2-Regression/1-Tools/solution/R/lesson_1.html similarity index 100% rename from 2-Regression/1-Tools/solution/R/lesson_1.html rename to Example project - Github_pages/2-Regression/1-Tools/solution/R/lesson_1.html diff --git a/2-Regression/1-Tools/solution/notebook.ipynb b/Example project - Github_pages/2-Regression/1-Tools/solution/notebook.ipynb similarity index 100% rename from 2-Regression/1-Tools/solution/notebook.ipynb rename to Example project - Github_pages/2-Regression/1-Tools/solution/notebook.ipynb diff --git a/2-Regression/1-Tools/translations/README.es.md b/Example project - Github_pages/2-Regression/1-Tools/translations/README.es.md similarity index 100% rename from 2-Regression/1-Tools/translations/README.es.md rename to Example project - Github_pages/2-Regression/1-Tools/translations/README.es.md diff --git a/2-Regression/1-Tools/translations/README.id.md b/Example project - Github_pages/2-Regression/1-Tools/translations/README.id.md similarity index 100% rename from 2-Regression/1-Tools/translations/README.id.md rename to Example project - Github_pages/2-Regression/1-Tools/translations/README.id.md diff --git a/2-Regression/1-Tools/translations/README.it.md b/Example project - Github_pages/2-Regression/1-Tools/translations/README.it.md similarity index 100% rename from 2-Regression/1-Tools/translations/README.it.md rename to Example project - Github_pages/2-Regression/1-Tools/translations/README.it.md diff --git a/2-Regression/1-Tools/translations/README.ja.md b/Example project - Github_pages/2-Regression/1-Tools/translations/README.ja.md similarity index 100% rename from 2-Regression/1-Tools/translations/README.ja.md rename to Example project - Github_pages/2-Regression/1-Tools/translations/README.ja.md diff --git a/2-Regression/1-Tools/translations/README.ko.md b/Example project - Github_pages/2-Regression/1-Tools/translations/README.ko.md similarity index 100% rename from 2-Regression/1-Tools/translations/README.ko.md rename to Example project - Github_pages/2-Regression/1-Tools/translations/README.ko.md diff --git a/2-Regression/1-Tools/translations/README.pt-br.md b/Example project - Github_pages/2-Regression/1-Tools/translations/README.pt-br.md similarity index 100% rename from 2-Regression/1-Tools/translations/README.pt-br.md rename to Example project - Github_pages/2-Regression/1-Tools/translations/README.pt-br.md diff --git a/2-Regression/1-Tools/translations/README.pt.md b/Example project - Github_pages/2-Regression/1-Tools/translations/README.pt.md similarity index 100% rename from 2-Regression/1-Tools/translations/README.pt.md rename to Example project - Github_pages/2-Regression/1-Tools/translations/README.pt.md diff --git a/2-Regression/1-Tools/translations/README.tr.md b/Example project - Github_pages/2-Regression/1-Tools/translations/README.tr.md similarity index 100% rename from 2-Regression/1-Tools/translations/README.tr.md rename to Example project - Github_pages/2-Regression/1-Tools/translations/README.tr.md diff --git a/2-Regression/1-Tools/translations/README.zh-cn.md b/Example project - Github_pages/2-Regression/1-Tools/translations/README.zh-cn.md similarity index 100% rename from 2-Regression/1-Tools/translations/README.zh-cn.md rename to Example project - Github_pages/2-Regression/1-Tools/translations/README.zh-cn.md diff --git a/2-Regression/1-Tools/translations/README.zh-tw.md b/Example project - Github_pages/2-Regression/1-Tools/translations/README.zh-tw.md similarity index 100% rename from 2-Regression/1-Tools/translations/README.zh-tw.md rename to Example project - Github_pages/2-Regression/1-Tools/translations/README.zh-tw.md diff --git a/2-Regression/1-Tools/translations/assignment.es.md b/Example project - Github_pages/2-Regression/1-Tools/translations/assignment.es.md similarity index 100% rename from 2-Regression/1-Tools/translations/assignment.es.md rename to Example project - Github_pages/2-Regression/1-Tools/translations/assignment.es.md diff --git a/2-Regression/1-Tools/translations/assignment.it.md b/Example project - Github_pages/2-Regression/1-Tools/translations/assignment.it.md similarity index 100% rename from 2-Regression/1-Tools/translations/assignment.it.md rename to Example project - Github_pages/2-Regression/1-Tools/translations/assignment.it.md diff --git a/2-Regression/1-Tools/translations/assignment.ja.md b/Example project - Github_pages/2-Regression/1-Tools/translations/assignment.ja.md similarity index 100% rename from 2-Regression/1-Tools/translations/assignment.ja.md rename to Example project - Github_pages/2-Regression/1-Tools/translations/assignment.ja.md diff --git a/2-Regression/1-Tools/translations/assignment.ko.md b/Example project - Github_pages/2-Regression/1-Tools/translations/assignment.ko.md similarity index 100% rename from 2-Regression/1-Tools/translations/assignment.ko.md rename to Example project - Github_pages/2-Regression/1-Tools/translations/assignment.ko.md diff --git a/2-Regression/1-Tools/translations/assignment.pt-br.md b/Example project - Github_pages/2-Regression/1-Tools/translations/assignment.pt-br.md similarity index 100% rename from 2-Regression/1-Tools/translations/assignment.pt-br.md rename to Example project - Github_pages/2-Regression/1-Tools/translations/assignment.pt-br.md diff --git a/2-Regression/1-Tools/translations/assignment.pt.md b/Example project - Github_pages/2-Regression/1-Tools/translations/assignment.pt.md similarity index 100% rename from 2-Regression/1-Tools/translations/assignment.pt.md rename to Example project - Github_pages/2-Regression/1-Tools/translations/assignment.pt.md diff --git a/2-Regression/1-Tools/translations/assignment.tr.md b/Example project - Github_pages/2-Regression/1-Tools/translations/assignment.tr.md similarity index 100% rename from 2-Regression/1-Tools/translations/assignment.tr.md rename to Example project - Github_pages/2-Regression/1-Tools/translations/assignment.tr.md diff --git a/2-Regression/1-Tools/translations/assignment.zh-cn.md b/Example project - Github_pages/2-Regression/1-Tools/translations/assignment.zh-cn.md similarity index 100% rename from 2-Regression/1-Tools/translations/assignment.zh-cn.md rename to Example project - Github_pages/2-Regression/1-Tools/translations/assignment.zh-cn.md diff --git a/2-Regression/1-Tools/translations/assignment.zh-tw.md b/Example project - Github_pages/2-Regression/1-Tools/translations/assignment.zh-tw.md similarity index 100% rename from 2-Regression/1-Tools/translations/assignment.zh-tw.md rename to Example project - Github_pages/2-Regression/1-Tools/translations/assignment.zh-tw.md diff --git a/2-Regression/2-Data/README.md b/Example project - Github_pages/2-Regression/2-Data/README.md similarity index 100% rename from 2-Regression/2-Data/README.md rename to Example project - Github_pages/2-Regression/2-Data/README.md diff --git a/2-Regression/2-Data/assignment.md b/Example project - Github_pages/2-Regression/2-Data/assignment.md similarity index 100% rename from 2-Regression/2-Data/assignment.md rename to Example project - Github_pages/2-Regression/2-Data/assignment.md diff --git a/2-Regression/2-Data/images/barchart.png b/Example project - Github_pages/2-Regression/2-Data/images/barchart.png similarity index 100% rename from 2-Regression/2-Data/images/barchart.png rename to Example project - Github_pages/2-Regression/2-Data/images/barchart.png diff --git a/2-Regression/2-Data/images/data-visualization.png b/Example project - Github_pages/2-Regression/2-Data/images/data-visualization.png similarity index 100% rename from 2-Regression/2-Data/images/data-visualization.png rename to Example project - Github_pages/2-Regression/2-Data/images/data-visualization.png diff --git a/2-Regression/2-Data/images/dplyr_wrangling.png b/Example project - Github_pages/2-Regression/2-Data/images/dplyr_wrangling.png similarity index 100% rename from 2-Regression/2-Data/images/dplyr_wrangling.png rename to Example project - Github_pages/2-Regression/2-Data/images/dplyr_wrangling.png diff --git a/2-Regression/2-Data/images/scatterplot.png b/Example project - Github_pages/2-Regression/2-Data/images/scatterplot.png similarity index 100% rename from 2-Regression/2-Data/images/scatterplot.png rename to Example project - Github_pages/2-Regression/2-Data/images/scatterplot.png diff --git a/2-Regression/2-Data/images/unruly_data.jpg b/Example project - Github_pages/2-Regression/2-Data/images/unruly_data.jpg similarity index 100% rename from 2-Regression/2-Data/images/unruly_data.jpg rename to Example project - Github_pages/2-Regression/2-Data/images/unruly_data.jpg diff --git a/2-Regression/2-Data/notebook.ipynb b/Example project - Github_pages/2-Regression/2-Data/notebook.ipynb similarity index 100% rename from 2-Regression/2-Data/notebook.ipynb rename to Example project - Github_pages/2-Regression/2-Data/notebook.ipynb diff --git a/2-Regression/2-Data/solution/Julia/README.md b/Example project - Github_pages/2-Regression/2-Data/solution/Julia/README.md similarity index 100% rename from 2-Regression/2-Data/solution/Julia/README.md rename to Example project - Github_pages/2-Regression/2-Data/solution/Julia/README.md diff --git a/2-Regression/2-Data/solution/R/lesson_2-R.ipynb b/Example project - Github_pages/2-Regression/2-Data/solution/R/lesson_2-R.ipynb similarity index 100% rename from 2-Regression/2-Data/solution/R/lesson_2-R.ipynb rename to Example project - Github_pages/2-Regression/2-Data/solution/R/lesson_2-R.ipynb diff --git a/2-Regression/2-Data/solution/R/lesson_2.Rmd b/Example project - Github_pages/2-Regression/2-Data/solution/R/lesson_2.Rmd similarity index 100% rename from 2-Regression/2-Data/solution/R/lesson_2.Rmd rename to Example project - Github_pages/2-Regression/2-Data/solution/R/lesson_2.Rmd diff --git a/2-Regression/2-Data/solution/R/lesson_2.html b/Example project - Github_pages/2-Regression/2-Data/solution/R/lesson_2.html similarity index 100% rename from 2-Regression/2-Data/solution/R/lesson_2.html rename to Example project - Github_pages/2-Regression/2-Data/solution/R/lesson_2.html diff --git a/2-Regression/2-Data/solution/notebook.ipynb b/Example project - Github_pages/2-Regression/2-Data/solution/notebook.ipynb similarity index 100% rename from 2-Regression/2-Data/solution/notebook.ipynb rename to Example project - Github_pages/2-Regression/2-Data/solution/notebook.ipynb diff --git a/2-Regression/2-Data/translations/README.es.md b/Example project - Github_pages/2-Regression/2-Data/translations/README.es.md similarity index 100% rename from 2-Regression/2-Data/translations/README.es.md rename to Example project - Github_pages/2-Regression/2-Data/translations/README.es.md diff --git a/2-Regression/2-Data/translations/README.id.md b/Example project - Github_pages/2-Regression/2-Data/translations/README.id.md similarity index 100% rename from 2-Regression/2-Data/translations/README.id.md rename to Example project - Github_pages/2-Regression/2-Data/translations/README.id.md diff --git a/2-Regression/2-Data/translations/README.it.md b/Example project - Github_pages/2-Regression/2-Data/translations/README.it.md similarity index 100% rename from 2-Regression/2-Data/translations/README.it.md rename to Example project - Github_pages/2-Regression/2-Data/translations/README.it.md diff --git a/2-Regression/2-Data/translations/README.ja.md b/Example project - Github_pages/2-Regression/2-Data/translations/README.ja.md similarity index 100% rename from 2-Regression/2-Data/translations/README.ja.md rename to Example project - Github_pages/2-Regression/2-Data/translations/README.ja.md diff --git a/2-Regression/2-Data/translations/README.ko.md b/Example project - Github_pages/2-Regression/2-Data/translations/README.ko.md similarity index 100% rename from 2-Regression/2-Data/translations/README.ko.md rename to Example project - Github_pages/2-Regression/2-Data/translations/README.ko.md diff --git a/2-Regression/2-Data/translations/README.pt-br.md b/Example project - Github_pages/2-Regression/2-Data/translations/README.pt-br.md similarity index 100% rename from 2-Regression/2-Data/translations/README.pt-br.md rename to Example project - Github_pages/2-Regression/2-Data/translations/README.pt-br.md diff --git a/2-Regression/2-Data/translations/README.pt.md b/Example project - Github_pages/2-Regression/2-Data/translations/README.pt.md similarity index 100% rename from 2-Regression/2-Data/translations/README.pt.md rename to Example project - Github_pages/2-Regression/2-Data/translations/README.pt.md diff --git a/2-Regression/2-Data/translations/README.zh-cn.md b/Example project - Github_pages/2-Regression/2-Data/translations/README.zh-cn.md similarity index 100% rename from 2-Regression/2-Data/translations/README.zh-cn.md rename to Example project - Github_pages/2-Regression/2-Data/translations/README.zh-cn.md diff --git a/2-Regression/2-Data/translations/README.zh-tw.md b/Example project - Github_pages/2-Regression/2-Data/translations/README.zh-tw.md similarity index 100% rename from 2-Regression/2-Data/translations/README.zh-tw.md rename to Example project - Github_pages/2-Regression/2-Data/translations/README.zh-tw.md diff --git a/2-Regression/2-Data/translations/assignment.es.md b/Example project - Github_pages/2-Regression/2-Data/translations/assignment.es.md similarity index 100% rename from 2-Regression/2-Data/translations/assignment.es.md rename to Example project - Github_pages/2-Regression/2-Data/translations/assignment.es.md diff --git a/2-Regression/2-Data/translations/assignment.it.md b/Example project - Github_pages/2-Regression/2-Data/translations/assignment.it.md similarity index 100% rename from 2-Regression/2-Data/translations/assignment.it.md rename to Example project - Github_pages/2-Regression/2-Data/translations/assignment.it.md diff --git a/2-Regression/2-Data/translations/assignment.ja.md b/Example project - Github_pages/2-Regression/2-Data/translations/assignment.ja.md similarity index 100% rename from 2-Regression/2-Data/translations/assignment.ja.md rename to Example project - Github_pages/2-Regression/2-Data/translations/assignment.ja.md diff --git a/2-Regression/2-Data/translations/assignment.ko.md b/Example project - Github_pages/2-Regression/2-Data/translations/assignment.ko.md similarity index 100% rename from 2-Regression/2-Data/translations/assignment.ko.md rename to Example project - Github_pages/2-Regression/2-Data/translations/assignment.ko.md diff --git a/2-Regression/2-Data/translations/assignment.pt-br.md b/Example project - Github_pages/2-Regression/2-Data/translations/assignment.pt-br.md similarity index 100% rename from 2-Regression/2-Data/translations/assignment.pt-br.md rename to Example project - Github_pages/2-Regression/2-Data/translations/assignment.pt-br.md diff --git a/2-Regression/2-Data/translations/assignment.pt.md b/Example project - Github_pages/2-Regression/2-Data/translations/assignment.pt.md similarity index 100% rename from 2-Regression/2-Data/translations/assignment.pt.md rename to Example project - Github_pages/2-Regression/2-Data/translations/assignment.pt.md diff --git a/2-Regression/2-Data/translations/assignment.zh-cn.md b/Example project - Github_pages/2-Regression/2-Data/translations/assignment.zh-cn.md similarity index 100% rename from 2-Regression/2-Data/translations/assignment.zh-cn.md rename to Example project - Github_pages/2-Regression/2-Data/translations/assignment.zh-cn.md diff --git a/2-Regression/2-Data/translations/assignment.zh-tw.md b/Example project - Github_pages/2-Regression/2-Data/translations/assignment.zh-tw.md similarity index 100% rename from 2-Regression/2-Data/translations/assignment.zh-tw.md rename to Example project - Github_pages/2-Regression/2-Data/translations/assignment.zh-tw.md diff --git a/2-Regression/3-Linear/README.md b/Example project - Github_pages/2-Regression/3-Linear/README.md similarity index 100% rename from 2-Regression/3-Linear/README.md rename to Example project - Github_pages/2-Regression/3-Linear/README.md diff --git a/2-Regression/3-Linear/assignment.md b/Example project - Github_pages/2-Regression/3-Linear/assignment.md similarity index 100% rename from 2-Regression/3-Linear/assignment.md rename to Example project - Github_pages/2-Regression/3-Linear/assignment.md diff --git a/2-Regression/3-Linear/images/calculation.png b/Example project - Github_pages/2-Regression/3-Linear/images/calculation.png similarity index 100% rename from 2-Regression/3-Linear/images/calculation.png rename to Example project - Github_pages/2-Regression/3-Linear/images/calculation.png diff --git a/2-Regression/3-Linear/images/heatmap.png b/Example project - Github_pages/2-Regression/3-Linear/images/heatmap.png similarity index 100% rename from 2-Regression/3-Linear/images/heatmap.png rename to Example project - Github_pages/2-Regression/3-Linear/images/heatmap.png diff --git a/2-Regression/3-Linear/images/janitor.jpg b/Example project - Github_pages/2-Regression/3-Linear/images/janitor.jpg similarity index 100% rename from 2-Regression/3-Linear/images/janitor.jpg rename to Example project - Github_pages/2-Regression/3-Linear/images/janitor.jpg diff --git a/2-Regression/3-Linear/images/linear-polynomial.png b/Example project - Github_pages/2-Regression/3-Linear/images/linear-polynomial.png similarity index 100% rename from 2-Regression/3-Linear/images/linear-polynomial.png rename to Example project - Github_pages/2-Regression/3-Linear/images/linear-polynomial.png diff --git a/2-Regression/3-Linear/images/linear-results.png b/Example project - Github_pages/2-Regression/3-Linear/images/linear-results.png similarity index 100% rename from 2-Regression/3-Linear/images/linear-results.png rename to Example project - Github_pages/2-Regression/3-Linear/images/linear-results.png diff --git a/2-Regression/3-Linear/images/linear.png b/Example project - Github_pages/2-Regression/3-Linear/images/linear.png similarity index 100% rename from 2-Regression/3-Linear/images/linear.png rename to Example project - Github_pages/2-Regression/3-Linear/images/linear.png diff --git a/2-Regression/3-Linear/images/pie-pumpkins-scatter.png b/Example project - Github_pages/2-Regression/3-Linear/images/pie-pumpkins-scatter.png similarity index 100% rename from 2-Regression/3-Linear/images/pie-pumpkins-scatter.png rename to Example project - Github_pages/2-Regression/3-Linear/images/pie-pumpkins-scatter.png diff --git a/2-Regression/3-Linear/images/poly-results.png b/Example project - Github_pages/2-Regression/3-Linear/images/poly-results.png similarity index 100% rename from 2-Regression/3-Linear/images/poly-results.png rename to Example project - Github_pages/2-Regression/3-Linear/images/poly-results.png diff --git a/2-Regression/3-Linear/images/polynomial.png b/Example project - Github_pages/2-Regression/3-Linear/images/polynomial.png similarity index 100% rename from 2-Regression/3-Linear/images/polynomial.png rename to Example project - Github_pages/2-Regression/3-Linear/images/polynomial.png diff --git a/2-Regression/3-Linear/images/price-by-variety.png b/Example project - Github_pages/2-Regression/3-Linear/images/price-by-variety.png similarity index 100% rename from 2-Regression/3-Linear/images/price-by-variety.png rename to Example project - Github_pages/2-Regression/3-Linear/images/price-by-variety.png diff --git a/2-Regression/3-Linear/images/recipes.png b/Example project - Github_pages/2-Regression/3-Linear/images/recipes.png similarity index 100% rename from 2-Regression/3-Linear/images/recipes.png rename to Example project - Github_pages/2-Regression/3-Linear/images/recipes.png diff --git a/2-Regression/3-Linear/images/scatter-dayofyear-color.png b/Example project - Github_pages/2-Regression/3-Linear/images/scatter-dayofyear-color.png similarity index 100% rename from 2-Regression/3-Linear/images/scatter-dayofyear-color.png rename to Example project - Github_pages/2-Regression/3-Linear/images/scatter-dayofyear-color.png diff --git a/2-Regression/3-Linear/images/scatter-dayofyear.png b/Example project - Github_pages/2-Regression/3-Linear/images/scatter-dayofyear.png similarity index 100% rename from 2-Regression/3-Linear/images/scatter-dayofyear.png rename to Example project - Github_pages/2-Regression/3-Linear/images/scatter-dayofyear.png diff --git a/2-Regression/3-Linear/images/slope.png b/Example project - Github_pages/2-Regression/3-Linear/images/slope.png similarity index 100% rename from 2-Regression/3-Linear/images/slope.png rename to Example project - Github_pages/2-Regression/3-Linear/images/slope.png diff --git a/2-Regression/3-Linear/notebook.ipynb b/Example project - Github_pages/2-Regression/3-Linear/notebook.ipynb similarity index 100% rename from 2-Regression/3-Linear/notebook.ipynb rename to Example project - Github_pages/2-Regression/3-Linear/notebook.ipynb diff --git a/2-Regression/3-Linear/solution/Julia/README.md b/Example project - Github_pages/2-Regression/3-Linear/solution/Julia/README.md similarity index 100% rename from 2-Regression/3-Linear/solution/Julia/README.md rename to Example project - Github_pages/2-Regression/3-Linear/solution/Julia/README.md diff --git a/2-Regression/3-Linear/solution/R/lesson_3-R.ipynb b/Example project - Github_pages/2-Regression/3-Linear/solution/R/lesson_3-R.ipynb similarity index 100% rename from 2-Regression/3-Linear/solution/R/lesson_3-R.ipynb rename to Example project - Github_pages/2-Regression/3-Linear/solution/R/lesson_3-R.ipynb diff --git a/2-Regression/3-Linear/solution/R/lesson_3.Rmd b/Example project - Github_pages/2-Regression/3-Linear/solution/R/lesson_3.Rmd similarity index 100% rename from 2-Regression/3-Linear/solution/R/lesson_3.Rmd rename to Example project - Github_pages/2-Regression/3-Linear/solution/R/lesson_3.Rmd diff --git a/2-Regression/3-Linear/solution/R/lesson_3.html b/Example project - Github_pages/2-Regression/3-Linear/solution/R/lesson_3.html similarity index 100% rename from 2-Regression/3-Linear/solution/R/lesson_3.html rename to Example project - Github_pages/2-Regression/3-Linear/solution/R/lesson_3.html diff --git a/2-Regression/3-Linear/solution/notebook.ipynb b/Example project - Github_pages/2-Regression/3-Linear/solution/notebook.ipynb similarity index 100% rename from 2-Regression/3-Linear/solution/notebook.ipynb rename to Example project - Github_pages/2-Regression/3-Linear/solution/notebook.ipynb diff --git a/2-Regression/3-Linear/translations/README.es.md b/Example project - Github_pages/2-Regression/3-Linear/translations/README.es.md similarity index 100% rename from 2-Regression/3-Linear/translations/README.es.md rename to Example project - Github_pages/2-Regression/3-Linear/translations/README.es.md diff --git a/2-Regression/3-Linear/translations/README.id.md b/Example project - Github_pages/2-Regression/3-Linear/translations/README.id.md similarity index 100% rename from 2-Regression/3-Linear/translations/README.id.md rename to Example project - Github_pages/2-Regression/3-Linear/translations/README.id.md diff --git a/2-Regression/3-Linear/translations/README.it.md b/Example project - Github_pages/2-Regression/3-Linear/translations/README.it.md similarity index 100% rename from 2-Regression/3-Linear/translations/README.it.md rename to Example project - Github_pages/2-Regression/3-Linear/translations/README.it.md diff --git a/2-Regression/3-Linear/translations/README.ja.md b/Example project - Github_pages/2-Regression/3-Linear/translations/README.ja.md similarity index 100% rename from 2-Regression/3-Linear/translations/README.ja.md rename to Example project - Github_pages/2-Regression/3-Linear/translations/README.ja.md diff --git a/2-Regression/3-Linear/translations/README.ko.md b/Example project - Github_pages/2-Regression/3-Linear/translations/README.ko.md similarity index 100% rename from 2-Regression/3-Linear/translations/README.ko.md rename to Example project - Github_pages/2-Regression/3-Linear/translations/README.ko.md diff --git a/2-Regression/3-Linear/translations/README.pt-br.md b/Example project - Github_pages/2-Regression/3-Linear/translations/README.pt-br.md similarity index 100% rename from 2-Regression/3-Linear/translations/README.pt-br.md rename to Example project - Github_pages/2-Regression/3-Linear/translations/README.pt-br.md diff --git a/2-Regression/3-Linear/translations/README.pt.md b/Example project - Github_pages/2-Regression/3-Linear/translations/README.pt.md similarity index 100% rename from 2-Regression/3-Linear/translations/README.pt.md rename to Example project - Github_pages/2-Regression/3-Linear/translations/README.pt.md diff --git a/2-Regression/3-Linear/translations/README.zh-cn.md b/Example project - Github_pages/2-Regression/3-Linear/translations/README.zh-cn.md similarity index 100% rename from 2-Regression/3-Linear/translations/README.zh-cn.md rename to Example project - Github_pages/2-Regression/3-Linear/translations/README.zh-cn.md diff --git a/2-Regression/3-Linear/translations/README.zh-tw.md b/Example project - Github_pages/2-Regression/3-Linear/translations/README.zh-tw.md similarity index 100% rename from 2-Regression/3-Linear/translations/README.zh-tw.md rename to Example project - Github_pages/2-Regression/3-Linear/translations/README.zh-tw.md diff --git a/2-Regression/3-Linear/translations/assignment.es.md b/Example project - Github_pages/2-Regression/3-Linear/translations/assignment.es.md similarity index 100% rename from 2-Regression/3-Linear/translations/assignment.es.md rename to Example project - Github_pages/2-Regression/3-Linear/translations/assignment.es.md diff --git a/2-Regression/3-Linear/translations/assignment.it.md b/Example project - Github_pages/2-Regression/3-Linear/translations/assignment.it.md similarity index 100% rename from 2-Regression/3-Linear/translations/assignment.it.md rename to Example project - Github_pages/2-Regression/3-Linear/translations/assignment.it.md diff --git a/2-Regression/3-Linear/translations/assignment.ja.md b/Example project - Github_pages/2-Regression/3-Linear/translations/assignment.ja.md similarity index 100% rename from 2-Regression/3-Linear/translations/assignment.ja.md rename to Example project - Github_pages/2-Regression/3-Linear/translations/assignment.ja.md diff --git a/2-Regression/3-Linear/translations/assignment.ko.md b/Example project - Github_pages/2-Regression/3-Linear/translations/assignment.ko.md similarity index 100% rename from 2-Regression/3-Linear/translations/assignment.ko.md rename to Example project - Github_pages/2-Regression/3-Linear/translations/assignment.ko.md diff --git a/2-Regression/3-Linear/translations/assignment.pt-br.md b/Example project - Github_pages/2-Regression/3-Linear/translations/assignment.pt-br.md similarity index 100% rename from 2-Regression/3-Linear/translations/assignment.pt-br.md rename to Example project - Github_pages/2-Regression/3-Linear/translations/assignment.pt-br.md diff --git a/2-Regression/3-Linear/translations/assignment.pt.md b/Example project - Github_pages/2-Regression/3-Linear/translations/assignment.pt.md similarity index 100% rename from 2-Regression/3-Linear/translations/assignment.pt.md rename to Example project - Github_pages/2-Regression/3-Linear/translations/assignment.pt.md diff --git a/2-Regression/3-Linear/translations/assignment.zh-cn.md b/Example project - Github_pages/2-Regression/3-Linear/translations/assignment.zh-cn.md similarity index 100% rename from 2-Regression/3-Linear/translations/assignment.zh-cn.md rename to Example project - Github_pages/2-Regression/3-Linear/translations/assignment.zh-cn.md diff --git a/2-Regression/3-Linear/translations/assignment.zh-tw.md b/Example project - Github_pages/2-Regression/3-Linear/translations/assignment.zh-tw.md similarity index 100% rename from 2-Regression/3-Linear/translations/assignment.zh-tw.md rename to Example project - Github_pages/2-Regression/3-Linear/translations/assignment.zh-tw.md diff --git a/2-Regression/4-Logistic/README.md b/Example project - Github_pages/2-Regression/4-Logistic/README.md similarity index 100% rename from 2-Regression/4-Logistic/README.md rename to Example project - Github_pages/2-Regression/4-Logistic/README.md diff --git a/2-Regression/4-Logistic/assignment.md b/Example project - Github_pages/2-Regression/4-Logistic/assignment.md similarity index 100% rename from 2-Regression/4-Logistic/assignment.md rename to Example project - Github_pages/2-Regression/4-Logistic/assignment.md diff --git a/2-Regression/4-Logistic/images/ROC.png b/Example project - Github_pages/2-Regression/4-Logistic/images/ROC.png similarity index 100% rename from 2-Regression/4-Logistic/images/ROC.png rename to Example project - Github_pages/2-Regression/4-Logistic/images/ROC.png diff --git a/2-Regression/4-Logistic/images/ROC_2.png b/Example project - Github_pages/2-Regression/4-Logistic/images/ROC_2.png similarity index 100% rename from 2-Regression/4-Logistic/images/ROC_2.png rename to Example project - Github_pages/2-Regression/4-Logistic/images/ROC_2.png diff --git a/2-Regression/4-Logistic/images/confusion-matrix.png b/Example project - Github_pages/2-Regression/4-Logistic/images/confusion-matrix.png similarity index 100% rename from 2-Regression/4-Logistic/images/confusion-matrix.png rename to Example project - Github_pages/2-Regression/4-Logistic/images/confusion-matrix.png diff --git a/2-Regression/4-Logistic/images/grid.png b/Example project - Github_pages/2-Regression/4-Logistic/images/grid.png similarity index 100% rename from 2-Regression/4-Logistic/images/grid.png rename to Example project - Github_pages/2-Regression/4-Logistic/images/grid.png diff --git a/2-Regression/4-Logistic/images/linear-vs-logistic.png b/Example project - Github_pages/2-Regression/4-Logistic/images/linear-vs-logistic.png similarity index 100% rename from 2-Regression/4-Logistic/images/linear-vs-logistic.png rename to Example project - Github_pages/2-Regression/4-Logistic/images/linear-vs-logistic.png diff --git a/2-Regression/4-Logistic/images/logistic-linear.png b/Example project - Github_pages/2-Regression/4-Logistic/images/logistic-linear.png similarity index 100% rename from 2-Regression/4-Logistic/images/logistic-linear.png rename to Example project - Github_pages/2-Regression/4-Logistic/images/logistic-linear.png diff --git a/2-Regression/4-Logistic/images/logistic.png b/Example project - Github_pages/2-Regression/4-Logistic/images/logistic.png similarity index 100% rename from 2-Regression/4-Logistic/images/logistic.png rename to Example project - Github_pages/2-Regression/4-Logistic/images/logistic.png diff --git a/2-Regression/4-Logistic/images/multinomial-ordinal.png b/Example project - Github_pages/2-Regression/4-Logistic/images/multinomial-ordinal.png similarity index 100% rename from 2-Regression/4-Logistic/images/multinomial-ordinal.png rename to Example project - Github_pages/2-Regression/4-Logistic/images/multinomial-ordinal.png diff --git a/2-Regression/4-Logistic/images/multinomial-vs-ordinal.png b/Example project - Github_pages/2-Regression/4-Logistic/images/multinomial-vs-ordinal.png similarity index 100% rename from 2-Regression/4-Logistic/images/multinomial-vs-ordinal.png rename to Example project - Github_pages/2-Regression/4-Logistic/images/multinomial-vs-ordinal.png diff --git a/2-Regression/4-Logistic/images/pumpkin-classifier.png b/Example project - Github_pages/2-Regression/4-Logistic/images/pumpkin-classifier.png similarity index 100% rename from 2-Regression/4-Logistic/images/pumpkin-classifier.png rename to Example project - Github_pages/2-Regression/4-Logistic/images/pumpkin-classifier.png diff --git a/2-Regression/4-Logistic/images/pumpkins_catplot_1.png b/Example project - Github_pages/2-Regression/4-Logistic/images/pumpkins_catplot_1.png similarity index 100% rename from 2-Regression/4-Logistic/images/pumpkins_catplot_1.png rename to Example project - Github_pages/2-Regression/4-Logistic/images/pumpkins_catplot_1.png diff --git a/2-Regression/4-Logistic/images/pumpkins_catplot_2.png b/Example project - Github_pages/2-Regression/4-Logistic/images/pumpkins_catplot_2.png similarity index 100% rename from 2-Regression/4-Logistic/images/pumpkins_catplot_2.png rename to Example project - Github_pages/2-Regression/4-Logistic/images/pumpkins_catplot_2.png diff --git a/2-Regression/4-Logistic/images/r_learners_sm.jpeg b/Example project - Github_pages/2-Regression/4-Logistic/images/r_learners_sm.jpeg similarity index 100% rename from 2-Regression/4-Logistic/images/r_learners_sm.jpeg rename to Example project - Github_pages/2-Regression/4-Logistic/images/r_learners_sm.jpeg diff --git a/2-Regression/4-Logistic/images/sigmoid.png b/Example project - Github_pages/2-Regression/4-Logistic/images/sigmoid.png similarity index 100% rename from 2-Regression/4-Logistic/images/sigmoid.png rename to Example project - Github_pages/2-Regression/4-Logistic/images/sigmoid.png diff --git a/2-Regression/4-Logistic/images/swarm.png b/Example project - Github_pages/2-Regression/4-Logistic/images/swarm.png similarity index 100% rename from 2-Regression/4-Logistic/images/swarm.png rename to Example project - Github_pages/2-Regression/4-Logistic/images/swarm.png diff --git a/2-Regression/4-Logistic/images/swarm_2.png b/Example project - Github_pages/2-Regression/4-Logistic/images/swarm_2.png similarity index 100% rename from 2-Regression/4-Logistic/images/swarm_2.png rename to Example project - Github_pages/2-Regression/4-Logistic/images/swarm_2.png diff --git a/2-Regression/4-Logistic/images/violin.png b/Example project - Github_pages/2-Regression/4-Logistic/images/violin.png similarity index 100% rename from 2-Regression/4-Logistic/images/violin.png rename to Example project - Github_pages/2-Regression/4-Logistic/images/violin.png diff --git a/2-Regression/4-Logistic/notebook.ipynb b/Example project - Github_pages/2-Regression/4-Logistic/notebook.ipynb similarity index 100% rename from 2-Regression/4-Logistic/notebook.ipynb rename to Example project - Github_pages/2-Regression/4-Logistic/notebook.ipynb diff --git a/2-Regression/4-Logistic/solution/Julia/README.md b/Example project - Github_pages/2-Regression/4-Logistic/solution/Julia/README.md similarity index 100% rename from 2-Regression/4-Logistic/solution/Julia/README.md rename to Example project - Github_pages/2-Regression/4-Logistic/solution/Julia/README.md diff --git a/2-Regression/4-Logistic/solution/R/lesson_4-R.ipynb b/Example project - Github_pages/2-Regression/4-Logistic/solution/R/lesson_4-R.ipynb similarity index 100% rename from 2-Regression/4-Logistic/solution/R/lesson_4-R.ipynb rename to Example project - Github_pages/2-Regression/4-Logistic/solution/R/lesson_4-R.ipynb diff --git a/2-Regression/4-Logistic/solution/R/lesson_4.Rmd b/Example project - Github_pages/2-Regression/4-Logistic/solution/R/lesson_4.Rmd similarity index 100% rename from 2-Regression/4-Logistic/solution/R/lesson_4.Rmd rename to Example project - Github_pages/2-Regression/4-Logistic/solution/R/lesson_4.Rmd diff --git a/2-Regression/4-Logistic/solution/R/lesson_4.html b/Example project - Github_pages/2-Regression/4-Logistic/solution/R/lesson_4.html similarity index 100% rename from 2-Regression/4-Logistic/solution/R/lesson_4.html rename to Example project - Github_pages/2-Regression/4-Logistic/solution/R/lesson_4.html diff --git a/2-Regression/4-Logistic/solution/notebook.ipynb b/Example project - Github_pages/2-Regression/4-Logistic/solution/notebook.ipynb similarity index 100% rename from 2-Regression/4-Logistic/solution/notebook.ipynb rename to Example project - Github_pages/2-Regression/4-Logistic/solution/notebook.ipynb diff --git a/2-Regression/4-Logistic/translations/README.es.md b/Example project - Github_pages/2-Regression/4-Logistic/translations/README.es.md similarity index 100% rename from 2-Regression/4-Logistic/translations/README.es.md rename to Example project - Github_pages/2-Regression/4-Logistic/translations/README.es.md diff --git a/2-Regression/4-Logistic/translations/README.id.md b/Example project - Github_pages/2-Regression/4-Logistic/translations/README.id.md similarity index 100% rename from 2-Regression/4-Logistic/translations/README.id.md rename to Example project - Github_pages/2-Regression/4-Logistic/translations/README.id.md diff --git a/2-Regression/4-Logistic/translations/README.it.md b/Example project - Github_pages/2-Regression/4-Logistic/translations/README.it.md similarity index 100% rename from 2-Regression/4-Logistic/translations/README.it.md rename to Example project - Github_pages/2-Regression/4-Logistic/translations/README.it.md diff --git a/2-Regression/4-Logistic/translations/README.ja.md b/Example project - Github_pages/2-Regression/4-Logistic/translations/README.ja.md similarity index 100% rename from 2-Regression/4-Logistic/translations/README.ja.md rename to Example project - Github_pages/2-Regression/4-Logistic/translations/README.ja.md diff --git a/2-Regression/4-Logistic/translations/README.ko.md b/Example project - Github_pages/2-Regression/4-Logistic/translations/README.ko.md similarity index 100% rename from 2-Regression/4-Logistic/translations/README.ko.md rename to Example project - Github_pages/2-Regression/4-Logistic/translations/README.ko.md diff --git a/2-Regression/4-Logistic/translations/README.pt-br.md b/Example project - Github_pages/2-Regression/4-Logistic/translations/README.pt-br.md similarity index 100% rename from 2-Regression/4-Logistic/translations/README.pt-br.md rename to Example project - Github_pages/2-Regression/4-Logistic/translations/README.pt-br.md diff --git a/2-Regression/4-Logistic/translations/README.pt.md b/Example project - Github_pages/2-Regression/4-Logistic/translations/README.pt.md similarity index 100% rename from 2-Regression/4-Logistic/translations/README.pt.md rename to Example project - Github_pages/2-Regression/4-Logistic/translations/README.pt.md diff --git a/2-Regression/4-Logistic/translations/README.zh-cn.md b/Example project - Github_pages/2-Regression/4-Logistic/translations/README.zh-cn.md similarity index 100% rename from 2-Regression/4-Logistic/translations/README.zh-cn.md rename to Example project - Github_pages/2-Regression/4-Logistic/translations/README.zh-cn.md diff --git a/2-Regression/4-Logistic/translations/README.zh-tw.md b/Example project - Github_pages/2-Regression/4-Logistic/translations/README.zh-tw.md similarity index 100% rename from 2-Regression/4-Logistic/translations/README.zh-tw.md rename to Example project - Github_pages/2-Regression/4-Logistic/translations/README.zh-tw.md diff --git a/2-Regression/4-Logistic/translations/assignment.es.md b/Example project - Github_pages/2-Regression/4-Logistic/translations/assignment.es.md similarity index 100% rename from 2-Regression/4-Logistic/translations/assignment.es.md rename to Example project - Github_pages/2-Regression/4-Logistic/translations/assignment.es.md diff --git a/2-Regression/4-Logistic/translations/assignment.it.md b/Example project - Github_pages/2-Regression/4-Logistic/translations/assignment.it.md similarity index 100% rename from 2-Regression/4-Logistic/translations/assignment.it.md rename to Example project - Github_pages/2-Regression/4-Logistic/translations/assignment.it.md diff --git a/2-Regression/4-Logistic/translations/assignment.ja.md b/Example project - Github_pages/2-Regression/4-Logistic/translations/assignment.ja.md similarity index 100% rename from 2-Regression/4-Logistic/translations/assignment.ja.md rename to Example project - Github_pages/2-Regression/4-Logistic/translations/assignment.ja.md diff --git a/2-Regression/4-Logistic/translations/assignment.ko.md b/Example project - Github_pages/2-Regression/4-Logistic/translations/assignment.ko.md similarity index 100% rename from 2-Regression/4-Logistic/translations/assignment.ko.md rename to Example project - Github_pages/2-Regression/4-Logistic/translations/assignment.ko.md diff --git a/2-Regression/4-Logistic/translations/assignment.pt-br.md b/Example project - Github_pages/2-Regression/4-Logistic/translations/assignment.pt-br.md similarity index 100% rename from 2-Regression/4-Logistic/translations/assignment.pt-br.md rename to Example project - Github_pages/2-Regression/4-Logistic/translations/assignment.pt-br.md diff --git a/2-Regression/4-Logistic/translations/assignment.pt.md b/Example project - Github_pages/2-Regression/4-Logistic/translations/assignment.pt.md similarity index 100% rename from 2-Regression/4-Logistic/translations/assignment.pt.md rename to Example project - Github_pages/2-Regression/4-Logistic/translations/assignment.pt.md diff --git a/2-Regression/4-Logistic/translations/assignment.zh-cn.md b/Example project - Github_pages/2-Regression/4-Logistic/translations/assignment.zh-cn.md similarity index 100% rename from 2-Regression/4-Logistic/translations/assignment.zh-cn.md rename to Example project - Github_pages/2-Regression/4-Logistic/translations/assignment.zh-cn.md diff --git a/2-Regression/4-Logistic/translations/assignment.zh-tw.md b/Example project - Github_pages/2-Regression/4-Logistic/translations/assignment.zh-tw.md similarity index 100% rename from 2-Regression/4-Logistic/translations/assignment.zh-tw.md rename to Example project - Github_pages/2-Regression/4-Logistic/translations/assignment.zh-tw.md diff --git a/2-Regression/README.md b/Example project - Github_pages/2-Regression/README.md similarity index 100% rename from 2-Regression/README.md rename to Example project - Github_pages/2-Regression/README.md diff --git a/2-Regression/data/US-pumpkins.csv b/Example project - Github_pages/2-Regression/data/US-pumpkins.csv similarity index 100% rename from 2-Regression/data/US-pumpkins.csv rename to Example project - Github_pages/2-Regression/data/US-pumpkins.csv diff --git a/2-Regression/images/jack-o-lanterns.jpg b/Example project - Github_pages/2-Regression/images/jack-o-lanterns.jpg similarity index 100% rename from 2-Regression/images/jack-o-lanterns.jpg rename to Example project - Github_pages/2-Regression/images/jack-o-lanterns.jpg diff --git a/2-Regression/translations/README.es.md b/Example project - Github_pages/2-Regression/translations/README.es.md similarity index 100% rename from 2-Regression/translations/README.es.md rename to Example project - Github_pages/2-Regression/translations/README.es.md diff --git a/2-Regression/translations/README.fr.md b/Example project - Github_pages/2-Regression/translations/README.fr.md similarity index 100% rename from 2-Regression/translations/README.fr.md rename to Example project - Github_pages/2-Regression/translations/README.fr.md diff --git a/2-Regression/translations/README.hi.md b/Example project - Github_pages/2-Regression/translations/README.hi.md similarity index 100% rename from 2-Regression/translations/README.hi.md rename to Example project - Github_pages/2-Regression/translations/README.hi.md diff --git a/2-Regression/translations/README.id.md b/Example project - Github_pages/2-Regression/translations/README.id.md similarity index 100% rename from 2-Regression/translations/README.id.md rename to Example project - Github_pages/2-Regression/translations/README.id.md diff --git a/2-Regression/translations/README.it.md b/Example project - Github_pages/2-Regression/translations/README.it.md similarity index 100% rename from 2-Regression/translations/README.it.md rename to Example project - Github_pages/2-Regression/translations/README.it.md diff --git a/2-Regression/translations/README.ja.md b/Example project - Github_pages/2-Regression/translations/README.ja.md similarity index 100% rename from 2-Regression/translations/README.ja.md rename to Example project - Github_pages/2-Regression/translations/README.ja.md diff --git a/2-Regression/translations/README.ko.md b/Example project - Github_pages/2-Regression/translations/README.ko.md similarity index 100% rename from 2-Regression/translations/README.ko.md rename to Example project - Github_pages/2-Regression/translations/README.ko.md diff --git a/2-Regression/translations/README.pt-br.md b/Example project - Github_pages/2-Regression/translations/README.pt-br.md similarity index 100% rename from 2-Regression/translations/README.pt-br.md rename to Example project - Github_pages/2-Regression/translations/README.pt-br.md diff --git a/2-Regression/translations/README.pt.md b/Example project - Github_pages/2-Regression/translations/README.pt.md similarity index 100% rename from 2-Regression/translations/README.pt.md rename to Example project - Github_pages/2-Regression/translations/README.pt.md diff --git a/2-Regression/translations/README.ru.md b/Example project - Github_pages/2-Regression/translations/README.ru.md similarity index 100% rename from 2-Regression/translations/README.ru.md rename to Example project - Github_pages/2-Regression/translations/README.ru.md diff --git a/2-Regression/translations/README.tr.md b/Example project - Github_pages/2-Regression/translations/README.tr.md similarity index 100% rename from 2-Regression/translations/README.tr.md rename to Example project - Github_pages/2-Regression/translations/README.tr.md diff --git a/2-Regression/translations/README.zh-cn.md b/Example project - Github_pages/2-Regression/translations/README.zh-cn.md similarity index 100% rename from 2-Regression/translations/README.zh-cn.md rename to Example project - Github_pages/2-Regression/translations/README.zh-cn.md diff --git a/2-Regression/translations/README.zh-tw.md b/Example project - Github_pages/2-Regression/translations/README.zh-tw.md similarity index 100% rename from 2-Regression/translations/README.zh-tw.md rename to Example project - Github_pages/2-Regression/translations/README.zh-tw.md diff --git a/3-Web-App/1-Web-App/README.md b/Example project - Github_pages/3-Web-App/1-Web-App/README.md similarity index 100% rename from 3-Web-App/1-Web-App/README.md rename to Example project - Github_pages/3-Web-App/1-Web-App/README.md diff --git a/3-Web-App/1-Web-App/assignment.md b/Example project - Github_pages/3-Web-App/1-Web-App/assignment.md similarity index 100% rename from 3-Web-App/1-Web-App/assignment.md rename to Example project - Github_pages/3-Web-App/1-Web-App/assignment.md diff --git a/3-Web-App/1-Web-App/data/ufos.csv b/Example project - Github_pages/3-Web-App/1-Web-App/data/ufos.csv similarity index 100% rename from 3-Web-App/1-Web-App/data/ufos.csv rename to Example project - Github_pages/3-Web-App/1-Web-App/data/ufos.csv diff --git a/3-Web-App/1-Web-App/images/lobe.png b/Example project - Github_pages/3-Web-App/1-Web-App/images/lobe.png similarity index 100% rename from 3-Web-App/1-Web-App/images/lobe.png rename to Example project - Github_pages/3-Web-App/1-Web-App/images/lobe.png diff --git a/3-Web-App/1-Web-App/notebook.ipynb b/Example project - Github_pages/3-Web-App/1-Web-App/notebook.ipynb similarity index 100% rename from 3-Web-App/1-Web-App/notebook.ipynb rename to Example project - Github_pages/3-Web-App/1-Web-App/notebook.ipynb diff --git a/3-Web-App/1-Web-App/solution/notebook.ipynb b/Example project - Github_pages/3-Web-App/1-Web-App/solution/notebook.ipynb similarity index 100% rename from 3-Web-App/1-Web-App/solution/notebook.ipynb rename to Example project - Github_pages/3-Web-App/1-Web-App/solution/notebook.ipynb diff --git a/3-Web-App/1-Web-App/solution/ufo-model.pkl b/Example project - Github_pages/3-Web-App/1-Web-App/solution/ufo-model.pkl similarity index 100% rename from 3-Web-App/1-Web-App/solution/ufo-model.pkl rename to Example project - Github_pages/3-Web-App/1-Web-App/solution/ufo-model.pkl diff --git a/3-Web-App/1-Web-App/solution/web-app/app.py b/Example project - Github_pages/3-Web-App/1-Web-App/solution/web-app/app.py similarity index 100% rename from 3-Web-App/1-Web-App/solution/web-app/app.py rename to Example project - Github_pages/3-Web-App/1-Web-App/solution/web-app/app.py diff --git a/3-Web-App/1-Web-App/solution/web-app/requirements.txt b/Example project - Github_pages/3-Web-App/1-Web-App/solution/web-app/requirements.txt similarity index 100% rename from 3-Web-App/1-Web-App/solution/web-app/requirements.txt rename to Example project - Github_pages/3-Web-App/1-Web-App/solution/web-app/requirements.txt diff --git a/3-Web-App/1-Web-App/solution/web-app/static/css/styles.css b/Example project - Github_pages/3-Web-App/1-Web-App/solution/web-app/static/css/styles.css similarity index 100% rename from 3-Web-App/1-Web-App/solution/web-app/static/css/styles.css rename to Example project - Github_pages/3-Web-App/1-Web-App/solution/web-app/static/css/styles.css diff --git a/3-Web-App/1-Web-App/solution/web-app/templates/index.html b/Example project - Github_pages/3-Web-App/1-Web-App/solution/web-app/templates/index.html similarity index 100% rename from 3-Web-App/1-Web-App/solution/web-app/templates/index.html rename to Example project - Github_pages/3-Web-App/1-Web-App/solution/web-app/templates/index.html diff --git a/3-Web-App/1-Web-App/translations/README.es.md b/Example project - Github_pages/3-Web-App/1-Web-App/translations/README.es.md similarity index 100% rename from 3-Web-App/1-Web-App/translations/README.es.md rename to Example project - Github_pages/3-Web-App/1-Web-App/translations/README.es.md diff --git a/3-Web-App/1-Web-App/translations/README.it.md b/Example project - Github_pages/3-Web-App/1-Web-App/translations/README.it.md similarity index 100% rename from 3-Web-App/1-Web-App/translations/README.it.md rename to Example project - Github_pages/3-Web-App/1-Web-App/translations/README.it.md diff --git a/3-Web-App/1-Web-App/translations/README.ja.md b/Example project - Github_pages/3-Web-App/1-Web-App/translations/README.ja.md similarity index 100% rename from 3-Web-App/1-Web-App/translations/README.ja.md rename to Example project - Github_pages/3-Web-App/1-Web-App/translations/README.ja.md diff --git a/3-Web-App/1-Web-App/translations/README.ko.md b/Example project - Github_pages/3-Web-App/1-Web-App/translations/README.ko.md similarity index 100% rename from 3-Web-App/1-Web-App/translations/README.ko.md rename to Example project - Github_pages/3-Web-App/1-Web-App/translations/README.ko.md diff --git a/3-Web-App/1-Web-App/translations/README.pt-br.md b/Example project - Github_pages/3-Web-App/1-Web-App/translations/README.pt-br.md similarity index 100% rename from 3-Web-App/1-Web-App/translations/README.pt-br.md rename to Example project - Github_pages/3-Web-App/1-Web-App/translations/README.pt-br.md diff --git a/3-Web-App/1-Web-App/translations/README.pt.md b/Example project - Github_pages/3-Web-App/1-Web-App/translations/README.pt.md similarity index 100% rename from 3-Web-App/1-Web-App/translations/README.pt.md rename to Example project - Github_pages/3-Web-App/1-Web-App/translations/README.pt.md diff --git a/3-Web-App/1-Web-App/translations/README.zh-cn.md b/Example project - Github_pages/3-Web-App/1-Web-App/translations/README.zh-cn.md similarity index 100% rename from 3-Web-App/1-Web-App/translations/README.zh-cn.md rename to Example project - Github_pages/3-Web-App/1-Web-App/translations/README.zh-cn.md diff --git a/3-Web-App/1-Web-App/translations/README.zh-tw.md b/Example project - Github_pages/3-Web-App/1-Web-App/translations/README.zh-tw.md similarity index 100% rename from 3-Web-App/1-Web-App/translations/README.zh-tw.md rename to Example project - Github_pages/3-Web-App/1-Web-App/translations/README.zh-tw.md diff --git a/3-Web-App/1-Web-App/translations/assignment.es.md b/Example project - Github_pages/3-Web-App/1-Web-App/translations/assignment.es.md similarity index 100% rename from 3-Web-App/1-Web-App/translations/assignment.es.md rename to Example project - Github_pages/3-Web-App/1-Web-App/translations/assignment.es.md diff --git a/3-Web-App/1-Web-App/translations/assignment.it.md b/Example project - Github_pages/3-Web-App/1-Web-App/translations/assignment.it.md similarity index 100% rename from 3-Web-App/1-Web-App/translations/assignment.it.md rename to Example project - Github_pages/3-Web-App/1-Web-App/translations/assignment.it.md diff --git a/3-Web-App/1-Web-App/translations/assignment.ja.md b/Example project - Github_pages/3-Web-App/1-Web-App/translations/assignment.ja.md similarity index 100% rename from 3-Web-App/1-Web-App/translations/assignment.ja.md rename to Example project - Github_pages/3-Web-App/1-Web-App/translations/assignment.ja.md diff --git a/3-Web-App/1-Web-App/translations/assignment.ko.md b/Example project - Github_pages/3-Web-App/1-Web-App/translations/assignment.ko.md similarity index 100% rename from 3-Web-App/1-Web-App/translations/assignment.ko.md rename to Example project - Github_pages/3-Web-App/1-Web-App/translations/assignment.ko.md diff --git a/3-Web-App/1-Web-App/translations/assignment.pt-br.md b/Example project - Github_pages/3-Web-App/1-Web-App/translations/assignment.pt-br.md similarity index 100% rename from 3-Web-App/1-Web-App/translations/assignment.pt-br.md rename to Example project - Github_pages/3-Web-App/1-Web-App/translations/assignment.pt-br.md diff --git a/3-Web-App/1-Web-App/translations/assignment.pt.md b/Example project - Github_pages/3-Web-App/1-Web-App/translations/assignment.pt.md similarity index 100% rename from 3-Web-App/1-Web-App/translations/assignment.pt.md rename to Example project - Github_pages/3-Web-App/1-Web-App/translations/assignment.pt.md diff --git a/3-Web-App/1-Web-App/translations/assignment.zh-cn.md b/Example project - Github_pages/3-Web-App/1-Web-App/translations/assignment.zh-cn.md similarity index 100% rename from 3-Web-App/1-Web-App/translations/assignment.zh-cn.md rename to Example project - Github_pages/3-Web-App/1-Web-App/translations/assignment.zh-cn.md diff --git a/3-Web-App/1-Web-App/translations/assignment.zh-tw.md b/Example project - Github_pages/3-Web-App/1-Web-App/translations/assignment.zh-tw.md similarity index 100% rename from 3-Web-App/1-Web-App/translations/assignment.zh-tw.md rename to Example project - Github_pages/3-Web-App/1-Web-App/translations/assignment.zh-tw.md diff --git a/3-Web-App/README.md b/Example project - Github_pages/3-Web-App/README.md similarity index 100% rename from 3-Web-App/README.md rename to Example project - Github_pages/3-Web-App/README.md diff --git a/3-Web-App/images/ufo.jpg b/Example project - Github_pages/3-Web-App/images/ufo.jpg similarity index 100% rename from 3-Web-App/images/ufo.jpg rename to Example project - Github_pages/3-Web-App/images/ufo.jpg diff --git a/3-Web-App/translations/README.es.md b/Example project - Github_pages/3-Web-App/translations/README.es.md similarity index 100% rename from 3-Web-App/translations/README.es.md rename to Example project - Github_pages/3-Web-App/translations/README.es.md diff --git a/3-Web-App/translations/README.hi.md b/Example project - Github_pages/3-Web-App/translations/README.hi.md similarity index 100% rename from 3-Web-App/translations/README.hi.md rename to Example project - Github_pages/3-Web-App/translations/README.hi.md diff --git a/3-Web-App/translations/README.it.md b/Example project - Github_pages/3-Web-App/translations/README.it.md similarity index 100% rename from 3-Web-App/translations/README.it.md rename to Example project - Github_pages/3-Web-App/translations/README.it.md diff --git a/3-Web-App/translations/README.ja.md b/Example project - Github_pages/3-Web-App/translations/README.ja.md similarity index 100% rename from 3-Web-App/translations/README.ja.md rename to Example project - Github_pages/3-Web-App/translations/README.ja.md diff --git a/3-Web-App/translations/README.ko.md b/Example project - Github_pages/3-Web-App/translations/README.ko.md similarity index 100% rename from 3-Web-App/translations/README.ko.md rename to Example project - Github_pages/3-Web-App/translations/README.ko.md diff --git a/3-Web-App/translations/README.pt-br.md b/Example project - Github_pages/3-Web-App/translations/README.pt-br.md similarity index 100% rename from 3-Web-App/translations/README.pt-br.md rename to Example project - Github_pages/3-Web-App/translations/README.pt-br.md diff --git a/3-Web-App/translations/README.pt.md b/Example project - Github_pages/3-Web-App/translations/README.pt.md similarity index 100% rename from 3-Web-App/translations/README.pt.md rename to Example project - Github_pages/3-Web-App/translations/README.pt.md diff --git a/3-Web-App/translations/README.ru.md b/Example project - Github_pages/3-Web-App/translations/README.ru.md similarity index 100% rename from 3-Web-App/translations/README.ru.md rename to Example project - Github_pages/3-Web-App/translations/README.ru.md diff --git a/3-Web-App/translations/README.zh-cn.md b/Example project - Github_pages/3-Web-App/translations/README.zh-cn.md similarity index 100% rename from 3-Web-App/translations/README.zh-cn.md rename to Example project - Github_pages/3-Web-App/translations/README.zh-cn.md diff --git a/3-Web-App/translations/README.zh-tw.md b/Example project - Github_pages/3-Web-App/translations/README.zh-tw.md similarity index 100% rename from 3-Web-App/translations/README.zh-tw.md rename to Example project - Github_pages/3-Web-App/translations/README.zh-tw.md diff --git a/4-Classification/1-Introduction/README.md b/Example project - Github_pages/4-Classification/1-Introduction/README.md similarity index 100% rename from 4-Classification/1-Introduction/README.md rename to Example project - Github_pages/4-Classification/1-Introduction/README.md diff --git a/4-Classification/1-Introduction/assignment.md b/Example project - Github_pages/4-Classification/1-Introduction/assignment.md similarity index 100% rename from 4-Classification/1-Introduction/assignment.md rename to Example project - Github_pages/4-Classification/1-Introduction/assignment.md diff --git a/4-Classification/1-Introduction/images/binary-multiclass.png b/Example project - Github_pages/4-Classification/1-Introduction/images/binary-multiclass.png similarity index 100% rename from 4-Classification/1-Introduction/images/binary-multiclass.png rename to Example project - Github_pages/4-Classification/1-Introduction/images/binary-multiclass.png diff --git a/4-Classification/1-Introduction/images/chinese.png b/Example project - Github_pages/4-Classification/1-Introduction/images/chinese.png similarity index 100% rename from 4-Classification/1-Introduction/images/chinese.png rename to Example project - Github_pages/4-Classification/1-Introduction/images/chinese.png diff --git a/4-Classification/1-Introduction/images/cuisine-dist.png b/Example project - Github_pages/4-Classification/1-Introduction/images/cuisine-dist.png similarity index 100% rename from 4-Classification/1-Introduction/images/cuisine-dist.png rename to Example project - Github_pages/4-Classification/1-Introduction/images/cuisine-dist.png diff --git a/4-Classification/1-Introduction/images/dplyr_filter.jpg b/Example project - Github_pages/4-Classification/1-Introduction/images/dplyr_filter.jpg similarity index 100% rename from 4-Classification/1-Introduction/images/dplyr_filter.jpg rename to Example project - Github_pages/4-Classification/1-Introduction/images/dplyr_filter.jpg diff --git a/4-Classification/1-Introduction/images/indian.png b/Example project - Github_pages/4-Classification/1-Introduction/images/indian.png similarity index 100% rename from 4-Classification/1-Introduction/images/indian.png rename to Example project - Github_pages/4-Classification/1-Introduction/images/indian.png diff --git a/4-Classification/1-Introduction/images/japanese.png b/Example project - Github_pages/4-Classification/1-Introduction/images/japanese.png similarity index 100% rename from 4-Classification/1-Introduction/images/japanese.png rename to Example project - Github_pages/4-Classification/1-Introduction/images/japanese.png diff --git a/4-Classification/1-Introduction/images/korean.png b/Example project - Github_pages/4-Classification/1-Introduction/images/korean.png similarity index 100% rename from 4-Classification/1-Introduction/images/korean.png rename to Example project - Github_pages/4-Classification/1-Introduction/images/korean.png diff --git a/4-Classification/1-Introduction/images/pinch.png b/Example project - Github_pages/4-Classification/1-Introduction/images/pinch.png similarity index 100% rename from 4-Classification/1-Introduction/images/pinch.png rename to Example project - Github_pages/4-Classification/1-Introduction/images/pinch.png diff --git a/4-Classification/1-Introduction/images/r_learners_sm.jpeg b/Example project - Github_pages/4-Classification/1-Introduction/images/r_learners_sm.jpeg similarity index 100% rename from 4-Classification/1-Introduction/images/r_learners_sm.jpeg rename to Example project - Github_pages/4-Classification/1-Introduction/images/r_learners_sm.jpeg diff --git a/4-Classification/1-Introduction/images/recipes.png b/Example project - Github_pages/4-Classification/1-Introduction/images/recipes.png similarity index 100% rename from 4-Classification/1-Introduction/images/recipes.png rename to Example project - Github_pages/4-Classification/1-Introduction/images/recipes.png diff --git a/4-Classification/1-Introduction/images/thai.png b/Example project - Github_pages/4-Classification/1-Introduction/images/thai.png similarity index 100% rename from 4-Classification/1-Introduction/images/thai.png rename to Example project - Github_pages/4-Classification/1-Introduction/images/thai.png diff --git a/4-Classification/1-Introduction/notebook.ipynb b/Example project - Github_pages/4-Classification/1-Introduction/notebook.ipynb similarity index 100% rename from 4-Classification/1-Introduction/notebook.ipynb rename to Example project - Github_pages/4-Classification/1-Introduction/notebook.ipynb diff --git a/4-Classification/1-Introduction/solution/Julia/README.md b/Example project - Github_pages/4-Classification/1-Introduction/solution/Julia/README.md similarity index 100% rename from 4-Classification/1-Introduction/solution/Julia/README.md rename to Example project - Github_pages/4-Classification/1-Introduction/solution/Julia/README.md diff --git a/4-Classification/1-Introduction/solution/R/lesson_10-R.ipynb b/Example project - Github_pages/4-Classification/1-Introduction/solution/R/lesson_10-R.ipynb similarity index 100% rename from 4-Classification/1-Introduction/solution/R/lesson_10-R.ipynb rename to Example project - Github_pages/4-Classification/1-Introduction/solution/R/lesson_10-R.ipynb diff --git a/4-Classification/1-Introduction/solution/R/lesson_10.Rmd b/Example project - Github_pages/4-Classification/1-Introduction/solution/R/lesson_10.Rmd similarity index 100% rename from 4-Classification/1-Introduction/solution/R/lesson_10.Rmd rename to Example project - Github_pages/4-Classification/1-Introduction/solution/R/lesson_10.Rmd diff --git a/4-Classification/1-Introduction/solution/R/lesson_10.html b/Example project - Github_pages/4-Classification/1-Introduction/solution/R/lesson_10.html similarity index 100% rename from 4-Classification/1-Introduction/solution/R/lesson_10.html rename to Example project - Github_pages/4-Classification/1-Introduction/solution/R/lesson_10.html diff --git a/4-Classification/1-Introduction/solution/notebook.ipynb b/Example project - Github_pages/4-Classification/1-Introduction/solution/notebook.ipynb similarity index 100% rename from 4-Classification/1-Introduction/solution/notebook.ipynb rename to Example project - Github_pages/4-Classification/1-Introduction/solution/notebook.ipynb diff --git a/4-Classification/1-Introduction/translations/README.es.md b/Example project - Github_pages/4-Classification/1-Introduction/translations/README.es.md similarity index 100% rename from 4-Classification/1-Introduction/translations/README.es.md rename to Example project - Github_pages/4-Classification/1-Introduction/translations/README.es.md diff --git a/4-Classification/1-Introduction/translations/README.it.md b/Example project - Github_pages/4-Classification/1-Introduction/translations/README.it.md similarity index 100% rename from 4-Classification/1-Introduction/translations/README.it.md rename to Example project - Github_pages/4-Classification/1-Introduction/translations/README.it.md diff --git a/4-Classification/1-Introduction/translations/README.ko.md b/Example project - Github_pages/4-Classification/1-Introduction/translations/README.ko.md similarity index 100% rename from 4-Classification/1-Introduction/translations/README.ko.md rename to Example project - Github_pages/4-Classification/1-Introduction/translations/README.ko.md diff --git a/4-Classification/1-Introduction/translations/README.pt-br.md b/Example project - Github_pages/4-Classification/1-Introduction/translations/README.pt-br.md similarity index 100% rename from 4-Classification/1-Introduction/translations/README.pt-br.md rename to Example project - Github_pages/4-Classification/1-Introduction/translations/README.pt-br.md diff --git a/4-Classification/1-Introduction/translations/README.tr.md b/Example project - Github_pages/4-Classification/1-Introduction/translations/README.tr.md similarity index 100% rename from 4-Classification/1-Introduction/translations/README.tr.md rename to Example project - Github_pages/4-Classification/1-Introduction/translations/README.tr.md diff --git a/4-Classification/1-Introduction/translations/README.zh-cn.md b/Example project - Github_pages/4-Classification/1-Introduction/translations/README.zh-cn.md similarity index 100% rename from 4-Classification/1-Introduction/translations/README.zh-cn.md rename to Example project - Github_pages/4-Classification/1-Introduction/translations/README.zh-cn.md diff --git a/4-Classification/1-Introduction/translations/assignment.es.md b/Example project - Github_pages/4-Classification/1-Introduction/translations/assignment.es.md similarity index 100% rename from 4-Classification/1-Introduction/translations/assignment.es.md rename to Example project - Github_pages/4-Classification/1-Introduction/translations/assignment.es.md diff --git a/4-Classification/1-Introduction/translations/assignment.it.md b/Example project - Github_pages/4-Classification/1-Introduction/translations/assignment.it.md similarity index 100% rename from 4-Classification/1-Introduction/translations/assignment.it.md rename to Example project - Github_pages/4-Classification/1-Introduction/translations/assignment.it.md diff --git a/4-Classification/1-Introduction/translations/assignment.ko.md b/Example project - Github_pages/4-Classification/1-Introduction/translations/assignment.ko.md similarity index 100% rename from 4-Classification/1-Introduction/translations/assignment.ko.md rename to Example project - Github_pages/4-Classification/1-Introduction/translations/assignment.ko.md diff --git a/4-Classification/1-Introduction/translations/assignment.pt-br.md b/Example project - Github_pages/4-Classification/1-Introduction/translations/assignment.pt-br.md similarity index 100% rename from 4-Classification/1-Introduction/translations/assignment.pt-br.md rename to Example project - Github_pages/4-Classification/1-Introduction/translations/assignment.pt-br.md diff --git a/4-Classification/1-Introduction/translations/assignment.tr.md b/Example project - Github_pages/4-Classification/1-Introduction/translations/assignment.tr.md similarity index 100% rename from 4-Classification/1-Introduction/translations/assignment.tr.md rename to Example project - Github_pages/4-Classification/1-Introduction/translations/assignment.tr.md diff --git a/4-Classification/1-Introduction/translations/assignment.zh-cn.md b/Example project - Github_pages/4-Classification/1-Introduction/translations/assignment.zh-cn.md similarity index 100% rename from 4-Classification/1-Introduction/translations/assignment.zh-cn.md rename to Example project - Github_pages/4-Classification/1-Introduction/translations/assignment.zh-cn.md diff --git a/4-Classification/2-Classifiers-1/README.md b/Example project - Github_pages/4-Classification/2-Classifiers-1/README.md similarity index 100% rename from 4-Classification/2-Classifiers-1/README.md rename to Example project - Github_pages/4-Classification/2-Classifiers-1/README.md diff --git a/4-Classification/2-Classifiers-1/assignment.md b/Example project - Github_pages/4-Classification/2-Classifiers-1/assignment.md similarity index 100% rename from 4-Classification/2-Classifiers-1/assignment.md rename to Example project - Github_pages/4-Classification/2-Classifiers-1/assignment.md diff --git a/4-Classification/2-Classifiers-1/images/cheatsheet.png b/Example project - Github_pages/4-Classification/2-Classifiers-1/images/cheatsheet.png similarity index 100% rename from 4-Classification/2-Classifiers-1/images/cheatsheet.png rename to Example project - Github_pages/4-Classification/2-Classifiers-1/images/cheatsheet.png diff --git a/4-Classification/2-Classifiers-1/images/comparison.png b/Example project - Github_pages/4-Classification/2-Classifiers-1/images/comparison.png similarity index 100% rename from 4-Classification/2-Classifiers-1/images/comparison.png rename to Example project - Github_pages/4-Classification/2-Classifiers-1/images/comparison.png diff --git a/4-Classification/2-Classifiers-1/images/parsnip.jpg b/Example project - Github_pages/4-Classification/2-Classifiers-1/images/parsnip.jpg similarity index 100% rename from 4-Classification/2-Classifiers-1/images/parsnip.jpg rename to Example project - Github_pages/4-Classification/2-Classifiers-1/images/parsnip.jpg diff --git a/4-Classification/2-Classifiers-1/images/solvers.png b/Example project - Github_pages/4-Classification/2-Classifiers-1/images/solvers.png similarity index 100% rename from 4-Classification/2-Classifiers-1/images/solvers.png rename to Example project - Github_pages/4-Classification/2-Classifiers-1/images/solvers.png diff --git a/4-Classification/2-Classifiers-1/notebook.ipynb b/Example project - Github_pages/4-Classification/2-Classifiers-1/notebook.ipynb similarity index 100% rename from 4-Classification/2-Classifiers-1/notebook.ipynb rename to Example project - Github_pages/4-Classification/2-Classifiers-1/notebook.ipynb diff --git a/4-Classification/2-Classifiers-1/solution/Julia/README.md b/Example project - Github_pages/4-Classification/2-Classifiers-1/solution/Julia/README.md similarity index 100% rename from 4-Classification/2-Classifiers-1/solution/Julia/README.md rename to Example project - Github_pages/4-Classification/2-Classifiers-1/solution/Julia/README.md diff --git a/4-Classification/2-Classifiers-1/solution/R/lesson_11-R.ipynb b/Example project - Github_pages/4-Classification/2-Classifiers-1/solution/R/lesson_11-R.ipynb similarity index 100% rename from 4-Classification/2-Classifiers-1/solution/R/lesson_11-R.ipynb rename to Example project - Github_pages/4-Classification/2-Classifiers-1/solution/R/lesson_11-R.ipynb diff --git a/4-Classification/2-Classifiers-1/solution/R/lesson_11.Rmd b/Example project - Github_pages/4-Classification/2-Classifiers-1/solution/R/lesson_11.Rmd similarity index 100% rename from 4-Classification/2-Classifiers-1/solution/R/lesson_11.Rmd rename to Example project - Github_pages/4-Classification/2-Classifiers-1/solution/R/lesson_11.Rmd diff --git a/4-Classification/2-Classifiers-1/solution/R/lesson_11.html b/Example project - Github_pages/4-Classification/2-Classifiers-1/solution/R/lesson_11.html similarity index 100% rename from 4-Classification/2-Classifiers-1/solution/R/lesson_11.html rename to Example project - Github_pages/4-Classification/2-Classifiers-1/solution/R/lesson_11.html diff --git a/4-Classification/2-Classifiers-1/solution/notebook.ipynb b/Example project - Github_pages/4-Classification/2-Classifiers-1/solution/notebook.ipynb similarity index 100% rename from 4-Classification/2-Classifiers-1/solution/notebook.ipynb rename to Example project - Github_pages/4-Classification/2-Classifiers-1/solution/notebook.ipynb diff --git a/4-Classification/2-Classifiers-1/translations/README.es.md b/Example project - Github_pages/4-Classification/2-Classifiers-1/translations/README.es.md similarity index 100% rename from 4-Classification/2-Classifiers-1/translations/README.es.md rename to Example project - Github_pages/4-Classification/2-Classifiers-1/translations/README.es.md diff --git a/4-Classification/2-Classifiers-1/translations/README.it.md b/Example project - Github_pages/4-Classification/2-Classifiers-1/translations/README.it.md similarity index 100% rename from 4-Classification/2-Classifiers-1/translations/README.it.md rename to Example project - Github_pages/4-Classification/2-Classifiers-1/translations/README.it.md diff --git a/4-Classification/2-Classifiers-1/translations/README.ko.md b/Example project - Github_pages/4-Classification/2-Classifiers-1/translations/README.ko.md similarity index 100% rename from 4-Classification/2-Classifiers-1/translations/README.ko.md rename to Example project - Github_pages/4-Classification/2-Classifiers-1/translations/README.ko.md diff --git a/4-Classification/2-Classifiers-1/translations/README.pt-br.md b/Example project - Github_pages/4-Classification/2-Classifiers-1/translations/README.pt-br.md similarity index 100% rename from 4-Classification/2-Classifiers-1/translations/README.pt-br.md rename to Example project - Github_pages/4-Classification/2-Classifiers-1/translations/README.pt-br.md diff --git a/4-Classification/2-Classifiers-1/translations/README.tr.md b/Example project - Github_pages/4-Classification/2-Classifiers-1/translations/README.tr.md similarity index 100% rename from 4-Classification/2-Classifiers-1/translations/README.tr.md rename to Example project - Github_pages/4-Classification/2-Classifiers-1/translations/README.tr.md diff --git a/4-Classification/2-Classifiers-1/translations/README.zh-cn.md b/Example project - Github_pages/4-Classification/2-Classifiers-1/translations/README.zh-cn.md similarity index 100% rename from 4-Classification/2-Classifiers-1/translations/README.zh-cn.md rename to Example project - Github_pages/4-Classification/2-Classifiers-1/translations/README.zh-cn.md diff --git a/4-Classification/2-Classifiers-1/translations/assignment.es.md b/Example project - Github_pages/4-Classification/2-Classifiers-1/translations/assignment.es.md similarity index 100% rename from 4-Classification/2-Classifiers-1/translations/assignment.es.md rename to Example project - Github_pages/4-Classification/2-Classifiers-1/translations/assignment.es.md diff --git a/4-Classification/2-Classifiers-1/translations/assignment.it.md b/Example project - Github_pages/4-Classification/2-Classifiers-1/translations/assignment.it.md similarity index 100% rename from 4-Classification/2-Classifiers-1/translations/assignment.it.md rename to Example project - Github_pages/4-Classification/2-Classifiers-1/translations/assignment.it.md diff --git a/4-Classification/2-Classifiers-1/translations/assignment.ko.md b/Example project - Github_pages/4-Classification/2-Classifiers-1/translations/assignment.ko.md similarity index 100% rename from 4-Classification/2-Classifiers-1/translations/assignment.ko.md rename to Example project - Github_pages/4-Classification/2-Classifiers-1/translations/assignment.ko.md diff --git a/4-Classification/2-Classifiers-1/translations/assignment.pt-br.md b/Example project - Github_pages/4-Classification/2-Classifiers-1/translations/assignment.pt-br.md similarity index 100% rename from 4-Classification/2-Classifiers-1/translations/assignment.pt-br.md rename to Example project - Github_pages/4-Classification/2-Classifiers-1/translations/assignment.pt-br.md diff --git a/4-Classification/2-Classifiers-1/translations/assignment.tr.md b/Example project - Github_pages/4-Classification/2-Classifiers-1/translations/assignment.tr.md similarity index 100% rename from 4-Classification/2-Classifiers-1/translations/assignment.tr.md rename to Example project - Github_pages/4-Classification/2-Classifiers-1/translations/assignment.tr.md diff --git a/4-Classification/2-Classifiers-1/translations/assignment.zh-cn.md b/Example project - Github_pages/4-Classification/2-Classifiers-1/translations/assignment.zh-cn.md similarity index 100% rename from 4-Classification/2-Classifiers-1/translations/assignment.zh-cn.md rename to Example project - Github_pages/4-Classification/2-Classifiers-1/translations/assignment.zh-cn.md diff --git a/4-Classification/3-Classifiers-2/README.md b/Example project - Github_pages/4-Classification/3-Classifiers-2/README.md similarity index 100% rename from 4-Classification/3-Classifiers-2/README.md rename to Example project - Github_pages/4-Classification/3-Classifiers-2/README.md diff --git a/4-Classification/3-Classifiers-2/assignment.md b/Example project - Github_pages/4-Classification/3-Classifiers-2/assignment.md similarity index 100% rename from 4-Classification/3-Classifiers-2/assignment.md rename to Example project - Github_pages/4-Classification/3-Classifiers-2/assignment.md diff --git a/4-Classification/3-Classifiers-2/images/map.png b/Example project - Github_pages/4-Classification/3-Classifiers-2/images/map.png similarity index 100% rename from 4-Classification/3-Classifiers-2/images/map.png rename to Example project - Github_pages/4-Classification/3-Classifiers-2/images/map.png diff --git a/4-Classification/3-Classifiers-2/images/r_learners_sm.jpeg b/Example project - Github_pages/4-Classification/3-Classifiers-2/images/r_learners_sm.jpeg similarity index 100% rename from 4-Classification/3-Classifiers-2/images/r_learners_sm.jpeg rename to Example project - Github_pages/4-Classification/3-Classifiers-2/images/r_learners_sm.jpeg diff --git a/4-Classification/3-Classifiers-2/images/svm.png b/Example project - Github_pages/4-Classification/3-Classifiers-2/images/svm.png similarity index 100% rename from 4-Classification/3-Classifiers-2/images/svm.png rename to Example project - Github_pages/4-Classification/3-Classifiers-2/images/svm.png diff --git a/4-Classification/3-Classifiers-2/notebook.ipynb b/Example project - Github_pages/4-Classification/3-Classifiers-2/notebook.ipynb similarity index 100% rename from 4-Classification/3-Classifiers-2/notebook.ipynb rename to Example project - Github_pages/4-Classification/3-Classifiers-2/notebook.ipynb diff --git a/4-Classification/3-Classifiers-2/solution/Julia/README.md b/Example project - Github_pages/4-Classification/3-Classifiers-2/solution/Julia/README.md similarity index 100% rename from 4-Classification/3-Classifiers-2/solution/Julia/README.md rename to Example project - Github_pages/4-Classification/3-Classifiers-2/solution/Julia/README.md diff --git a/4-Classification/3-Classifiers-2/solution/R/lesson_12-R.ipynb b/Example project - Github_pages/4-Classification/3-Classifiers-2/solution/R/lesson_12-R.ipynb similarity index 100% rename from 4-Classification/3-Classifiers-2/solution/R/lesson_12-R.ipynb rename to Example project - Github_pages/4-Classification/3-Classifiers-2/solution/R/lesson_12-R.ipynb diff --git a/4-Classification/3-Classifiers-2/solution/R/lesson_12.Rmd b/Example project - Github_pages/4-Classification/3-Classifiers-2/solution/R/lesson_12.Rmd similarity index 100% rename from 4-Classification/3-Classifiers-2/solution/R/lesson_12.Rmd rename to Example project - Github_pages/4-Classification/3-Classifiers-2/solution/R/lesson_12.Rmd diff --git a/4-Classification/3-Classifiers-2/solution/R/lesson_12.html b/Example project - Github_pages/4-Classification/3-Classifiers-2/solution/R/lesson_12.html similarity index 100% rename from 4-Classification/3-Classifiers-2/solution/R/lesson_12.html rename to Example project - Github_pages/4-Classification/3-Classifiers-2/solution/R/lesson_12.html diff --git a/4-Classification/3-Classifiers-2/solution/notebook.ipynb b/Example project - Github_pages/4-Classification/3-Classifiers-2/solution/notebook.ipynb similarity index 100% rename from 4-Classification/3-Classifiers-2/solution/notebook.ipynb rename to Example project - Github_pages/4-Classification/3-Classifiers-2/solution/notebook.ipynb diff --git a/4-Classification/3-Classifiers-2/translations/README.es.md b/Example project - Github_pages/4-Classification/3-Classifiers-2/translations/README.es.md similarity index 100% rename from 4-Classification/3-Classifiers-2/translations/README.es.md rename to Example project - Github_pages/4-Classification/3-Classifiers-2/translations/README.es.md diff --git a/4-Classification/3-Classifiers-2/translations/README.it.md b/Example project - Github_pages/4-Classification/3-Classifiers-2/translations/README.it.md similarity index 100% rename from 4-Classification/3-Classifiers-2/translations/README.it.md rename to Example project - Github_pages/4-Classification/3-Classifiers-2/translations/README.it.md diff --git a/4-Classification/3-Classifiers-2/translations/README.ko.md b/Example project - Github_pages/4-Classification/3-Classifiers-2/translations/README.ko.md similarity index 100% rename from 4-Classification/3-Classifiers-2/translations/README.ko.md rename to Example project - Github_pages/4-Classification/3-Classifiers-2/translations/README.ko.md diff --git a/4-Classification/3-Classifiers-2/translations/README.pt-br.md b/Example project - Github_pages/4-Classification/3-Classifiers-2/translations/README.pt-br.md similarity index 100% rename from 4-Classification/3-Classifiers-2/translations/README.pt-br.md rename to Example project - Github_pages/4-Classification/3-Classifiers-2/translations/README.pt-br.md diff --git a/4-Classification/3-Classifiers-2/translations/README.tr.md b/Example project - Github_pages/4-Classification/3-Classifiers-2/translations/README.tr.md similarity index 100% rename from 4-Classification/3-Classifiers-2/translations/README.tr.md rename to Example project - Github_pages/4-Classification/3-Classifiers-2/translations/README.tr.md diff --git a/4-Classification/3-Classifiers-2/translations/README.zh-cn.md b/Example project - Github_pages/4-Classification/3-Classifiers-2/translations/README.zh-cn.md similarity index 100% rename from 4-Classification/3-Classifiers-2/translations/README.zh-cn.md rename to Example project - Github_pages/4-Classification/3-Classifiers-2/translations/README.zh-cn.md diff --git a/4-Classification/3-Classifiers-2/translations/assignment.es.md b/Example project - Github_pages/4-Classification/3-Classifiers-2/translations/assignment.es.md similarity index 100% rename from 4-Classification/3-Classifiers-2/translations/assignment.es.md rename to Example project - Github_pages/4-Classification/3-Classifiers-2/translations/assignment.es.md diff --git a/4-Classification/3-Classifiers-2/translations/assignment.it.md b/Example project - Github_pages/4-Classification/3-Classifiers-2/translations/assignment.it.md similarity index 100% rename from 4-Classification/3-Classifiers-2/translations/assignment.it.md rename to Example project - Github_pages/4-Classification/3-Classifiers-2/translations/assignment.it.md diff --git a/4-Classification/3-Classifiers-2/translations/assignment.ko.md b/Example project - Github_pages/4-Classification/3-Classifiers-2/translations/assignment.ko.md similarity index 100% rename from 4-Classification/3-Classifiers-2/translations/assignment.ko.md rename to Example project - Github_pages/4-Classification/3-Classifiers-2/translations/assignment.ko.md diff --git a/4-Classification/3-Classifiers-2/translations/assignment.pt-br.md b/Example project - Github_pages/4-Classification/3-Classifiers-2/translations/assignment.pt-br.md similarity index 100% rename from 4-Classification/3-Classifiers-2/translations/assignment.pt-br.md rename to Example project - Github_pages/4-Classification/3-Classifiers-2/translations/assignment.pt-br.md diff --git a/4-Classification/3-Classifiers-2/translations/assignment.tr.md b/Example project - Github_pages/4-Classification/3-Classifiers-2/translations/assignment.tr.md similarity index 100% rename from 4-Classification/3-Classifiers-2/translations/assignment.tr.md rename to Example project - Github_pages/4-Classification/3-Classifiers-2/translations/assignment.tr.md diff --git a/4-Classification/3-Classifiers-2/translations/assignment.zh-cn.md b/Example project - Github_pages/4-Classification/3-Classifiers-2/translations/assignment.zh-cn.md similarity index 100% rename from 4-Classification/3-Classifiers-2/translations/assignment.zh-cn.md rename to Example project - Github_pages/4-Classification/3-Classifiers-2/translations/assignment.zh-cn.md diff --git a/4-Classification/4-Applied/README.md b/Example project - Github_pages/4-Classification/4-Applied/README.md similarity index 100% rename from 4-Classification/4-Applied/README.md rename to Example project - Github_pages/4-Classification/4-Applied/README.md diff --git a/4-Classification/4-Applied/assignment.md b/Example project - Github_pages/4-Classification/4-Applied/assignment.md similarity index 100% rename from 4-Classification/4-Applied/assignment.md rename to Example project - Github_pages/4-Classification/4-Applied/assignment.md diff --git a/4-Classification/4-Applied/images/netron.png b/Example project - Github_pages/4-Classification/4-Applied/images/netron.png similarity index 100% rename from 4-Classification/4-Applied/images/netron.png rename to Example project - Github_pages/4-Classification/4-Applied/images/netron.png diff --git a/4-Classification/4-Applied/images/web-app.png b/Example project - Github_pages/4-Classification/4-Applied/images/web-app.png similarity index 100% rename from 4-Classification/4-Applied/images/web-app.png rename to Example project - Github_pages/4-Classification/4-Applied/images/web-app.png diff --git a/4-Classification/4-Applied/notebook.ipynb b/Example project - Github_pages/4-Classification/4-Applied/notebook.ipynb similarity index 100% rename from 4-Classification/4-Applied/notebook.ipynb rename to Example project - Github_pages/4-Classification/4-Applied/notebook.ipynb diff --git a/4-Classification/4-Applied/solution/index.html b/Example project - Github_pages/4-Classification/4-Applied/solution/index.html similarity index 100% rename from 4-Classification/4-Applied/solution/index.html rename to Example project - Github_pages/4-Classification/4-Applied/solution/index.html diff --git a/4-Classification/4-Applied/solution/model.onnx b/Example project - Github_pages/4-Classification/4-Applied/solution/model.onnx similarity index 100% rename from 4-Classification/4-Applied/solution/model.onnx rename to Example project - Github_pages/4-Classification/4-Applied/solution/model.onnx diff --git a/4-Classification/4-Applied/solution/notebook.ipynb b/Example project - Github_pages/4-Classification/4-Applied/solution/notebook.ipynb similarity index 100% rename from 4-Classification/4-Applied/solution/notebook.ipynb rename to Example project - Github_pages/4-Classification/4-Applied/solution/notebook.ipynb diff --git a/4-Classification/4-Applied/translations/README.es.md b/Example project - Github_pages/4-Classification/4-Applied/translations/README.es.md similarity index 100% rename from 4-Classification/4-Applied/translations/README.es.md rename to Example project - Github_pages/4-Classification/4-Applied/translations/README.es.md diff --git a/4-Classification/4-Applied/translations/README.it.md b/Example project - Github_pages/4-Classification/4-Applied/translations/README.it.md similarity index 100% rename from 4-Classification/4-Applied/translations/README.it.md rename to Example project - Github_pages/4-Classification/4-Applied/translations/README.it.md diff --git a/4-Classification/4-Applied/translations/README.ko.md b/Example project - Github_pages/4-Classification/4-Applied/translations/README.ko.md similarity index 100% rename from 4-Classification/4-Applied/translations/README.ko.md rename to Example project - Github_pages/4-Classification/4-Applied/translations/README.ko.md diff --git a/4-Classification/4-Applied/translations/README.pt-br.md b/Example project - Github_pages/4-Classification/4-Applied/translations/README.pt-br.md similarity index 100% rename from 4-Classification/4-Applied/translations/README.pt-br.md rename to Example project - Github_pages/4-Classification/4-Applied/translations/README.pt-br.md diff --git a/4-Classification/4-Applied/translations/README.tr.md b/Example project - Github_pages/4-Classification/4-Applied/translations/README.tr.md similarity index 100% rename from 4-Classification/4-Applied/translations/README.tr.md rename to Example project - Github_pages/4-Classification/4-Applied/translations/README.tr.md diff --git a/4-Classification/4-Applied/translations/README.zh-CN.md b/Example project - Github_pages/4-Classification/4-Applied/translations/README.zh-CN.md similarity index 100% rename from 4-Classification/4-Applied/translations/README.zh-CN.md rename to Example project - Github_pages/4-Classification/4-Applied/translations/README.zh-CN.md diff --git a/4-Classification/4-Applied/translations/assignment.es.md b/Example project - Github_pages/4-Classification/4-Applied/translations/assignment.es.md similarity index 100% rename from 4-Classification/4-Applied/translations/assignment.es.md rename to Example project - Github_pages/4-Classification/4-Applied/translations/assignment.es.md diff --git a/4-Classification/4-Applied/translations/assignment.it.md b/Example project - Github_pages/4-Classification/4-Applied/translations/assignment.it.md similarity index 100% rename from 4-Classification/4-Applied/translations/assignment.it.md rename to Example project - Github_pages/4-Classification/4-Applied/translations/assignment.it.md diff --git a/4-Classification/4-Applied/translations/assignment.ko.md b/Example project - Github_pages/4-Classification/4-Applied/translations/assignment.ko.md similarity index 100% rename from 4-Classification/4-Applied/translations/assignment.ko.md rename to Example project - Github_pages/4-Classification/4-Applied/translations/assignment.ko.md diff --git a/4-Classification/4-Applied/translations/assignment.pt-br.md b/Example project - Github_pages/4-Classification/4-Applied/translations/assignment.pt-br.md similarity index 100% rename from 4-Classification/4-Applied/translations/assignment.pt-br.md rename to Example project - Github_pages/4-Classification/4-Applied/translations/assignment.pt-br.md diff --git a/4-Classification/4-Applied/translations/assignment.tr.md b/Example project - Github_pages/4-Classification/4-Applied/translations/assignment.tr.md similarity index 100% rename from 4-Classification/4-Applied/translations/assignment.tr.md rename to Example project - Github_pages/4-Classification/4-Applied/translations/assignment.tr.md diff --git a/4-Classification/4-Applied/translations/assignment.zh-CN.md b/Example project - Github_pages/4-Classification/4-Applied/translations/assignment.zh-CN.md similarity index 100% rename from 4-Classification/4-Applied/translations/assignment.zh-CN.md rename to Example project - Github_pages/4-Classification/4-Applied/translations/assignment.zh-CN.md diff --git a/4-Classification/README.md b/Example project - Github_pages/4-Classification/README.md similarity index 100% rename from 4-Classification/README.md rename to Example project - Github_pages/4-Classification/README.md diff --git a/4-Classification/data/cleaned_cuisines.csv b/Example project - Github_pages/4-Classification/data/cleaned_cuisines.csv similarity index 100% rename from 4-Classification/data/cleaned_cuisines.csv rename to Example project - Github_pages/4-Classification/data/cleaned_cuisines.csv diff --git a/4-Classification/data/cleaned_cuisines_R.csv b/Example project - Github_pages/4-Classification/data/cleaned_cuisines_R.csv similarity index 100% rename from 4-Classification/data/cleaned_cuisines_R.csv rename to Example project - Github_pages/4-Classification/data/cleaned_cuisines_R.csv diff --git a/4-Classification/data/cuisines.csv b/Example project - Github_pages/4-Classification/data/cuisines.csv similarity index 100% rename from 4-Classification/data/cuisines.csv rename to Example project - Github_pages/4-Classification/data/cuisines.csv diff --git a/4-Classification/data/ingredient_indexes.csv b/Example project - Github_pages/4-Classification/data/ingredient_indexes.csv similarity index 100% rename from 4-Classification/data/ingredient_indexes.csv rename to Example project - Github_pages/4-Classification/data/ingredient_indexes.csv diff --git a/4-Classification/images/thai-food.jpg b/Example project - Github_pages/4-Classification/images/thai-food.jpg similarity index 100% rename from 4-Classification/images/thai-food.jpg rename to Example project - Github_pages/4-Classification/images/thai-food.jpg diff --git a/4-Classification/translations/README.es.md b/Example project - Github_pages/4-Classification/translations/README.es.md similarity index 100% rename from 4-Classification/translations/README.es.md rename to Example project - Github_pages/4-Classification/translations/README.es.md diff --git a/4-Classification/translations/README.hi.md b/Example project - Github_pages/4-Classification/translations/README.hi.md similarity index 100% rename from 4-Classification/translations/README.hi.md rename to Example project - Github_pages/4-Classification/translations/README.hi.md diff --git a/4-Classification/translations/README.it.md b/Example project - Github_pages/4-Classification/translations/README.it.md similarity index 100% rename from 4-Classification/translations/README.it.md rename to Example project - Github_pages/4-Classification/translations/README.it.md diff --git a/4-Classification/translations/README.ko.md b/Example project - Github_pages/4-Classification/translations/README.ko.md similarity index 100% rename from 4-Classification/translations/README.ko.md rename to Example project - Github_pages/4-Classification/translations/README.ko.md diff --git a/4-Classification/translations/README.pt-br.md b/Example project - Github_pages/4-Classification/translations/README.pt-br.md similarity index 100% rename from 4-Classification/translations/README.pt-br.md rename to Example project - Github_pages/4-Classification/translations/README.pt-br.md diff --git a/4-Classification/translations/README.ru.md b/Example project - Github_pages/4-Classification/translations/README.ru.md similarity index 100% rename from 4-Classification/translations/README.ru.md rename to Example project - Github_pages/4-Classification/translations/README.ru.md diff --git a/4-Classification/translations/README.tr.md b/Example project - Github_pages/4-Classification/translations/README.tr.md similarity index 100% rename from 4-Classification/translations/README.tr.md rename to Example project - Github_pages/4-Classification/translations/README.tr.md diff --git a/4-Classification/translations/README.zh-cn.md b/Example project - Github_pages/4-Classification/translations/README.zh-cn.md similarity index 100% rename from 4-Classification/translations/README.zh-cn.md rename to Example project - Github_pages/4-Classification/translations/README.zh-cn.md diff --git a/5-Clustering/1-Visualize/README.md b/Example project - Github_pages/5-Clustering/1-Visualize/README.md similarity index 100% rename from 5-Clustering/1-Visualize/README.md rename to Example project - Github_pages/5-Clustering/1-Visualize/README.md diff --git a/5-Clustering/1-Visualize/assignment.md b/Example project - Github_pages/5-Clustering/1-Visualize/assignment.md similarity index 100% rename from 5-Clustering/1-Visualize/assignment.md rename to Example project - Github_pages/5-Clustering/1-Visualize/assignment.md diff --git a/5-Clustering/1-Visualize/images/all-genres.png b/Example project - Github_pages/5-Clustering/1-Visualize/images/all-genres.png similarity index 100% rename from 5-Clustering/1-Visualize/images/all-genres.png rename to Example project - Github_pages/5-Clustering/1-Visualize/images/all-genres.png diff --git a/5-Clustering/1-Visualize/images/centroid.png b/Example project - Github_pages/5-Clustering/1-Visualize/images/centroid.png similarity index 100% rename from 5-Clustering/1-Visualize/images/centroid.png rename to Example project - Github_pages/5-Clustering/1-Visualize/images/centroid.png diff --git a/5-Clustering/1-Visualize/images/correlation.png b/Example project - Github_pages/5-Clustering/1-Visualize/images/correlation.png similarity index 100% rename from 5-Clustering/1-Visualize/images/correlation.png rename to Example project - Github_pages/5-Clustering/1-Visualize/images/correlation.png diff --git a/5-Clustering/1-Visualize/images/distribution.png b/Example project - Github_pages/5-Clustering/1-Visualize/images/distribution.png similarity index 100% rename from 5-Clustering/1-Visualize/images/distribution.png rename to Example project - Github_pages/5-Clustering/1-Visualize/images/distribution.png diff --git a/5-Clustering/1-Visualize/images/facetgrid.png b/Example project - Github_pages/5-Clustering/1-Visualize/images/facetgrid.png similarity index 100% rename from 5-Clustering/1-Visualize/images/facetgrid.png rename to Example project - Github_pages/5-Clustering/1-Visualize/images/facetgrid.png diff --git a/5-Clustering/1-Visualize/images/flat-nonflat.png b/Example project - Github_pages/5-Clustering/1-Visualize/images/flat-nonflat.png similarity index 100% rename from 5-Clustering/1-Visualize/images/flat-nonflat.png rename to Example project - Github_pages/5-Clustering/1-Visualize/images/flat-nonflat.png diff --git a/5-Clustering/1-Visualize/images/hierarchical.png b/Example project - Github_pages/5-Clustering/1-Visualize/images/hierarchical.png similarity index 100% rename from 5-Clustering/1-Visualize/images/hierarchical.png rename to Example project - Github_pages/5-Clustering/1-Visualize/images/hierarchical.png diff --git a/5-Clustering/1-Visualize/images/popular.png b/Example project - Github_pages/5-Clustering/1-Visualize/images/popular.png similarity index 100% rename from 5-Clustering/1-Visualize/images/popular.png rename to Example project - Github_pages/5-Clustering/1-Visualize/images/popular.png diff --git a/5-Clustering/1-Visualize/notebook.ipynb b/Example project - Github_pages/5-Clustering/1-Visualize/notebook.ipynb similarity index 100% rename from 5-Clustering/1-Visualize/notebook.ipynb rename to Example project - Github_pages/5-Clustering/1-Visualize/notebook.ipynb diff --git a/5-Clustering/1-Visualize/solution/Julia/README.md b/Example project - Github_pages/5-Clustering/1-Visualize/solution/Julia/README.md similarity index 100% rename from 5-Clustering/1-Visualize/solution/Julia/README.md rename to Example project - Github_pages/5-Clustering/1-Visualize/solution/Julia/README.md diff --git a/5-Clustering/1-Visualize/solution/R/lesson_14-R.ipynb b/Example project - Github_pages/5-Clustering/1-Visualize/solution/R/lesson_14-R.ipynb similarity index 100% rename from 5-Clustering/1-Visualize/solution/R/lesson_14-R.ipynb rename to Example project - Github_pages/5-Clustering/1-Visualize/solution/R/lesson_14-R.ipynb diff --git a/5-Clustering/1-Visualize/solution/R/lesson_14.Rmd b/Example project - Github_pages/5-Clustering/1-Visualize/solution/R/lesson_14.Rmd similarity index 100% rename from 5-Clustering/1-Visualize/solution/R/lesson_14.Rmd rename to Example project - Github_pages/5-Clustering/1-Visualize/solution/R/lesson_14.Rmd diff --git a/5-Clustering/1-Visualize/solution/R/lesson_14.html b/Example project - Github_pages/5-Clustering/1-Visualize/solution/R/lesson_14.html similarity index 100% rename from 5-Clustering/1-Visualize/solution/R/lesson_14.html rename to Example project - Github_pages/5-Clustering/1-Visualize/solution/R/lesson_14.html diff --git a/5-Clustering/1-Visualize/solution/notebook.ipynb b/Example project - Github_pages/5-Clustering/1-Visualize/solution/notebook.ipynb similarity index 100% rename from 5-Clustering/1-Visualize/solution/notebook.ipynb rename to Example project - Github_pages/5-Clustering/1-Visualize/solution/notebook.ipynb diff --git a/5-Clustering/1-Visualize/translations/README.es.md b/Example project - Github_pages/5-Clustering/1-Visualize/translations/README.es.md similarity index 100% rename from 5-Clustering/1-Visualize/translations/README.es.md rename to Example project - Github_pages/5-Clustering/1-Visualize/translations/README.es.md diff --git a/5-Clustering/1-Visualize/translations/README.it.md b/Example project - Github_pages/5-Clustering/1-Visualize/translations/README.it.md similarity index 100% rename from 5-Clustering/1-Visualize/translations/README.it.md rename to Example project - Github_pages/5-Clustering/1-Visualize/translations/README.it.md diff --git a/5-Clustering/1-Visualize/translations/README.ko.md b/Example project - Github_pages/5-Clustering/1-Visualize/translations/README.ko.md similarity index 100% rename from 5-Clustering/1-Visualize/translations/README.ko.md rename to Example project - Github_pages/5-Clustering/1-Visualize/translations/README.ko.md diff --git a/5-Clustering/1-Visualize/translations/README.zh-cn.md b/Example project - Github_pages/5-Clustering/1-Visualize/translations/README.zh-cn.md similarity index 100% rename from 5-Clustering/1-Visualize/translations/README.zh-cn.md rename to Example project - Github_pages/5-Clustering/1-Visualize/translations/README.zh-cn.md diff --git a/5-Clustering/1-Visualize/translations/assignment.es.md b/Example project - Github_pages/5-Clustering/1-Visualize/translations/assignment.es.md similarity index 100% rename from 5-Clustering/1-Visualize/translations/assignment.es.md rename to Example project - Github_pages/5-Clustering/1-Visualize/translations/assignment.es.md diff --git a/5-Clustering/1-Visualize/translations/assignment.it.md b/Example project - Github_pages/5-Clustering/1-Visualize/translations/assignment.it.md similarity index 100% rename from 5-Clustering/1-Visualize/translations/assignment.it.md rename to Example project - Github_pages/5-Clustering/1-Visualize/translations/assignment.it.md diff --git a/5-Clustering/1-Visualize/translations/assignment.ko.md b/Example project - Github_pages/5-Clustering/1-Visualize/translations/assignment.ko.md similarity index 100% rename from 5-Clustering/1-Visualize/translations/assignment.ko.md rename to Example project - Github_pages/5-Clustering/1-Visualize/translations/assignment.ko.md diff --git a/5-Clustering/1-Visualize/translations/assignment.zh-cn.md b/Example project - Github_pages/5-Clustering/1-Visualize/translations/assignment.zh-cn.md similarity index 100% rename from 5-Clustering/1-Visualize/translations/assignment.zh-cn.md rename to Example project - Github_pages/5-Clustering/1-Visualize/translations/assignment.zh-cn.md diff --git a/5-Clustering/2-K-Means/README.md b/Example project - Github_pages/5-Clustering/2-K-Means/README.md similarity index 100% rename from 5-Clustering/2-K-Means/README.md rename to Example project - Github_pages/5-Clustering/2-K-Means/README.md diff --git a/5-Clustering/2-K-Means/assignment.md b/Example project - Github_pages/5-Clustering/2-K-Means/assignment.md similarity index 100% rename from 5-Clustering/2-K-Means/assignment.md rename to Example project - Github_pages/5-Clustering/2-K-Means/assignment.md diff --git a/5-Clustering/2-K-Means/images/boxplots.png b/Example project - Github_pages/5-Clustering/2-K-Means/images/boxplots.png similarity index 100% rename from 5-Clustering/2-K-Means/images/boxplots.png rename to Example project - Github_pages/5-Clustering/2-K-Means/images/boxplots.png diff --git a/5-Clustering/2-K-Means/images/clusters.png b/Example project - Github_pages/5-Clustering/2-K-Means/images/clusters.png similarity index 100% rename from 5-Clustering/2-K-Means/images/clusters.png rename to Example project - Github_pages/5-Clustering/2-K-Means/images/clusters.png diff --git a/5-Clustering/2-K-Means/images/elbow.png b/Example project - Github_pages/5-Clustering/2-K-Means/images/elbow.png similarity index 100% rename from 5-Clustering/2-K-Means/images/elbow.png rename to Example project - Github_pages/5-Clustering/2-K-Means/images/elbow.png diff --git a/5-Clustering/2-K-Means/images/kmeans.gif b/Example project - Github_pages/5-Clustering/2-K-Means/images/kmeans.gif similarity index 100% rename from 5-Clustering/2-K-Means/images/kmeans.gif rename to Example project - Github_pages/5-Clustering/2-K-Means/images/kmeans.gif diff --git a/5-Clustering/2-K-Means/images/problems.png b/Example project - Github_pages/5-Clustering/2-K-Means/images/problems.png similarity index 100% rename from 5-Clustering/2-K-Means/images/problems.png rename to Example project - Github_pages/5-Clustering/2-K-Means/images/problems.png diff --git a/5-Clustering/2-K-Means/images/r_learners_sm.jpeg b/Example project - Github_pages/5-Clustering/2-K-Means/images/r_learners_sm.jpeg similarity index 100% rename from 5-Clustering/2-K-Means/images/r_learners_sm.jpeg rename to Example project - Github_pages/5-Clustering/2-K-Means/images/r_learners_sm.jpeg diff --git a/5-Clustering/2-K-Means/images/voronoi.png b/Example project - Github_pages/5-Clustering/2-K-Means/images/voronoi.png similarity index 100% rename from 5-Clustering/2-K-Means/images/voronoi.png rename to Example project - Github_pages/5-Clustering/2-K-Means/images/voronoi.png diff --git a/5-Clustering/2-K-Means/notebook.ipynb b/Example project - Github_pages/5-Clustering/2-K-Means/notebook.ipynb similarity index 100% rename from 5-Clustering/2-K-Means/notebook.ipynb rename to Example project - Github_pages/5-Clustering/2-K-Means/notebook.ipynb diff --git a/5-Clustering/2-K-Means/solution/Julia/README.md b/Example project - Github_pages/5-Clustering/2-K-Means/solution/Julia/README.md similarity index 100% rename from 5-Clustering/2-K-Means/solution/Julia/README.md rename to Example project - Github_pages/5-Clustering/2-K-Means/solution/Julia/README.md diff --git a/5-Clustering/2-K-Means/solution/R/lesson_15-R.ipynb b/Example project - Github_pages/5-Clustering/2-K-Means/solution/R/lesson_15-R.ipynb similarity index 100% rename from 5-Clustering/2-K-Means/solution/R/lesson_15-R.ipynb rename to Example project - Github_pages/5-Clustering/2-K-Means/solution/R/lesson_15-R.ipynb diff --git a/5-Clustering/2-K-Means/solution/R/lesson_15.Rmd b/Example project - Github_pages/5-Clustering/2-K-Means/solution/R/lesson_15.Rmd similarity index 100% rename from 5-Clustering/2-K-Means/solution/R/lesson_15.Rmd rename to Example project - Github_pages/5-Clustering/2-K-Means/solution/R/lesson_15.Rmd diff --git a/5-Clustering/2-K-Means/solution/R/lesson_15.html b/Example project - Github_pages/5-Clustering/2-K-Means/solution/R/lesson_15.html similarity index 100% rename from 5-Clustering/2-K-Means/solution/R/lesson_15.html rename to Example project - Github_pages/5-Clustering/2-K-Means/solution/R/lesson_15.html diff --git a/5-Clustering/2-K-Means/solution/notebook.ipynb b/Example project - Github_pages/5-Clustering/2-K-Means/solution/notebook.ipynb similarity index 100% rename from 5-Clustering/2-K-Means/solution/notebook.ipynb rename to Example project - Github_pages/5-Clustering/2-K-Means/solution/notebook.ipynb diff --git a/5-Clustering/2-K-Means/solution/tester.ipynb b/Example project - Github_pages/5-Clustering/2-K-Means/solution/tester.ipynb similarity index 100% rename from 5-Clustering/2-K-Means/solution/tester.ipynb rename to Example project - Github_pages/5-Clustering/2-K-Means/solution/tester.ipynb diff --git a/5-Clustering/2-K-Means/translations/README.es.md b/Example project - Github_pages/5-Clustering/2-K-Means/translations/README.es.md similarity index 100% rename from 5-Clustering/2-K-Means/translations/README.es.md rename to Example project - Github_pages/5-Clustering/2-K-Means/translations/README.es.md diff --git a/5-Clustering/2-K-Means/translations/README.it.md b/Example project - Github_pages/5-Clustering/2-K-Means/translations/README.it.md similarity index 100% rename from 5-Clustering/2-K-Means/translations/README.it.md rename to Example project - Github_pages/5-Clustering/2-K-Means/translations/README.it.md diff --git a/5-Clustering/2-K-Means/translations/README.ko.md b/Example project - Github_pages/5-Clustering/2-K-Means/translations/README.ko.md similarity index 100% rename from 5-Clustering/2-K-Means/translations/README.ko.md rename to Example project - Github_pages/5-Clustering/2-K-Means/translations/README.ko.md diff --git a/5-Clustering/2-K-Means/translations/README.zh-cn.md b/Example project - Github_pages/5-Clustering/2-K-Means/translations/README.zh-cn.md similarity index 100% rename from 5-Clustering/2-K-Means/translations/README.zh-cn.md rename to Example project - Github_pages/5-Clustering/2-K-Means/translations/README.zh-cn.md diff --git a/5-Clustering/2-K-Means/translations/assignment.es.md b/Example project - Github_pages/5-Clustering/2-K-Means/translations/assignment.es.md similarity index 100% rename from 5-Clustering/2-K-Means/translations/assignment.es.md rename to Example project - Github_pages/5-Clustering/2-K-Means/translations/assignment.es.md diff --git a/5-Clustering/2-K-Means/translations/assignment.it.md b/Example project - Github_pages/5-Clustering/2-K-Means/translations/assignment.it.md similarity index 100% rename from 5-Clustering/2-K-Means/translations/assignment.it.md rename to Example project - Github_pages/5-Clustering/2-K-Means/translations/assignment.it.md diff --git a/5-Clustering/2-K-Means/translations/assignment.ko.md b/Example project - Github_pages/5-Clustering/2-K-Means/translations/assignment.ko.md similarity index 100% rename from 5-Clustering/2-K-Means/translations/assignment.ko.md rename to Example project - Github_pages/5-Clustering/2-K-Means/translations/assignment.ko.md diff --git a/5-Clustering/2-K-Means/translations/assignment.zh-cn.md b/Example project - Github_pages/5-Clustering/2-K-Means/translations/assignment.zh-cn.md similarity index 100% rename from 5-Clustering/2-K-Means/translations/assignment.zh-cn.md rename to Example project - Github_pages/5-Clustering/2-K-Means/translations/assignment.zh-cn.md diff --git a/5-Clustering/README.md b/Example project - Github_pages/5-Clustering/README.md similarity index 100% rename from 5-Clustering/README.md rename to Example project - Github_pages/5-Clustering/README.md diff --git a/5-Clustering/data/nigerian-songs.csv b/Example project - Github_pages/5-Clustering/data/nigerian-songs.csv similarity index 100% rename from 5-Clustering/data/nigerian-songs.csv rename to Example project - Github_pages/5-Clustering/data/nigerian-songs.csv diff --git a/5-Clustering/images/turntable.jpg b/Example project - Github_pages/5-Clustering/images/turntable.jpg similarity index 100% rename from 5-Clustering/images/turntable.jpg rename to Example project - Github_pages/5-Clustering/images/turntable.jpg diff --git a/5-Clustering/translations/README.es.md b/Example project - Github_pages/5-Clustering/translations/README.es.md similarity index 100% rename from 5-Clustering/translations/README.es.md rename to Example project - Github_pages/5-Clustering/translations/README.es.md diff --git a/5-Clustering/translations/README.hi.md b/Example project - Github_pages/5-Clustering/translations/README.hi.md similarity index 100% rename from 5-Clustering/translations/README.hi.md rename to Example project - Github_pages/5-Clustering/translations/README.hi.md diff --git a/5-Clustering/translations/README.it.md b/Example project - Github_pages/5-Clustering/translations/README.it.md similarity index 100% rename from 5-Clustering/translations/README.it.md rename to Example project - Github_pages/5-Clustering/translations/README.it.md diff --git a/5-Clustering/translations/README.ko.md b/Example project - Github_pages/5-Clustering/translations/README.ko.md similarity index 100% rename from 5-Clustering/translations/README.ko.md rename to Example project - Github_pages/5-Clustering/translations/README.ko.md diff --git a/5-Clustering/translations/README.ru.md b/Example project - Github_pages/5-Clustering/translations/README.ru.md similarity index 100% rename from 5-Clustering/translations/README.ru.md rename to Example project - Github_pages/5-Clustering/translations/README.ru.md diff --git a/5-Clustering/translations/README.zh-cn.md b/Example project - Github_pages/5-Clustering/translations/README.zh-cn.md similarity index 100% rename from 5-Clustering/translations/README.zh-cn.md rename to Example project - Github_pages/5-Clustering/translations/README.zh-cn.md diff --git a/6-NLP/1-Introduction-to-NLP/README.md b/Example project - Github_pages/6-NLP/1-Introduction-to-NLP/README.md similarity index 100% rename from 6-NLP/1-Introduction-to-NLP/README.md rename to Example project - Github_pages/6-NLP/1-Introduction-to-NLP/README.md diff --git a/6-NLP/1-Introduction-to-NLP/assignment.md b/Example project - Github_pages/6-NLP/1-Introduction-to-NLP/assignment.md similarity index 100% rename from 6-NLP/1-Introduction-to-NLP/assignment.md rename to Example project - Github_pages/6-NLP/1-Introduction-to-NLP/assignment.md diff --git a/6-NLP/1-Introduction-to-NLP/images/comprehension.png b/Example project - Github_pages/6-NLP/1-Introduction-to-NLP/images/comprehension.png similarity index 100% rename from 6-NLP/1-Introduction-to-NLP/images/comprehension.png rename to Example project - Github_pages/6-NLP/1-Introduction-to-NLP/images/comprehension.png diff --git a/6-NLP/1-Introduction-to-NLP/solution/bot.py b/Example project - Github_pages/6-NLP/1-Introduction-to-NLP/solution/bot.py similarity index 100% rename from 6-NLP/1-Introduction-to-NLP/solution/bot.py rename to Example project - Github_pages/6-NLP/1-Introduction-to-NLP/solution/bot.py diff --git a/6-NLP/1-Introduction-to-NLP/translations/README.es.md b/Example project - Github_pages/6-NLP/1-Introduction-to-NLP/translations/README.es.md similarity index 100% rename from 6-NLP/1-Introduction-to-NLP/translations/README.es.md rename to Example project - Github_pages/6-NLP/1-Introduction-to-NLP/translations/README.es.md diff --git a/6-NLP/1-Introduction-to-NLP/translations/README.it.md b/Example project - Github_pages/6-NLP/1-Introduction-to-NLP/translations/README.it.md similarity index 100% rename from 6-NLP/1-Introduction-to-NLP/translations/README.it.md rename to Example project - Github_pages/6-NLP/1-Introduction-to-NLP/translations/README.it.md diff --git a/6-NLP/1-Introduction-to-NLP/translations/README.ko.md b/Example project - Github_pages/6-NLP/1-Introduction-to-NLP/translations/README.ko.md similarity index 100% rename from 6-NLP/1-Introduction-to-NLP/translations/README.ko.md rename to Example project - Github_pages/6-NLP/1-Introduction-to-NLP/translations/README.ko.md diff --git a/6-NLP/1-Introduction-to-NLP/translations/README.pt-br.md b/Example project - Github_pages/6-NLP/1-Introduction-to-NLP/translations/README.pt-br.md similarity index 100% rename from 6-NLP/1-Introduction-to-NLP/translations/README.pt-br.md rename to Example project - Github_pages/6-NLP/1-Introduction-to-NLP/translations/README.pt-br.md diff --git a/6-NLP/1-Introduction-to-NLP/translations/README.zh-cn.md b/Example project - Github_pages/6-NLP/1-Introduction-to-NLP/translations/README.zh-cn.md similarity index 100% rename from 6-NLP/1-Introduction-to-NLP/translations/README.zh-cn.md rename to Example project - Github_pages/6-NLP/1-Introduction-to-NLP/translations/README.zh-cn.md diff --git a/6-NLP/1-Introduction-to-NLP/translations/assignment.es.md b/Example project - Github_pages/6-NLP/1-Introduction-to-NLP/translations/assignment.es.md similarity index 100% rename from 6-NLP/1-Introduction-to-NLP/translations/assignment.es.md rename to Example project - Github_pages/6-NLP/1-Introduction-to-NLP/translations/assignment.es.md diff --git a/6-NLP/1-Introduction-to-NLP/translations/assignment.it.md b/Example project - Github_pages/6-NLP/1-Introduction-to-NLP/translations/assignment.it.md similarity index 100% rename from 6-NLP/1-Introduction-to-NLP/translations/assignment.it.md rename to Example project - Github_pages/6-NLP/1-Introduction-to-NLP/translations/assignment.it.md diff --git a/6-NLP/1-Introduction-to-NLP/translations/assignment.ko.md b/Example project - Github_pages/6-NLP/1-Introduction-to-NLP/translations/assignment.ko.md similarity index 100% rename from 6-NLP/1-Introduction-to-NLP/translations/assignment.ko.md rename to Example project - Github_pages/6-NLP/1-Introduction-to-NLP/translations/assignment.ko.md diff --git a/6-NLP/1-Introduction-to-NLP/translations/assignment.pt-br.md b/Example project - Github_pages/6-NLP/1-Introduction-to-NLP/translations/assignment.pt-br.md similarity index 100% rename from 6-NLP/1-Introduction-to-NLP/translations/assignment.pt-br.md rename to Example project - Github_pages/6-NLP/1-Introduction-to-NLP/translations/assignment.pt-br.md diff --git a/6-NLP/2-Tasks/README.md b/Example project - Github_pages/6-NLP/2-Tasks/README.md similarity index 100% rename from 6-NLP/2-Tasks/README.md rename to Example project - Github_pages/6-NLP/2-Tasks/README.md diff --git a/6-NLP/2-Tasks/assignment.md b/Example project - Github_pages/6-NLP/2-Tasks/assignment.md similarity index 100% rename from 6-NLP/2-Tasks/assignment.md rename to Example project - Github_pages/6-NLP/2-Tasks/assignment.md diff --git a/6-NLP/2-Tasks/images/embedding.png b/Example project - Github_pages/6-NLP/2-Tasks/images/embedding.png similarity index 100% rename from 6-NLP/2-Tasks/images/embedding.png rename to Example project - Github_pages/6-NLP/2-Tasks/images/embedding.png diff --git a/6-NLP/2-Tasks/images/n-grams.gif b/Example project - Github_pages/6-NLP/2-Tasks/images/n-grams.gif similarity index 100% rename from 6-NLP/2-Tasks/images/n-grams.gif rename to Example project - Github_pages/6-NLP/2-Tasks/images/n-grams.gif diff --git a/6-NLP/2-Tasks/images/parse.png b/Example project - Github_pages/6-NLP/2-Tasks/images/parse.png similarity index 100% rename from 6-NLP/2-Tasks/images/parse.png rename to Example project - Github_pages/6-NLP/2-Tasks/images/parse.png diff --git a/6-NLP/2-Tasks/images/tokenization.png b/Example project - Github_pages/6-NLP/2-Tasks/images/tokenization.png similarity index 100% rename from 6-NLP/2-Tasks/images/tokenization.png rename to Example project - Github_pages/6-NLP/2-Tasks/images/tokenization.png diff --git a/6-NLP/2-Tasks/solution/bot.py b/Example project - Github_pages/6-NLP/2-Tasks/solution/bot.py similarity index 100% rename from 6-NLP/2-Tasks/solution/bot.py rename to Example project - Github_pages/6-NLP/2-Tasks/solution/bot.py diff --git a/6-NLP/2-Tasks/translations/README.es.md b/Example project - Github_pages/6-NLP/2-Tasks/translations/README.es.md similarity index 100% rename from 6-NLP/2-Tasks/translations/README.es.md rename to Example project - Github_pages/6-NLP/2-Tasks/translations/README.es.md diff --git a/6-NLP/2-Tasks/translations/README.it.md b/Example project - Github_pages/6-NLP/2-Tasks/translations/README.it.md similarity index 100% rename from 6-NLP/2-Tasks/translations/README.it.md rename to Example project - Github_pages/6-NLP/2-Tasks/translations/README.it.md diff --git a/6-NLP/2-Tasks/translations/README.ko.md b/Example project - Github_pages/6-NLP/2-Tasks/translations/README.ko.md similarity index 100% rename from 6-NLP/2-Tasks/translations/README.ko.md rename to Example project - Github_pages/6-NLP/2-Tasks/translations/README.ko.md diff --git a/6-NLP/2-Tasks/translations/README.pt-br.md b/Example project - Github_pages/6-NLP/2-Tasks/translations/README.pt-br.md similarity index 100% rename from 6-NLP/2-Tasks/translations/README.pt-br.md rename to Example project - Github_pages/6-NLP/2-Tasks/translations/README.pt-br.md diff --git a/6-NLP/2-Tasks/translations/assignment.es.md b/Example project - Github_pages/6-NLP/2-Tasks/translations/assignment.es.md similarity index 100% rename from 6-NLP/2-Tasks/translations/assignment.es.md rename to Example project - Github_pages/6-NLP/2-Tasks/translations/assignment.es.md diff --git a/6-NLP/2-Tasks/translations/assignment.it.md b/Example project - Github_pages/6-NLP/2-Tasks/translations/assignment.it.md similarity index 100% rename from 6-NLP/2-Tasks/translations/assignment.it.md rename to Example project - Github_pages/6-NLP/2-Tasks/translations/assignment.it.md diff --git a/6-NLP/2-Tasks/translations/assignment.ko.md b/Example project - Github_pages/6-NLP/2-Tasks/translations/assignment.ko.md similarity index 100% rename from 6-NLP/2-Tasks/translations/assignment.ko.md rename to Example project - Github_pages/6-NLP/2-Tasks/translations/assignment.ko.md diff --git a/6-NLP/2-Tasks/translations/assignment.pt-br.md b/Example project - Github_pages/6-NLP/2-Tasks/translations/assignment.pt-br.md similarity index 100% rename from 6-NLP/2-Tasks/translations/assignment.pt-br.md rename to Example project - Github_pages/6-NLP/2-Tasks/translations/assignment.pt-br.md diff --git a/6-NLP/3-Translation-Sentiment/README.md b/Example project - Github_pages/6-NLP/3-Translation-Sentiment/README.md similarity index 100% rename from 6-NLP/3-Translation-Sentiment/README.md rename to Example project - Github_pages/6-NLP/3-Translation-Sentiment/README.md diff --git a/6-NLP/3-Translation-Sentiment/assignment.md b/Example project - Github_pages/6-NLP/3-Translation-Sentiment/assignment.md similarity index 100% rename from 6-NLP/3-Translation-Sentiment/assignment.md rename to Example project - Github_pages/6-NLP/3-Translation-Sentiment/assignment.md diff --git a/6-NLP/3-Translation-Sentiment/images/monnaie.png b/Example project - Github_pages/6-NLP/3-Translation-Sentiment/images/monnaie.png similarity index 100% rename from 6-NLP/3-Translation-Sentiment/images/monnaie.png rename to Example project - Github_pages/6-NLP/3-Translation-Sentiment/images/monnaie.png diff --git a/6-NLP/3-Translation-Sentiment/solution/Julia/README.md b/Example project - Github_pages/6-NLP/3-Translation-Sentiment/solution/Julia/README.md similarity index 100% rename from 6-NLP/3-Translation-Sentiment/solution/Julia/README.md rename to Example project - Github_pages/6-NLP/3-Translation-Sentiment/solution/Julia/README.md diff --git a/6-NLP/3-Translation-Sentiment/solution/R/README.md b/Example project - Github_pages/6-NLP/3-Translation-Sentiment/solution/R/README.md similarity index 100% rename from 6-NLP/3-Translation-Sentiment/solution/R/README.md rename to Example project - Github_pages/6-NLP/3-Translation-Sentiment/solution/R/README.md diff --git a/6-NLP/3-Translation-Sentiment/solution/notebook.ipynb b/Example project - Github_pages/6-NLP/3-Translation-Sentiment/solution/notebook.ipynb similarity index 100% rename from 6-NLP/3-Translation-Sentiment/solution/notebook.ipynb rename to Example project - Github_pages/6-NLP/3-Translation-Sentiment/solution/notebook.ipynb diff --git a/6-NLP/3-Translation-Sentiment/translations/README.es.md b/Example project - Github_pages/6-NLP/3-Translation-Sentiment/translations/README.es.md similarity index 100% rename from 6-NLP/3-Translation-Sentiment/translations/README.es.md rename to Example project - Github_pages/6-NLP/3-Translation-Sentiment/translations/README.es.md diff --git a/6-NLP/3-Translation-Sentiment/translations/README.it.md b/Example project - Github_pages/6-NLP/3-Translation-Sentiment/translations/README.it.md similarity index 100% rename from 6-NLP/3-Translation-Sentiment/translations/README.it.md rename to Example project - Github_pages/6-NLP/3-Translation-Sentiment/translations/README.it.md diff --git a/6-NLP/3-Translation-Sentiment/translations/README.ko.md b/Example project - Github_pages/6-NLP/3-Translation-Sentiment/translations/README.ko.md similarity index 100% rename from 6-NLP/3-Translation-Sentiment/translations/README.ko.md rename to Example project - Github_pages/6-NLP/3-Translation-Sentiment/translations/README.ko.md diff --git a/6-NLP/3-Translation-Sentiment/translations/assignment.es.md b/Example project - Github_pages/6-NLP/3-Translation-Sentiment/translations/assignment.es.md similarity index 100% rename from 6-NLP/3-Translation-Sentiment/translations/assignment.es.md rename to Example project - Github_pages/6-NLP/3-Translation-Sentiment/translations/assignment.es.md diff --git a/6-NLP/3-Translation-Sentiment/translations/assignment.it.md b/Example project - Github_pages/6-NLP/3-Translation-Sentiment/translations/assignment.it.md similarity index 100% rename from 6-NLP/3-Translation-Sentiment/translations/assignment.it.md rename to Example project - Github_pages/6-NLP/3-Translation-Sentiment/translations/assignment.it.md diff --git a/6-NLP/3-Translation-Sentiment/translations/assignment.ko.md b/Example project - Github_pages/6-NLP/3-Translation-Sentiment/translations/assignment.ko.md similarity index 100% rename from 6-NLP/3-Translation-Sentiment/translations/assignment.ko.md rename to Example project - Github_pages/6-NLP/3-Translation-Sentiment/translations/assignment.ko.md diff --git a/6-NLP/4-Hotel-Reviews-1/README.md b/Example project - Github_pages/6-NLP/4-Hotel-Reviews-1/README.md similarity index 100% rename from 6-NLP/4-Hotel-Reviews-1/README.md rename to Example project - Github_pages/6-NLP/4-Hotel-Reviews-1/README.md diff --git a/6-NLP/4-Hotel-Reviews-1/assignment.md b/Example project - Github_pages/6-NLP/4-Hotel-Reviews-1/assignment.md similarity index 100% rename from 6-NLP/4-Hotel-Reviews-1/assignment.md rename to Example project - Github_pages/6-NLP/4-Hotel-Reviews-1/assignment.md diff --git a/6-NLP/4-Hotel-Reviews-1/notebook.ipynb b/Example project - Github_pages/6-NLP/4-Hotel-Reviews-1/notebook.ipynb similarity index 100% rename from 6-NLP/4-Hotel-Reviews-1/notebook.ipynb rename to Example project - Github_pages/6-NLP/4-Hotel-Reviews-1/notebook.ipynb diff --git a/6-NLP/4-Hotel-Reviews-1/solution/Julia/README.md b/Example project - Github_pages/6-NLP/4-Hotel-Reviews-1/solution/Julia/README.md similarity index 100% rename from 6-NLP/4-Hotel-Reviews-1/solution/Julia/README.md rename to Example project - Github_pages/6-NLP/4-Hotel-Reviews-1/solution/Julia/README.md diff --git a/6-NLP/4-Hotel-Reviews-1/solution/R/README.md b/Example project - Github_pages/6-NLP/4-Hotel-Reviews-1/solution/R/README.md similarity index 100% rename from 6-NLP/4-Hotel-Reviews-1/solution/R/README.md rename to Example project - Github_pages/6-NLP/4-Hotel-Reviews-1/solution/R/README.md diff --git a/6-NLP/4-Hotel-Reviews-1/solution/notebook.ipynb b/Example project - Github_pages/6-NLP/4-Hotel-Reviews-1/solution/notebook.ipynb similarity index 100% rename from 6-NLP/4-Hotel-Reviews-1/solution/notebook.ipynb rename to Example project - Github_pages/6-NLP/4-Hotel-Reviews-1/solution/notebook.ipynb diff --git a/6-NLP/4-Hotel-Reviews-1/translations/README.es.md b/Example project - Github_pages/6-NLP/4-Hotel-Reviews-1/translations/README.es.md similarity index 100% rename from 6-NLP/4-Hotel-Reviews-1/translations/README.es.md rename to Example project - Github_pages/6-NLP/4-Hotel-Reviews-1/translations/README.es.md diff --git a/6-NLP/4-Hotel-Reviews-1/translations/README.it.md b/Example project - Github_pages/6-NLP/4-Hotel-Reviews-1/translations/README.it.md similarity index 100% rename from 6-NLP/4-Hotel-Reviews-1/translations/README.it.md rename to Example project - Github_pages/6-NLP/4-Hotel-Reviews-1/translations/README.it.md diff --git a/6-NLP/4-Hotel-Reviews-1/translations/README.ko.md b/Example project - Github_pages/6-NLP/4-Hotel-Reviews-1/translations/README.ko.md similarity index 100% rename from 6-NLP/4-Hotel-Reviews-1/translations/README.ko.md rename to Example project - Github_pages/6-NLP/4-Hotel-Reviews-1/translations/README.ko.md diff --git a/6-NLP/4-Hotel-Reviews-1/translations/assignment.es.md b/Example project - Github_pages/6-NLP/4-Hotel-Reviews-1/translations/assignment.es.md similarity index 100% rename from 6-NLP/4-Hotel-Reviews-1/translations/assignment.es.md rename to Example project - Github_pages/6-NLP/4-Hotel-Reviews-1/translations/assignment.es.md diff --git a/6-NLP/4-Hotel-Reviews-1/translations/assignment.it.md b/Example project - Github_pages/6-NLP/4-Hotel-Reviews-1/translations/assignment.it.md similarity index 100% rename from 6-NLP/4-Hotel-Reviews-1/translations/assignment.it.md rename to Example project - Github_pages/6-NLP/4-Hotel-Reviews-1/translations/assignment.it.md diff --git a/6-NLP/4-Hotel-Reviews-1/translations/assignment.ko.md b/Example project - Github_pages/6-NLP/4-Hotel-Reviews-1/translations/assignment.ko.md similarity index 100% rename from 6-NLP/4-Hotel-Reviews-1/translations/assignment.ko.md rename to Example project - Github_pages/6-NLP/4-Hotel-Reviews-1/translations/assignment.ko.md diff --git a/6-NLP/5-Hotel-Reviews-2/README.md b/Example project - Github_pages/6-NLP/5-Hotel-Reviews-2/README.md similarity index 100% rename from 6-NLP/5-Hotel-Reviews-2/README.md rename to Example project - Github_pages/6-NLP/5-Hotel-Reviews-2/README.md diff --git a/6-NLP/5-Hotel-Reviews-2/assignment.md b/Example project - Github_pages/6-NLP/5-Hotel-Reviews-2/assignment.md similarity index 100% rename from 6-NLP/5-Hotel-Reviews-2/assignment.md rename to Example project - Github_pages/6-NLP/5-Hotel-Reviews-2/assignment.md diff --git a/6-NLP/5-Hotel-Reviews-2/notebook.ipynb b/Example project - Github_pages/6-NLP/5-Hotel-Reviews-2/notebook.ipynb similarity index 100% rename from 6-NLP/5-Hotel-Reviews-2/notebook.ipynb rename to Example project - Github_pages/6-NLP/5-Hotel-Reviews-2/notebook.ipynb diff --git a/6-NLP/5-Hotel-Reviews-2/solution/1-notebook.ipynb b/Example project - Github_pages/6-NLP/5-Hotel-Reviews-2/solution/1-notebook.ipynb similarity index 100% rename from 6-NLP/5-Hotel-Reviews-2/solution/1-notebook.ipynb rename to Example project - Github_pages/6-NLP/5-Hotel-Reviews-2/solution/1-notebook.ipynb diff --git a/6-NLP/5-Hotel-Reviews-2/solution/2-notebook.ipynb b/Example project - Github_pages/6-NLP/5-Hotel-Reviews-2/solution/2-notebook.ipynb similarity index 100% rename from 6-NLP/5-Hotel-Reviews-2/solution/2-notebook.ipynb rename to Example project - Github_pages/6-NLP/5-Hotel-Reviews-2/solution/2-notebook.ipynb diff --git a/6-NLP/5-Hotel-Reviews-2/solution/3-notebook.ipynb b/Example project - Github_pages/6-NLP/5-Hotel-Reviews-2/solution/3-notebook.ipynb similarity index 100% rename from 6-NLP/5-Hotel-Reviews-2/solution/3-notebook.ipynb rename to Example project - Github_pages/6-NLP/5-Hotel-Reviews-2/solution/3-notebook.ipynb diff --git a/6-NLP/5-Hotel-Reviews-2/solution/Julia/README.md b/Example project - Github_pages/6-NLP/5-Hotel-Reviews-2/solution/Julia/README.md similarity index 100% rename from 6-NLP/5-Hotel-Reviews-2/solution/Julia/README.md rename to Example project - Github_pages/6-NLP/5-Hotel-Reviews-2/solution/Julia/README.md diff --git a/6-NLP/5-Hotel-Reviews-2/solution/R/README.md b/Example project - Github_pages/6-NLP/5-Hotel-Reviews-2/solution/R/README.md similarity index 100% rename from 6-NLP/5-Hotel-Reviews-2/solution/R/README.md rename to Example project - Github_pages/6-NLP/5-Hotel-Reviews-2/solution/R/README.md diff --git a/6-NLP/5-Hotel-Reviews-2/translations/README.es.md b/Example project - Github_pages/6-NLP/5-Hotel-Reviews-2/translations/README.es.md similarity index 100% rename from 6-NLP/5-Hotel-Reviews-2/translations/README.es.md rename to Example project - Github_pages/6-NLP/5-Hotel-Reviews-2/translations/README.es.md diff --git a/6-NLP/5-Hotel-Reviews-2/translations/README.it.md b/Example project - Github_pages/6-NLP/5-Hotel-Reviews-2/translations/README.it.md similarity index 100% rename from 6-NLP/5-Hotel-Reviews-2/translations/README.it.md rename to Example project - Github_pages/6-NLP/5-Hotel-Reviews-2/translations/README.it.md diff --git a/6-NLP/5-Hotel-Reviews-2/translations/README.ko.md b/Example project - Github_pages/6-NLP/5-Hotel-Reviews-2/translations/README.ko.md similarity index 100% rename from 6-NLP/5-Hotel-Reviews-2/translations/README.ko.md rename to Example project - Github_pages/6-NLP/5-Hotel-Reviews-2/translations/README.ko.md diff --git a/6-NLP/5-Hotel-Reviews-2/translations/assignment.es.md b/Example project - Github_pages/6-NLP/5-Hotel-Reviews-2/translations/assignment.es.md similarity index 100% rename from 6-NLP/5-Hotel-Reviews-2/translations/assignment.es.md rename to Example project - Github_pages/6-NLP/5-Hotel-Reviews-2/translations/assignment.es.md diff --git a/6-NLP/5-Hotel-Reviews-2/translations/assignment.it.md b/Example project - Github_pages/6-NLP/5-Hotel-Reviews-2/translations/assignment.it.md similarity index 100% rename from 6-NLP/5-Hotel-Reviews-2/translations/assignment.it.md rename to Example project - Github_pages/6-NLP/5-Hotel-Reviews-2/translations/assignment.it.md diff --git a/6-NLP/5-Hotel-Reviews-2/translations/assignment.ko.md b/Example project - Github_pages/6-NLP/5-Hotel-Reviews-2/translations/assignment.ko.md similarity index 100% rename from 6-NLP/5-Hotel-Reviews-2/translations/assignment.ko.md rename to Example project - Github_pages/6-NLP/5-Hotel-Reviews-2/translations/assignment.ko.md diff --git a/6-NLP/README.md b/Example project - Github_pages/6-NLP/README.md similarity index 100% rename from 6-NLP/README.md rename to Example project - Github_pages/6-NLP/README.md diff --git a/6-NLP/data/README.md b/Example project - Github_pages/6-NLP/data/README.md similarity index 100% rename from 6-NLP/data/README.md rename to Example project - Github_pages/6-NLP/data/README.md diff --git a/6-NLP/images/p&p.jpg b/Example project - Github_pages/6-NLP/images/p&p.jpg similarity index 100% rename from 6-NLP/images/p&p.jpg rename to Example project - Github_pages/6-NLP/images/p&p.jpg diff --git a/6-NLP/translations/README.es.md b/Example project - Github_pages/6-NLP/translations/README.es.md similarity index 100% rename from 6-NLP/translations/README.es.md rename to Example project - Github_pages/6-NLP/translations/README.es.md diff --git a/6-NLP/translations/README.hi.md b/Example project - Github_pages/6-NLP/translations/README.hi.md similarity index 100% rename from 6-NLP/translations/README.hi.md rename to Example project - Github_pages/6-NLP/translations/README.hi.md diff --git a/6-NLP/translations/README.it.md b/Example project - Github_pages/6-NLP/translations/README.it.md similarity index 100% rename from 6-NLP/translations/README.it.md rename to Example project - Github_pages/6-NLP/translations/README.it.md diff --git a/6-NLP/translations/README.ko.md b/Example project - Github_pages/6-NLP/translations/README.ko.md similarity index 100% rename from 6-NLP/translations/README.ko.md rename to Example project - Github_pages/6-NLP/translations/README.ko.md diff --git a/6-NLP/translations/README.pt-br.md b/Example project - Github_pages/6-NLP/translations/README.pt-br.md similarity index 100% rename from 6-NLP/translations/README.pt-br.md rename to Example project - Github_pages/6-NLP/translations/README.pt-br.md diff --git a/6-NLP/translations/README.ru.md b/Example project - Github_pages/6-NLP/translations/README.ru.md similarity index 100% rename from 6-NLP/translations/README.ru.md rename to Example project - Github_pages/6-NLP/translations/README.ru.md diff --git a/6-NLP/translations/README.zh-cn.md b/Example project - Github_pages/6-NLP/translations/README.zh-cn.md similarity index 100% rename from 6-NLP/translations/README.zh-cn.md rename to Example project - Github_pages/6-NLP/translations/README.zh-cn.md diff --git a/7-TimeSeries/1-Introduction/README.md b/Example project - Github_pages/7-TimeSeries/1-Introduction/README.md similarity index 100% rename from 7-TimeSeries/1-Introduction/README.md rename to Example project - Github_pages/7-TimeSeries/1-Introduction/README.md diff --git a/7-TimeSeries/1-Introduction/assignment.md b/Example project - Github_pages/7-TimeSeries/1-Introduction/assignment.md similarity index 100% rename from 7-TimeSeries/1-Introduction/assignment.md rename to Example project - Github_pages/7-TimeSeries/1-Introduction/assignment.md diff --git a/7-TimeSeries/1-Introduction/images/currency.png b/Example project - Github_pages/7-TimeSeries/1-Introduction/images/currency.png similarity index 100% rename from 7-TimeSeries/1-Introduction/images/currency.png rename to Example project - Github_pages/7-TimeSeries/1-Introduction/images/currency.png diff --git a/7-TimeSeries/1-Introduction/images/energy-plot.png b/Example project - Github_pages/7-TimeSeries/1-Introduction/images/energy-plot.png similarity index 100% rename from 7-TimeSeries/1-Introduction/images/energy-plot.png rename to Example project - Github_pages/7-TimeSeries/1-Introduction/images/energy-plot.png diff --git a/7-TimeSeries/1-Introduction/images/july-2014.png b/Example project - Github_pages/7-TimeSeries/1-Introduction/images/july-2014.png similarity index 100% rename from 7-TimeSeries/1-Introduction/images/july-2014.png rename to Example project - Github_pages/7-TimeSeries/1-Introduction/images/july-2014.png diff --git a/7-TimeSeries/1-Introduction/images/scaled.png b/Example project - Github_pages/7-TimeSeries/1-Introduction/images/scaled.png similarity index 100% rename from 7-TimeSeries/1-Introduction/images/scaled.png rename to Example project - Github_pages/7-TimeSeries/1-Introduction/images/scaled.png diff --git a/7-TimeSeries/1-Introduction/solution/Julia/README.md b/Example project - Github_pages/7-TimeSeries/1-Introduction/solution/Julia/README.md similarity index 100% rename from 7-TimeSeries/1-Introduction/solution/Julia/README.md rename to Example project - Github_pages/7-TimeSeries/1-Introduction/solution/Julia/README.md diff --git a/7-TimeSeries/1-Introduction/solution/R/README.md b/Example project - Github_pages/7-TimeSeries/1-Introduction/solution/R/README.md similarity index 100% rename from 7-TimeSeries/1-Introduction/solution/R/README.md rename to Example project - Github_pages/7-TimeSeries/1-Introduction/solution/R/README.md diff --git a/7-TimeSeries/1-Introduction/solution/common/__init__.py b/Example project - Github_pages/7-TimeSeries/1-Introduction/solution/common/__init__.py similarity index 100% rename from 7-TimeSeries/1-Introduction/solution/common/__init__.py rename to Example project - Github_pages/7-TimeSeries/1-Introduction/solution/common/__init__.py diff --git a/7-TimeSeries/1-Introduction/solution/common/environment.yaml b/Example project - Github_pages/7-TimeSeries/1-Introduction/solution/common/environment.yaml similarity index 100% rename from 7-TimeSeries/1-Introduction/solution/common/environment.yaml rename to Example project - Github_pages/7-TimeSeries/1-Introduction/solution/common/environment.yaml diff --git a/7-TimeSeries/1-Introduction/solution/common/extract_data.py b/Example project - Github_pages/7-TimeSeries/1-Introduction/solution/common/extract_data.py similarity index 100% rename from 7-TimeSeries/1-Introduction/solution/common/extract_data.py rename to Example project - Github_pages/7-TimeSeries/1-Introduction/solution/common/extract_data.py diff --git a/7-TimeSeries/1-Introduction/solution/common/utils.py b/Example project - Github_pages/7-TimeSeries/1-Introduction/solution/common/utils.py similarity index 100% rename from 7-TimeSeries/1-Introduction/solution/common/utils.py rename to Example project - Github_pages/7-TimeSeries/1-Introduction/solution/common/utils.py diff --git a/7-TimeSeries/1-Introduction/solution/data/energy.csv b/Example project - Github_pages/7-TimeSeries/1-Introduction/solution/data/energy.csv similarity index 100% rename from 7-TimeSeries/1-Introduction/solution/data/energy.csv rename to Example project - Github_pages/7-TimeSeries/1-Introduction/solution/data/energy.csv diff --git a/7-TimeSeries/1-Introduction/solution/notebook.ipynb b/Example project - Github_pages/7-TimeSeries/1-Introduction/solution/notebook.ipynb similarity index 100% rename from 7-TimeSeries/1-Introduction/solution/notebook.ipynb rename to Example project - Github_pages/7-TimeSeries/1-Introduction/solution/notebook.ipynb diff --git a/7-TimeSeries/1-Introduction/translations/README.es.md b/Example project - Github_pages/7-TimeSeries/1-Introduction/translations/README.es.md similarity index 100% rename from 7-TimeSeries/1-Introduction/translations/README.es.md rename to Example project - Github_pages/7-TimeSeries/1-Introduction/translations/README.es.md diff --git a/7-TimeSeries/1-Introduction/translations/README.it.md b/Example project - Github_pages/7-TimeSeries/1-Introduction/translations/README.it.md similarity index 100% rename from 7-TimeSeries/1-Introduction/translations/README.it.md rename to Example project - Github_pages/7-TimeSeries/1-Introduction/translations/README.it.md diff --git a/7-TimeSeries/1-Introduction/translations/README.ko.md b/Example project - Github_pages/7-TimeSeries/1-Introduction/translations/README.ko.md similarity index 100% rename from 7-TimeSeries/1-Introduction/translations/README.ko.md rename to Example project - Github_pages/7-TimeSeries/1-Introduction/translations/README.ko.md diff --git a/7-TimeSeries/1-Introduction/translations/assignment.es.md b/Example project - Github_pages/7-TimeSeries/1-Introduction/translations/assignment.es.md similarity index 100% rename from 7-TimeSeries/1-Introduction/translations/assignment.es.md rename to Example project - Github_pages/7-TimeSeries/1-Introduction/translations/assignment.es.md diff --git a/7-TimeSeries/1-Introduction/translations/assignment.it.md b/Example project - Github_pages/7-TimeSeries/1-Introduction/translations/assignment.it.md similarity index 100% rename from 7-TimeSeries/1-Introduction/translations/assignment.it.md rename to Example project - Github_pages/7-TimeSeries/1-Introduction/translations/assignment.it.md diff --git a/7-TimeSeries/1-Introduction/translations/assignment.ko.md b/Example project - Github_pages/7-TimeSeries/1-Introduction/translations/assignment.ko.md similarity index 100% rename from 7-TimeSeries/1-Introduction/translations/assignment.ko.md rename to Example project - Github_pages/7-TimeSeries/1-Introduction/translations/assignment.ko.md diff --git a/7-TimeSeries/1-Introduction/working/common/__init__.py b/Example project - Github_pages/7-TimeSeries/1-Introduction/working/common/__init__.py similarity index 100% rename from 7-TimeSeries/1-Introduction/working/common/__init__.py rename to Example project - Github_pages/7-TimeSeries/1-Introduction/working/common/__init__.py diff --git a/7-TimeSeries/1-Introduction/working/common/environment.yaml b/Example project - Github_pages/7-TimeSeries/1-Introduction/working/common/environment.yaml similarity index 100% rename from 7-TimeSeries/1-Introduction/working/common/environment.yaml rename to Example project - Github_pages/7-TimeSeries/1-Introduction/working/common/environment.yaml diff --git a/7-TimeSeries/1-Introduction/working/common/extract_data.py b/Example project - Github_pages/7-TimeSeries/1-Introduction/working/common/extract_data.py similarity index 100% rename from 7-TimeSeries/1-Introduction/working/common/extract_data.py rename to Example project - Github_pages/7-TimeSeries/1-Introduction/working/common/extract_data.py diff --git a/7-TimeSeries/1-Introduction/working/common/utils.py b/Example project - Github_pages/7-TimeSeries/1-Introduction/working/common/utils.py similarity index 100% rename from 7-TimeSeries/1-Introduction/working/common/utils.py rename to Example project - Github_pages/7-TimeSeries/1-Introduction/working/common/utils.py diff --git a/7-TimeSeries/1-Introduction/working/data/energy.csv b/Example project - Github_pages/7-TimeSeries/1-Introduction/working/data/energy.csv similarity index 100% rename from 7-TimeSeries/1-Introduction/working/data/energy.csv rename to Example project - Github_pages/7-TimeSeries/1-Introduction/working/data/energy.csv diff --git a/7-TimeSeries/1-Introduction/working/notebook.ipynb b/Example project - Github_pages/7-TimeSeries/1-Introduction/working/notebook.ipynb similarity index 100% rename from 7-TimeSeries/1-Introduction/working/notebook.ipynb rename to Example project - Github_pages/7-TimeSeries/1-Introduction/working/notebook.ipynb diff --git a/7-TimeSeries/2-ARIMA/README.md b/Example project - Github_pages/7-TimeSeries/2-ARIMA/README.md similarity index 100% rename from 7-TimeSeries/2-ARIMA/README.md rename to Example project - Github_pages/7-TimeSeries/2-ARIMA/README.md diff --git a/7-TimeSeries/2-ARIMA/assignment.md b/Example project - Github_pages/7-TimeSeries/2-ARIMA/assignment.md similarity index 100% rename from 7-TimeSeries/2-ARIMA/assignment.md rename to Example project - Github_pages/7-TimeSeries/2-ARIMA/assignment.md diff --git a/7-TimeSeries/2-ARIMA/images/accuracy.png b/Example project - Github_pages/7-TimeSeries/2-ARIMA/images/accuracy.png similarity index 100% rename from 7-TimeSeries/2-ARIMA/images/accuracy.png rename to Example project - Github_pages/7-TimeSeries/2-ARIMA/images/accuracy.png diff --git a/7-TimeSeries/2-ARIMA/images/mape.png b/Example project - Github_pages/7-TimeSeries/2-ARIMA/images/mape.png similarity index 100% rename from 7-TimeSeries/2-ARIMA/images/mape.png rename to Example project - Github_pages/7-TimeSeries/2-ARIMA/images/mape.png diff --git a/7-TimeSeries/2-ARIMA/images/original.png b/Example project - Github_pages/7-TimeSeries/2-ARIMA/images/original.png similarity index 100% rename from 7-TimeSeries/2-ARIMA/images/original.png rename to Example project - Github_pages/7-TimeSeries/2-ARIMA/images/original.png diff --git a/7-TimeSeries/2-ARIMA/images/scaled.png b/Example project - Github_pages/7-TimeSeries/2-ARIMA/images/scaled.png similarity index 100% rename from 7-TimeSeries/2-ARIMA/images/scaled.png rename to Example project - Github_pages/7-TimeSeries/2-ARIMA/images/scaled.png diff --git a/7-TimeSeries/2-ARIMA/images/train-test.png b/Example project - Github_pages/7-TimeSeries/2-ARIMA/images/train-test.png similarity index 100% rename from 7-TimeSeries/2-ARIMA/images/train-test.png rename to Example project - Github_pages/7-TimeSeries/2-ARIMA/images/train-test.png diff --git a/7-TimeSeries/2-ARIMA/solution/Julia/README.md b/Example project - Github_pages/7-TimeSeries/2-ARIMA/solution/Julia/README.md similarity index 100% rename from 7-TimeSeries/2-ARIMA/solution/Julia/README.md rename to Example project - Github_pages/7-TimeSeries/2-ARIMA/solution/Julia/README.md diff --git a/7-TimeSeries/2-ARIMA/solution/R/README.md b/Example project - Github_pages/7-TimeSeries/2-ARIMA/solution/R/README.md similarity index 100% rename from 7-TimeSeries/2-ARIMA/solution/R/README.md rename to Example project - Github_pages/7-TimeSeries/2-ARIMA/solution/R/README.md diff --git a/7-TimeSeries/2-ARIMA/solution/common/__init__.py b/Example project - Github_pages/7-TimeSeries/2-ARIMA/solution/common/__init__.py similarity index 100% rename from 7-TimeSeries/2-ARIMA/solution/common/__init__.py rename to Example project - Github_pages/7-TimeSeries/2-ARIMA/solution/common/__init__.py diff --git a/7-TimeSeries/2-ARIMA/solution/common/environment.yaml b/Example project - Github_pages/7-TimeSeries/2-ARIMA/solution/common/environment.yaml similarity index 100% rename from 7-TimeSeries/2-ARIMA/solution/common/environment.yaml rename to Example project - Github_pages/7-TimeSeries/2-ARIMA/solution/common/environment.yaml diff --git a/7-TimeSeries/2-ARIMA/solution/common/extract_data.py b/Example project - Github_pages/7-TimeSeries/2-ARIMA/solution/common/extract_data.py similarity index 100% rename from 7-TimeSeries/2-ARIMA/solution/common/extract_data.py rename to Example project - Github_pages/7-TimeSeries/2-ARIMA/solution/common/extract_data.py diff --git a/7-TimeSeries/2-ARIMA/solution/common/utils.py b/Example project - Github_pages/7-TimeSeries/2-ARIMA/solution/common/utils.py similarity index 100% rename from 7-TimeSeries/2-ARIMA/solution/common/utils.py rename to Example project - Github_pages/7-TimeSeries/2-ARIMA/solution/common/utils.py diff --git a/7-TimeSeries/2-ARIMA/solution/data/energy.csv b/Example project - Github_pages/7-TimeSeries/2-ARIMA/solution/data/energy.csv similarity index 100% rename from 7-TimeSeries/2-ARIMA/solution/data/energy.csv rename to Example project - Github_pages/7-TimeSeries/2-ARIMA/solution/data/energy.csv diff --git a/7-TimeSeries/2-ARIMA/solution/notebook.ipynb b/Example project - Github_pages/7-TimeSeries/2-ARIMA/solution/notebook.ipynb similarity index 100% rename from 7-TimeSeries/2-ARIMA/solution/notebook.ipynb rename to Example project - Github_pages/7-TimeSeries/2-ARIMA/solution/notebook.ipynb diff --git a/7-TimeSeries/2-ARIMA/translations/README.it.md b/Example project - Github_pages/7-TimeSeries/2-ARIMA/translations/README.it.md similarity index 100% rename from 7-TimeSeries/2-ARIMA/translations/README.it.md rename to Example project - Github_pages/7-TimeSeries/2-ARIMA/translations/README.it.md diff --git a/7-TimeSeries/2-ARIMA/translations/README.ko.md b/Example project - Github_pages/7-TimeSeries/2-ARIMA/translations/README.ko.md similarity index 100% rename from 7-TimeSeries/2-ARIMA/translations/README.ko.md rename to Example project - Github_pages/7-TimeSeries/2-ARIMA/translations/README.ko.md diff --git a/7-TimeSeries/2-ARIMA/translations/assignment.es.md b/Example project - Github_pages/7-TimeSeries/2-ARIMA/translations/assignment.es.md similarity index 100% rename from 7-TimeSeries/2-ARIMA/translations/assignment.es.md rename to Example project - Github_pages/7-TimeSeries/2-ARIMA/translations/assignment.es.md diff --git a/7-TimeSeries/2-ARIMA/translations/assignment.it.md b/Example project - Github_pages/7-TimeSeries/2-ARIMA/translations/assignment.it.md similarity index 100% rename from 7-TimeSeries/2-ARIMA/translations/assignment.it.md rename to Example project - Github_pages/7-TimeSeries/2-ARIMA/translations/assignment.it.md diff --git a/7-TimeSeries/2-ARIMA/translations/assignment.ko.md b/Example project - Github_pages/7-TimeSeries/2-ARIMA/translations/assignment.ko.md similarity index 100% rename from 7-TimeSeries/2-ARIMA/translations/assignment.ko.md rename to Example project - Github_pages/7-TimeSeries/2-ARIMA/translations/assignment.ko.md diff --git a/7-TimeSeries/2-ARIMA/working/common/__init__.py b/Example project - Github_pages/7-TimeSeries/2-ARIMA/working/common/__init__.py similarity index 100% rename from 7-TimeSeries/2-ARIMA/working/common/__init__.py rename to Example project - Github_pages/7-TimeSeries/2-ARIMA/working/common/__init__.py diff --git a/7-TimeSeries/2-ARIMA/working/common/environment.yaml b/Example project - Github_pages/7-TimeSeries/2-ARIMA/working/common/environment.yaml similarity index 100% rename from 7-TimeSeries/2-ARIMA/working/common/environment.yaml rename to Example project - Github_pages/7-TimeSeries/2-ARIMA/working/common/environment.yaml diff --git a/7-TimeSeries/2-ARIMA/working/common/extract_data.py b/Example project - Github_pages/7-TimeSeries/2-ARIMA/working/common/extract_data.py similarity index 100% rename from 7-TimeSeries/2-ARIMA/working/common/extract_data.py rename to Example project - Github_pages/7-TimeSeries/2-ARIMA/working/common/extract_data.py diff --git a/7-TimeSeries/2-ARIMA/working/common/utils.py b/Example project - Github_pages/7-TimeSeries/2-ARIMA/working/common/utils.py similarity index 100% rename from 7-TimeSeries/2-ARIMA/working/common/utils.py rename to Example project - Github_pages/7-TimeSeries/2-ARIMA/working/common/utils.py diff --git a/7-TimeSeries/2-ARIMA/working/data/energy.csv b/Example project - Github_pages/7-TimeSeries/2-ARIMA/working/data/energy.csv similarity index 100% rename from 7-TimeSeries/2-ARIMA/working/data/energy.csv rename to Example project - Github_pages/7-TimeSeries/2-ARIMA/working/data/energy.csv diff --git a/7-TimeSeries/2-ARIMA/working/notebook.ipynb b/Example project - Github_pages/7-TimeSeries/2-ARIMA/working/notebook.ipynb similarity index 100% rename from 7-TimeSeries/2-ARIMA/working/notebook.ipynb rename to Example project - Github_pages/7-TimeSeries/2-ARIMA/working/notebook.ipynb diff --git a/7-TimeSeries/3-SVR/README.md b/Example project - Github_pages/7-TimeSeries/3-SVR/README.md similarity index 100% rename from 7-TimeSeries/3-SVR/README.md rename to Example project - Github_pages/7-TimeSeries/3-SVR/README.md diff --git a/7-TimeSeries/3-SVR/assignment.md b/Example project - Github_pages/7-TimeSeries/3-SVR/assignment.md similarity index 100% rename from 7-TimeSeries/3-SVR/assignment.md rename to Example project - Github_pages/7-TimeSeries/3-SVR/assignment.md diff --git a/7-TimeSeries/3-SVR/images/full-data-predict.png b/Example project - Github_pages/7-TimeSeries/3-SVR/images/full-data-predict.png similarity index 100% rename from 7-TimeSeries/3-SVR/images/full-data-predict.png rename to Example project - Github_pages/7-TimeSeries/3-SVR/images/full-data-predict.png diff --git a/7-TimeSeries/3-SVR/images/full-data.png b/Example project - Github_pages/7-TimeSeries/3-SVR/images/full-data.png similarity index 100% rename from 7-TimeSeries/3-SVR/images/full-data.png rename to Example project - Github_pages/7-TimeSeries/3-SVR/images/full-data.png diff --git a/7-TimeSeries/3-SVR/images/test-data-predict.png b/Example project - Github_pages/7-TimeSeries/3-SVR/images/test-data-predict.png similarity index 100% rename from 7-TimeSeries/3-SVR/images/test-data-predict.png rename to Example project - Github_pages/7-TimeSeries/3-SVR/images/test-data-predict.png diff --git a/7-TimeSeries/3-SVR/images/train-data-predict.png b/Example project - Github_pages/7-TimeSeries/3-SVR/images/train-data-predict.png similarity index 100% rename from 7-TimeSeries/3-SVR/images/train-data-predict.png rename to Example project - Github_pages/7-TimeSeries/3-SVR/images/train-data-predict.png diff --git a/7-TimeSeries/3-SVR/images/train-test.png b/Example project - Github_pages/7-TimeSeries/3-SVR/images/train-test.png similarity index 100% rename from 7-TimeSeries/3-SVR/images/train-test.png rename to Example project - Github_pages/7-TimeSeries/3-SVR/images/train-test.png diff --git a/7-TimeSeries/3-SVR/solution/notebook.ipynb b/Example project - Github_pages/7-TimeSeries/3-SVR/solution/notebook.ipynb similarity index 100% rename from 7-TimeSeries/3-SVR/solution/notebook.ipynb rename to Example project - Github_pages/7-TimeSeries/3-SVR/solution/notebook.ipynb diff --git a/7-TimeSeries/3-SVR/translations/README.md b/Example project - Github_pages/7-TimeSeries/3-SVR/translations/README.md similarity index 100% rename from 7-TimeSeries/3-SVR/translations/README.md rename to Example project - Github_pages/7-TimeSeries/3-SVR/translations/README.md diff --git a/7-TimeSeries/3-SVR/translations/assignment.es.md b/Example project - Github_pages/7-TimeSeries/3-SVR/translations/assignment.es.md similarity index 100% rename from 7-TimeSeries/3-SVR/translations/assignment.es.md rename to Example project - Github_pages/7-TimeSeries/3-SVR/translations/assignment.es.md diff --git a/7-TimeSeries/3-SVR/working/notebook.ipynb b/Example project - Github_pages/7-TimeSeries/3-SVR/working/notebook.ipynb similarity index 100% rename from 7-TimeSeries/3-SVR/working/notebook.ipynb rename to Example project - Github_pages/7-TimeSeries/3-SVR/working/notebook.ipynb diff --git a/7-TimeSeries/README.md b/Example project - Github_pages/7-TimeSeries/README.md similarity index 100% rename from 7-TimeSeries/README.md rename to Example project - Github_pages/7-TimeSeries/README.md diff --git a/7-TimeSeries/common/utils.py b/Example project - Github_pages/7-TimeSeries/common/utils.py similarity index 100% rename from 7-TimeSeries/common/utils.py rename to Example project - Github_pages/7-TimeSeries/common/utils.py diff --git a/7-TimeSeries/data/energy.csv b/Example project - Github_pages/7-TimeSeries/data/energy.csv similarity index 100% rename from 7-TimeSeries/data/energy.csv rename to Example project - Github_pages/7-TimeSeries/data/energy.csv diff --git a/7-TimeSeries/images/electric-grid.jpg b/Example project - Github_pages/7-TimeSeries/images/electric-grid.jpg similarity index 100% rename from 7-TimeSeries/images/electric-grid.jpg rename to Example project - Github_pages/7-TimeSeries/images/electric-grid.jpg diff --git a/7-TimeSeries/translations/README.es.md b/Example project - Github_pages/7-TimeSeries/translations/README.es.md similarity index 100% rename from 7-TimeSeries/translations/README.es.md rename to Example project - Github_pages/7-TimeSeries/translations/README.es.md diff --git a/7-TimeSeries/translations/README.fr.md b/Example project - Github_pages/7-TimeSeries/translations/README.fr.md similarity index 100% rename from 7-TimeSeries/translations/README.fr.md rename to Example project - Github_pages/7-TimeSeries/translations/README.fr.md diff --git a/7-TimeSeries/translations/README.hi.md b/Example project - Github_pages/7-TimeSeries/translations/README.hi.md similarity index 100% rename from 7-TimeSeries/translations/README.hi.md rename to Example project - Github_pages/7-TimeSeries/translations/README.hi.md diff --git a/7-TimeSeries/translations/README.it.md b/Example project - Github_pages/7-TimeSeries/translations/README.it.md similarity index 100% rename from 7-TimeSeries/translations/README.it.md rename to Example project - Github_pages/7-TimeSeries/translations/README.it.md diff --git a/7-TimeSeries/translations/README.ko.md b/Example project - Github_pages/7-TimeSeries/translations/README.ko.md similarity index 100% rename from 7-TimeSeries/translations/README.ko.md rename to Example project - Github_pages/7-TimeSeries/translations/README.ko.md diff --git a/7-TimeSeries/translations/README.ru.md b/Example project - Github_pages/7-TimeSeries/translations/README.ru.md similarity index 100% rename from 7-TimeSeries/translations/README.ru.md rename to Example project - Github_pages/7-TimeSeries/translations/README.ru.md diff --git a/7-TimeSeries/translations/README.zh-cn.md b/Example project - Github_pages/7-TimeSeries/translations/README.zh-cn.md similarity index 100% rename from 7-TimeSeries/translations/README.zh-cn.md rename to Example project - Github_pages/7-TimeSeries/translations/README.zh-cn.md diff --git a/8-Reinforcement/1-QLearning/README.md b/Example project - Github_pages/8-Reinforcement/1-QLearning/README.md similarity index 100% rename from 8-Reinforcement/1-QLearning/README.md rename to Example project - Github_pages/8-Reinforcement/1-QLearning/README.md diff --git a/8-Reinforcement/1-QLearning/assignment.md b/Example project - Github_pages/8-Reinforcement/1-QLearning/assignment.md similarity index 100% rename from 8-Reinforcement/1-QLearning/assignment.md rename to Example project - Github_pages/8-Reinforcement/1-QLearning/assignment.md diff --git a/8-Reinforcement/1-QLearning/images/apple.png b/Example project - Github_pages/8-Reinforcement/1-QLearning/images/apple.png similarity index 100% rename from 8-Reinforcement/1-QLearning/images/apple.png rename to Example project - Github_pages/8-Reinforcement/1-QLearning/images/apple.png diff --git a/8-Reinforcement/1-QLearning/images/bellman-equation.png b/Example project - Github_pages/8-Reinforcement/1-QLearning/images/bellman-equation.png similarity index 100% rename from 8-Reinforcement/1-QLearning/images/bellman-equation.png rename to Example project - Github_pages/8-Reinforcement/1-QLearning/images/bellman-equation.png diff --git a/8-Reinforcement/1-QLearning/images/bellmaneq.gif b/Example project - Github_pages/8-Reinforcement/1-QLearning/images/bellmaneq.gif similarity index 100% rename from 8-Reinforcement/1-QLearning/images/bellmaneq.gif rename to Example project - Github_pages/8-Reinforcement/1-QLearning/images/bellmaneq.gif diff --git a/8-Reinforcement/1-QLearning/images/env_init.png b/Example project - Github_pages/8-Reinforcement/1-QLearning/images/env_init.png similarity index 100% rename from 8-Reinforcement/1-QLearning/images/env_init.png rename to Example project - Github_pages/8-Reinforcement/1-QLearning/images/env_init.png diff --git a/8-Reinforcement/1-QLearning/images/environment.png b/Example project - Github_pages/8-Reinforcement/1-QLearning/images/environment.png similarity index 100% rename from 8-Reinforcement/1-QLearning/images/environment.png rename to Example project - Github_pages/8-Reinforcement/1-QLearning/images/environment.png diff --git a/8-Reinforcement/1-QLearning/images/human.png b/Example project - Github_pages/8-Reinforcement/1-QLearning/images/human.png similarity index 100% rename from 8-Reinforcement/1-QLearning/images/human.png rename to Example project - Github_pages/8-Reinforcement/1-QLearning/images/human.png diff --git a/8-Reinforcement/1-QLearning/images/learned.png b/Example project - Github_pages/8-Reinforcement/1-QLearning/images/learned.png similarity index 100% rename from 8-Reinforcement/1-QLearning/images/learned.png rename to Example project - Github_pages/8-Reinforcement/1-QLearning/images/learned.png diff --git a/8-Reinforcement/1-QLearning/images/lpathlen.png b/Example project - Github_pages/8-Reinforcement/1-QLearning/images/lpathlen.png similarity index 100% rename from 8-Reinforcement/1-QLearning/images/lpathlen.png rename to Example project - Github_pages/8-Reinforcement/1-QLearning/images/lpathlen.png diff --git a/8-Reinforcement/1-QLearning/images/lpathlen1.png b/Example project - Github_pages/8-Reinforcement/1-QLearning/images/lpathlen1.png similarity index 100% rename from 8-Reinforcement/1-QLearning/images/lpathlen1.png rename to Example project - Github_pages/8-Reinforcement/1-QLearning/images/lpathlen1.png diff --git a/8-Reinforcement/1-QLearning/images/qwalk.gif b/Example project - Github_pages/8-Reinforcement/1-QLearning/images/qwalk.gif similarity index 100% rename from 8-Reinforcement/1-QLearning/images/qwalk.gif rename to Example project - Github_pages/8-Reinforcement/1-QLearning/images/qwalk.gif diff --git a/8-Reinforcement/1-QLearning/images/random_walk.gif b/Example project - Github_pages/8-Reinforcement/1-QLearning/images/random_walk.gif similarity index 100% rename from 8-Reinforcement/1-QLearning/images/random_walk.gif rename to Example project - Github_pages/8-Reinforcement/1-QLearning/images/random_walk.gif diff --git a/8-Reinforcement/1-QLearning/images/wolf.png b/Example project - Github_pages/8-Reinforcement/1-QLearning/images/wolf.png similarity index 100% rename from 8-Reinforcement/1-QLearning/images/wolf.png rename to Example project - Github_pages/8-Reinforcement/1-QLearning/images/wolf.png diff --git a/8-Reinforcement/1-QLearning/notebook.ipynb b/Example project - Github_pages/8-Reinforcement/1-QLearning/notebook.ipynb similarity index 100% rename from 8-Reinforcement/1-QLearning/notebook.ipynb rename to Example project - Github_pages/8-Reinforcement/1-QLearning/notebook.ipynb diff --git a/8-Reinforcement/1-QLearning/rlboard.py b/Example project - Github_pages/8-Reinforcement/1-QLearning/rlboard.py similarity index 100% rename from 8-Reinforcement/1-QLearning/rlboard.py rename to Example project - Github_pages/8-Reinforcement/1-QLearning/rlboard.py diff --git a/8-Reinforcement/1-QLearning/solution/Julia/README.md b/Example project - Github_pages/8-Reinforcement/1-QLearning/solution/Julia/README.md similarity index 100% rename from 8-Reinforcement/1-QLearning/solution/Julia/README.md rename to Example project - Github_pages/8-Reinforcement/1-QLearning/solution/Julia/README.md diff --git a/8-Reinforcement/1-QLearning/solution/R/README.md b/Example project - Github_pages/8-Reinforcement/1-QLearning/solution/R/README.md similarity index 100% rename from 8-Reinforcement/1-QLearning/solution/R/README.md rename to Example project - Github_pages/8-Reinforcement/1-QLearning/solution/R/README.md diff --git a/8-Reinforcement/1-QLearning/solution/assignment-solution.ipynb b/Example project - Github_pages/8-Reinforcement/1-QLearning/solution/assignment-solution.ipynb similarity index 100% rename from 8-Reinforcement/1-QLearning/solution/assignment-solution.ipynb rename to Example project - Github_pages/8-Reinforcement/1-QLearning/solution/assignment-solution.ipynb diff --git a/8-Reinforcement/1-QLearning/solution/notebook.ipynb b/Example project - Github_pages/8-Reinforcement/1-QLearning/solution/notebook.ipynb similarity index 100% rename from 8-Reinforcement/1-QLearning/solution/notebook.ipynb rename to Example project - Github_pages/8-Reinforcement/1-QLearning/solution/notebook.ipynb diff --git a/8-Reinforcement/1-QLearning/solution/rlboard.py b/Example project - Github_pages/8-Reinforcement/1-QLearning/solution/rlboard.py similarity index 100% rename from 8-Reinforcement/1-QLearning/solution/rlboard.py rename to Example project - Github_pages/8-Reinforcement/1-QLearning/solution/rlboard.py diff --git a/8-Reinforcement/1-QLearning/translations/README.it.md b/Example project - Github_pages/8-Reinforcement/1-QLearning/translations/README.it.md similarity index 100% rename from 8-Reinforcement/1-QLearning/translations/README.it.md rename to Example project - Github_pages/8-Reinforcement/1-QLearning/translations/README.it.md diff --git a/8-Reinforcement/1-QLearning/translations/README.ko.md b/Example project - Github_pages/8-Reinforcement/1-QLearning/translations/README.ko.md similarity index 100% rename from 8-Reinforcement/1-QLearning/translations/README.ko.md rename to Example project - Github_pages/8-Reinforcement/1-QLearning/translations/README.ko.md diff --git a/8-Reinforcement/1-QLearning/translations/README.zh-cn.md b/Example project - Github_pages/8-Reinforcement/1-QLearning/translations/README.zh-cn.md similarity index 100% rename from 8-Reinforcement/1-QLearning/translations/README.zh-cn.md rename to Example project - Github_pages/8-Reinforcement/1-QLearning/translations/README.zh-cn.md diff --git a/8-Reinforcement/1-QLearning/translations/assignment.es.md b/Example project - Github_pages/8-Reinforcement/1-QLearning/translations/assignment.es.md similarity index 100% rename from 8-Reinforcement/1-QLearning/translations/assignment.es.md rename to Example project - Github_pages/8-Reinforcement/1-QLearning/translations/assignment.es.md diff --git a/8-Reinforcement/1-QLearning/translations/assignment.it.md b/Example project - Github_pages/8-Reinforcement/1-QLearning/translations/assignment.it.md similarity index 100% rename from 8-Reinforcement/1-QLearning/translations/assignment.it.md rename to Example project - Github_pages/8-Reinforcement/1-QLearning/translations/assignment.it.md diff --git a/8-Reinforcement/1-QLearning/translations/assignment.ko.md b/Example project - Github_pages/8-Reinforcement/1-QLearning/translations/assignment.ko.md similarity index 100% rename from 8-Reinforcement/1-QLearning/translations/assignment.ko.md rename to Example project - Github_pages/8-Reinforcement/1-QLearning/translations/assignment.ko.md diff --git a/8-Reinforcement/1-QLearning/translations/assignment.zh-cn.md b/Example project - Github_pages/8-Reinforcement/1-QLearning/translations/assignment.zh-cn.md similarity index 100% rename from 8-Reinforcement/1-QLearning/translations/assignment.zh-cn.md rename to Example project - Github_pages/8-Reinforcement/1-QLearning/translations/assignment.zh-cn.md diff --git a/8-Reinforcement/2-Gym/README.md b/Example project - Github_pages/8-Reinforcement/2-Gym/README.md similarity index 100% rename from 8-Reinforcement/2-Gym/README.md rename to Example project - Github_pages/8-Reinforcement/2-Gym/README.md diff --git a/8-Reinforcement/2-Gym/assignment.md b/Example project - Github_pages/8-Reinforcement/2-Gym/assignment.md similarity index 100% rename from 8-Reinforcement/2-Gym/assignment.md rename to Example project - Github_pages/8-Reinforcement/2-Gym/assignment.md diff --git a/8-Reinforcement/2-Gym/images/cartpole-balance.gif b/Example project - Github_pages/8-Reinforcement/2-Gym/images/cartpole-balance.gif similarity index 100% rename from 8-Reinforcement/2-Gym/images/cartpole-balance.gif rename to Example project - Github_pages/8-Reinforcement/2-Gym/images/cartpole-balance.gif diff --git a/8-Reinforcement/2-Gym/images/cartpole-nobalance.gif b/Example project - Github_pages/8-Reinforcement/2-Gym/images/cartpole-nobalance.gif similarity index 100% rename from 8-Reinforcement/2-Gym/images/cartpole-nobalance.gif rename to Example project - Github_pages/8-Reinforcement/2-Gym/images/cartpole-nobalance.gif diff --git a/8-Reinforcement/2-Gym/images/cartpole.png b/Example project - Github_pages/8-Reinforcement/2-Gym/images/cartpole.png similarity index 100% rename from 8-Reinforcement/2-Gym/images/cartpole.png rename to Example project - Github_pages/8-Reinforcement/2-Gym/images/cartpole.png diff --git a/8-Reinforcement/2-Gym/images/escape.png b/Example project - Github_pages/8-Reinforcement/2-Gym/images/escape.png similarity index 100% rename from 8-Reinforcement/2-Gym/images/escape.png rename to Example project - Github_pages/8-Reinforcement/2-Gym/images/escape.png diff --git a/8-Reinforcement/2-Gym/images/mountaincar.png b/Example project - Github_pages/8-Reinforcement/2-Gym/images/mountaincar.png similarity index 100% rename from 8-Reinforcement/2-Gym/images/mountaincar.png rename to Example project - Github_pages/8-Reinforcement/2-Gym/images/mountaincar.png diff --git a/8-Reinforcement/2-Gym/images/train_progress_raw.png b/Example project - Github_pages/8-Reinforcement/2-Gym/images/train_progress_raw.png similarity index 100% rename from 8-Reinforcement/2-Gym/images/train_progress_raw.png rename to Example project - Github_pages/8-Reinforcement/2-Gym/images/train_progress_raw.png diff --git a/8-Reinforcement/2-Gym/images/train_progress_runav.png b/Example project - Github_pages/8-Reinforcement/2-Gym/images/train_progress_runav.png similarity index 100% rename from 8-Reinforcement/2-Gym/images/train_progress_runav.png rename to Example project - Github_pages/8-Reinforcement/2-Gym/images/train_progress_runav.png diff --git a/8-Reinforcement/2-Gym/notebook.ipynb b/Example project - Github_pages/8-Reinforcement/2-Gym/notebook.ipynb similarity index 100% rename from 8-Reinforcement/2-Gym/notebook.ipynb rename to Example project - Github_pages/8-Reinforcement/2-Gym/notebook.ipynb diff --git a/8-Reinforcement/2-Gym/solution/Julia/README.md b/Example project - Github_pages/8-Reinforcement/2-Gym/solution/Julia/README.md similarity index 100% rename from 8-Reinforcement/2-Gym/solution/Julia/README.md rename to Example project - Github_pages/8-Reinforcement/2-Gym/solution/Julia/README.md diff --git a/8-Reinforcement/2-Gym/solution/R/README.md b/Example project - Github_pages/8-Reinforcement/2-Gym/solution/R/README.md similarity index 100% rename from 8-Reinforcement/2-Gym/solution/R/README.md rename to Example project - Github_pages/8-Reinforcement/2-Gym/solution/R/README.md diff --git a/8-Reinforcement/2-Gym/solution/notebook.ipynb b/Example project - Github_pages/8-Reinforcement/2-Gym/solution/notebook.ipynb similarity index 100% rename from 8-Reinforcement/2-Gym/solution/notebook.ipynb rename to Example project - Github_pages/8-Reinforcement/2-Gym/solution/notebook.ipynb diff --git a/8-Reinforcement/2-Gym/translations/README.it.md b/Example project - Github_pages/8-Reinforcement/2-Gym/translations/README.it.md similarity index 100% rename from 8-Reinforcement/2-Gym/translations/README.it.md rename to Example project - Github_pages/8-Reinforcement/2-Gym/translations/README.it.md diff --git a/8-Reinforcement/2-Gym/translations/README.ko.md b/Example project - Github_pages/8-Reinforcement/2-Gym/translations/README.ko.md similarity index 100% rename from 8-Reinforcement/2-Gym/translations/README.ko.md rename to Example project - Github_pages/8-Reinforcement/2-Gym/translations/README.ko.md diff --git a/8-Reinforcement/2-Gym/translations/README.zh-cn.md b/Example project - Github_pages/8-Reinforcement/2-Gym/translations/README.zh-cn.md similarity index 100% rename from 8-Reinforcement/2-Gym/translations/README.zh-cn.md rename to Example project - Github_pages/8-Reinforcement/2-Gym/translations/README.zh-cn.md diff --git a/8-Reinforcement/2-Gym/translations/assignment.es.md b/Example project - Github_pages/8-Reinforcement/2-Gym/translations/assignment.es.md similarity index 100% rename from 8-Reinforcement/2-Gym/translations/assignment.es.md rename to Example project - Github_pages/8-Reinforcement/2-Gym/translations/assignment.es.md diff --git a/8-Reinforcement/2-Gym/translations/assignment.it.md b/Example project - Github_pages/8-Reinforcement/2-Gym/translations/assignment.it.md similarity index 100% rename from 8-Reinforcement/2-Gym/translations/assignment.it.md rename to Example project - Github_pages/8-Reinforcement/2-Gym/translations/assignment.it.md diff --git a/8-Reinforcement/2-Gym/translations/assignment.ko.md b/Example project - Github_pages/8-Reinforcement/2-Gym/translations/assignment.ko.md similarity index 100% rename from 8-Reinforcement/2-Gym/translations/assignment.ko.md rename to Example project - Github_pages/8-Reinforcement/2-Gym/translations/assignment.ko.md diff --git a/8-Reinforcement/2-Gym/translations/assignment.zh-cn.md b/Example project - Github_pages/8-Reinforcement/2-Gym/translations/assignment.zh-cn.md similarity index 100% rename from 8-Reinforcement/2-Gym/translations/assignment.zh-cn.md rename to Example project - Github_pages/8-Reinforcement/2-Gym/translations/assignment.zh-cn.md diff --git a/8-Reinforcement/README.md b/Example project - Github_pages/8-Reinforcement/README.md similarity index 100% rename from 8-Reinforcement/README.md rename to Example project - Github_pages/8-Reinforcement/README.md diff --git a/8-Reinforcement/images/peter.png b/Example project - Github_pages/8-Reinforcement/images/peter.png similarity index 100% rename from 8-Reinforcement/images/peter.png rename to Example project - Github_pages/8-Reinforcement/images/peter.png diff --git a/8-Reinforcement/translations/README.it.md b/Example project - Github_pages/8-Reinforcement/translations/README.it.md similarity index 100% rename from 8-Reinforcement/translations/README.it.md rename to Example project - Github_pages/8-Reinforcement/translations/README.it.md diff --git a/8-Reinforcement/translations/README.ko.md b/Example project - Github_pages/8-Reinforcement/translations/README.ko.md similarity index 100% rename from 8-Reinforcement/translations/README.ko.md rename to Example project - Github_pages/8-Reinforcement/translations/README.ko.md diff --git a/8-Reinforcement/translations/README.ru.md b/Example project - Github_pages/8-Reinforcement/translations/README.ru.md similarity index 100% rename from 8-Reinforcement/translations/README.ru.md rename to Example project - Github_pages/8-Reinforcement/translations/README.ru.md diff --git a/8-Reinforcement/translations/README.tr.md b/Example project - Github_pages/8-Reinforcement/translations/README.tr.md similarity index 100% rename from 8-Reinforcement/translations/README.tr.md rename to Example project - Github_pages/8-Reinforcement/translations/README.tr.md diff --git a/8-Reinforcement/translations/README.zh-cn.md b/Example project - Github_pages/8-Reinforcement/translations/README.zh-cn.md similarity index 100% rename from 8-Reinforcement/translations/README.zh-cn.md rename to Example project - Github_pages/8-Reinforcement/translations/README.zh-cn.md diff --git a/9-Real-World/1-Applications/README.md b/Example project - Github_pages/9-Real-World/1-Applications/README.md similarity index 100% rename from 9-Real-World/1-Applications/README.md rename to Example project - Github_pages/9-Real-World/1-Applications/README.md diff --git a/9-Real-World/1-Applications/assignment.md b/Example project - Github_pages/9-Real-World/1-Applications/assignment.md similarity index 100% rename from 9-Real-World/1-Applications/assignment.md rename to Example project - Github_pages/9-Real-World/1-Applications/assignment.md diff --git a/9-Real-World/1-Applications/translations/README.it.md b/Example project - Github_pages/9-Real-World/1-Applications/translations/README.it.md similarity index 100% rename from 9-Real-World/1-Applications/translations/README.it.md rename to Example project - Github_pages/9-Real-World/1-Applications/translations/README.it.md diff --git a/9-Real-World/1-Applications/translations/README.ko.md b/Example project - Github_pages/9-Real-World/1-Applications/translations/README.ko.md similarity index 100% rename from 9-Real-World/1-Applications/translations/README.ko.md rename to Example project - Github_pages/9-Real-World/1-Applications/translations/README.ko.md diff --git a/9-Real-World/1-Applications/translations/assignment.es.md b/Example project - Github_pages/9-Real-World/1-Applications/translations/assignment.es.md similarity index 100% rename from 9-Real-World/1-Applications/translations/assignment.es.md rename to Example project - Github_pages/9-Real-World/1-Applications/translations/assignment.es.md diff --git a/9-Real-World/1-Applications/translations/assignment.it.md b/Example project - Github_pages/9-Real-World/1-Applications/translations/assignment.it.md similarity index 100% rename from 9-Real-World/1-Applications/translations/assignment.it.md rename to Example project - Github_pages/9-Real-World/1-Applications/translations/assignment.it.md diff --git a/9-Real-World/1-Applications/translations/assignment.ko.md b/Example project - Github_pages/9-Real-World/1-Applications/translations/assignment.ko.md similarity index 100% rename from 9-Real-World/1-Applications/translations/assignment.ko.md rename to Example project - Github_pages/9-Real-World/1-Applications/translations/assignment.ko.md diff --git a/9-Real-World/2-Debugging-ML-Models/README.md b/Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/README.md similarity index 100% rename from 9-Real-World/2-Debugging-ML-Models/README.md rename to Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/README.md diff --git a/9-Real-World/2-Debugging-ML-Models/assignment.md b/Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/assignment.md similarity index 100% rename from 9-Real-World/2-Debugging-ML-Models/assignment.md rename to Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/assignment.md diff --git a/9-Real-World/2-Debugging-ML-Models/images/9-feature-importance.png b/Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/images/9-feature-importance.png similarity index 100% rename from 9-Real-World/2-Debugging-ML-Models/images/9-feature-importance.png rename to Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/images/9-feature-importance.png diff --git a/9-Real-World/2-Debugging-ML-Models/images/9-features-influence.png b/Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/images/9-features-influence.png similarity index 100% rename from 9-Real-World/2-Debugging-ML-Models/images/9-features-influence.png rename to Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/images/9-features-influence.png diff --git a/1-Introduction/3-fairness/images/ceos.png b/Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/images/ceos.png similarity index 100% rename from 1-Introduction/3-fairness/images/ceos.png rename to Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/images/ceos.png diff --git a/9-Real-World/2-Debugging-ML-Models/images/cf-what-if-features.png b/Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/images/cf-what-if-features.png similarity index 100% rename from 9-Real-World/2-Debugging-ML-Models/images/cf-what-if-features.png rename to Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/images/cf-what-if-features.png diff --git a/9-Real-World/2-Debugging-ML-Models/images/counterfactuals-examples.png b/Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/images/counterfactuals-examples.png similarity index 100% rename from 9-Real-World/2-Debugging-ML-Models/images/counterfactuals-examples.png rename to Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/images/counterfactuals-examples.png diff --git a/9-Real-World/2-Debugging-ML-Models/images/dataanalysis-cover.png b/Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/images/dataanalysis-cover.png similarity index 100% rename from 9-Real-World/2-Debugging-ML-Models/images/dataanalysis-cover.png rename to Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/images/dataanalysis-cover.png diff --git a/9-Real-World/2-Debugging-ML-Models/images/datapoints.png b/Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/images/datapoints.png similarity index 100% rename from 9-Real-World/2-Debugging-ML-Models/images/datapoints.png rename to Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/images/datapoints.png diff --git a/9-Real-World/2-Debugging-ML-Models/images/ea-error-cohort.png b/Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/images/ea-error-cohort.png similarity index 100% rename from 9-Real-World/2-Debugging-ML-Models/images/ea-error-cohort.png rename to Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/images/ea-error-cohort.png diff --git a/9-Real-World/2-Debugging-ML-Models/images/ea-error-distribution.png b/Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/images/ea-error-distribution.png similarity index 100% rename from 9-Real-World/2-Debugging-ML-Models/images/ea-error-distribution.png rename to Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/images/ea-error-distribution.png diff --git a/9-Real-World/2-Debugging-ML-Models/images/ea-heatmap.png b/Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/images/ea-heatmap.png similarity index 100% rename from 9-Real-World/2-Debugging-ML-Models/images/ea-heatmap.png rename to Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/images/ea-heatmap.png diff --git a/1-Introduction/3-fairness/images/fairness.png b/Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/images/fairness.png similarity index 100% rename from 1-Introduction/3-fairness/images/fairness.png rename to Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/images/fairness.png diff --git a/1-Introduction/3-fairness/images/gender-bias-translate-en-tr.png b/Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/images/gender-bias-translate-en-tr.png similarity index 100% rename from 1-Introduction/3-fairness/images/gender-bias-translate-en-tr.png rename to Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/images/gender-bias-translate-en-tr.png diff --git a/1-Introduction/3-fairness/images/gender-bias-translate-tr-en.png b/Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/images/gender-bias-translate-tr-en.png similarity index 100% rename from 1-Introduction/3-fairness/images/gender-bias-translate-tr-en.png rename to Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/images/gender-bias-translate-tr-en.png diff --git a/9-Real-World/2-Debugging-ML-Models/images/individual-causal-what-if.png b/Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/images/individual-causal-what-if.png similarity index 100% rename from 9-Real-World/2-Debugging-ML-Models/images/individual-causal-what-if.png rename to Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/images/individual-causal-what-if.png diff --git a/9-Real-World/2-Debugging-ML-Models/images/model-overview-dataset-cohorts.png b/Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/images/model-overview-dataset-cohorts.png similarity index 100% rename from 9-Real-World/2-Debugging-ML-Models/images/model-overview-dataset-cohorts.png rename to Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/images/model-overview-dataset-cohorts.png diff --git a/9-Real-World/2-Debugging-ML-Models/images/model-overview-feature-cohorts.png b/Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/images/model-overview-feature-cohorts.png similarity index 100% rename from 9-Real-World/2-Debugging-ML-Models/images/model-overview-feature-cohorts.png rename to Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/images/model-overview-feature-cohorts.png diff --git a/9-Real-World/2-Debugging-ML-Models/images/rai-overview.gif b/Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/images/rai-overview.gif similarity index 100% rename from 9-Real-World/2-Debugging-ML-Models/images/rai-overview.gif rename to Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/images/rai-overview.gif diff --git a/1-Introduction/3-fairness/translations/README.es.md b/Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/translations/README.es.md similarity index 100% rename from 1-Introduction/3-fairness/translations/README.es.md rename to Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/translations/README.es.md diff --git a/1-Introduction/3-fairness/translations/README.fr.md b/Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/translations/README.fr.md similarity index 100% rename from 1-Introduction/3-fairness/translations/README.fr.md rename to Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/translations/README.fr.md diff --git a/1-Introduction/3-fairness/translations/README.id.md b/Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/translations/README.id.md similarity index 100% rename from 1-Introduction/3-fairness/translations/README.id.md rename to Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/translations/README.id.md diff --git a/1-Introduction/3-fairness/translations/README.it.md b/Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/translations/README.it.md similarity index 100% rename from 1-Introduction/3-fairness/translations/README.it.md rename to Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/translations/README.it.md diff --git a/1-Introduction/3-fairness/translations/README.ja.md b/Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/translations/README.ja.md similarity index 100% rename from 1-Introduction/3-fairness/translations/README.ja.md rename to Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/translations/README.ja.md diff --git a/1-Introduction/3-fairness/translations/README.ko.md b/Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/translations/README.ko.md similarity index 100% rename from 1-Introduction/3-fairness/translations/README.ko.md rename to Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/translations/README.ko.md diff --git a/1-Introduction/3-fairness/translations/README.pt-br.md b/Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/translations/README.pt-br.md similarity index 100% rename from 1-Introduction/3-fairness/translations/README.pt-br.md rename to Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/translations/README.pt-br.md diff --git a/1-Introduction/3-fairness/translations/README.zh-cn.md b/Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/translations/README.zh-cn.md similarity index 100% rename from 1-Introduction/3-fairness/translations/README.zh-cn.md rename to Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/translations/README.zh-cn.md diff --git a/1-Introduction/3-fairness/translations/README.zh-tw.md b/Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/translations/README.zh-tw.md similarity index 100% rename from 1-Introduction/3-fairness/translations/README.zh-tw.md rename to Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/translations/README.zh-tw.md diff --git a/9-Real-World/2-Debugging-ML-Models/translations/assignment.es.md b/Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/translations/assignment.es.md similarity index 100% rename from 9-Real-World/2-Debugging-ML-Models/translations/assignment.es.md rename to Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/translations/assignment.es.md diff --git a/1-Introduction/3-fairness/translations/assignment.fr.md b/Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/translations/assignment.fr.md similarity index 100% rename from 1-Introduction/3-fairness/translations/assignment.fr.md rename to Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/translations/assignment.fr.md diff --git a/1-Introduction/3-fairness/translations/assignment.id.md b/Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/translations/assignment.id.md similarity index 100% rename from 1-Introduction/3-fairness/translations/assignment.id.md rename to Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/translations/assignment.id.md diff --git a/1-Introduction/3-fairness/translations/assignment.it.md b/Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/translations/assignment.it.md similarity index 100% rename from 1-Introduction/3-fairness/translations/assignment.it.md rename to Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/translations/assignment.it.md diff --git a/1-Introduction/3-fairness/translations/assignment.ja.md b/Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/translations/assignment.ja.md similarity index 100% rename from 1-Introduction/3-fairness/translations/assignment.ja.md rename to Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/translations/assignment.ja.md diff --git a/1-Introduction/3-fairness/translations/assignment.ko.md b/Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/translations/assignment.ko.md similarity index 100% rename from 1-Introduction/3-fairness/translations/assignment.ko.md rename to Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/translations/assignment.ko.md diff --git a/1-Introduction/3-fairness/translations/assignment.pt-br.md b/Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/translations/assignment.pt-br.md similarity index 100% rename from 1-Introduction/3-fairness/translations/assignment.pt-br.md rename to Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/translations/assignment.pt-br.md diff --git a/1-Introduction/3-fairness/translations/assignment.zh-cn.md b/Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/translations/assignment.zh-cn.md similarity index 100% rename from 1-Introduction/3-fairness/translations/assignment.zh-cn.md rename to Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/translations/assignment.zh-cn.md diff --git a/1-Introduction/3-fairness/translations/assignment.zh-tw.md b/Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/translations/assignment.zh-tw.md similarity index 100% rename from 1-Introduction/3-fairness/translations/assignment.zh-tw.md rename to Example project - Github_pages/9-Real-World/2-Debugging-ML-Models/translations/assignment.zh-tw.md diff --git a/9-Real-World/README.md b/Example project - Github_pages/9-Real-World/README.md similarity index 100% rename from 9-Real-World/README.md rename to Example project - Github_pages/9-Real-World/README.md diff --git a/9-Real-World/images/chess.jpg b/Example project - Github_pages/9-Real-World/images/chess.jpg similarity index 100% rename from 9-Real-World/images/chess.jpg rename to Example project - Github_pages/9-Real-World/images/chess.jpg diff --git a/9-Real-World/translations/README.es.md b/Example project - Github_pages/9-Real-World/translations/README.es.md similarity index 100% rename from 9-Real-World/translations/README.es.md rename to Example project - Github_pages/9-Real-World/translations/README.es.md diff --git a/9-Real-World/translations/README.fr.md b/Example project - Github_pages/9-Real-World/translations/README.fr.md similarity index 100% rename from 9-Real-World/translations/README.fr.md rename to Example project - Github_pages/9-Real-World/translations/README.fr.md diff --git a/9-Real-World/translations/README.hi.md b/Example project - Github_pages/9-Real-World/translations/README.hi.md similarity index 100% rename from 9-Real-World/translations/README.hi.md rename to Example project - Github_pages/9-Real-World/translations/README.hi.md diff --git a/9-Real-World/translations/README.it.md b/Example project - Github_pages/9-Real-World/translations/README.it.md similarity index 100% rename from 9-Real-World/translations/README.it.md rename to Example project - Github_pages/9-Real-World/translations/README.it.md diff --git a/9-Real-World/translations/README.ko.md b/Example project - Github_pages/9-Real-World/translations/README.ko.md similarity index 100% rename from 9-Real-World/translations/README.ko.md rename to Example project - Github_pages/9-Real-World/translations/README.ko.md diff --git a/9-Real-World/translations/README.pt.md b/Example project - Github_pages/9-Real-World/translations/README.pt.md similarity index 100% rename from 9-Real-World/translations/README.pt.md rename to Example project - Github_pages/9-Real-World/translations/README.pt.md diff --git a/9-Real-World/translations/README.ru.md b/Example project - Github_pages/9-Real-World/translations/README.ru.md similarity index 100% rename from 9-Real-World/translations/README.ru.md rename to Example project - Github_pages/9-Real-World/translations/README.ru.md diff --git a/9-Real-World/translations/README.tr.md b/Example project - Github_pages/9-Real-World/translations/README.tr.md similarity index 100% rename from 9-Real-World/translations/README.tr.md rename to Example project - Github_pages/9-Real-World/translations/README.tr.md diff --git a/9-Real-World/translations/README.zh-cn.md b/Example project - Github_pages/9-Real-World/translations/README.zh-cn.md similarity index 100% rename from 9-Real-World/translations/README.zh-cn.md rename to Example project - Github_pages/9-Real-World/translations/README.zh-cn.md diff --git a/CONTRIBUTING.md b/Example project - Github_pages/CONTRIBUTING.md similarity index 100% rename from CONTRIBUTING.md rename to Example project - Github_pages/CONTRIBUTING.md diff --git a/docs/_sidebar.md b/Example project - Github_pages/docs/_sidebar.md similarity index 100% rename from docs/_sidebar.md rename to Example project - Github_pages/docs/_sidebar.md diff --git a/for-teachers.md b/Example project - Github_pages/for-teachers.md similarity index 100% rename from for-teachers.md rename to Example project - Github_pages/for-teachers.md diff --git a/images/favicon.png b/Example project - Github_pages/images/favicon.png similarity index 100% rename from images/favicon.png rename to Example project - Github_pages/images/favicon.png diff --git a/ml-for-beginners-video-banner.png b/Example project - Github_pages/ml-for-beginners-video-banner.png similarity index 100% rename from ml-for-beginners-video-banner.png rename to Example project - Github_pages/ml-for-beginners-video-banner.png diff --git a/ml-for-beginners.png b/Example project - Github_pages/ml-for-beginners.png similarity index 100% rename from ml-for-beginners.png rename to Example project - Github_pages/ml-for-beginners.png diff --git a/ml.gif b/Example project - Github_pages/ml.gif similarity index 100% rename from ml.gif rename to Example project - Github_pages/ml.gif diff --git a/pdf/readme.pdf b/Example project - Github_pages/pdf/readme.pdf similarity index 100% rename from pdf/readme.pdf rename to Example project - Github_pages/pdf/readme.pdf diff --git a/quiz-app/.gitignore b/Example project - Github_pages/quiz-app/.gitignore similarity index 100% rename from quiz-app/.gitignore rename to Example project - Github_pages/quiz-app/.gitignore diff --git a/quiz-app/LICENSE b/Example project - Github_pages/quiz-app/LICENSE similarity index 100% rename from quiz-app/LICENSE rename to Example project - Github_pages/quiz-app/LICENSE diff --git a/quiz-app/README.md b/Example project - Github_pages/quiz-app/README.md similarity index 100% rename from quiz-app/README.md rename to Example project - Github_pages/quiz-app/README.md diff --git a/quiz-app/babel.config.js b/Example project - Github_pages/quiz-app/babel.config.js similarity index 100% rename from quiz-app/babel.config.js rename to Example project - Github_pages/quiz-app/babel.config.js diff --git a/quiz-app/package-lock.json b/Example project - Github_pages/quiz-app/package-lock.json similarity index 100% rename from quiz-app/package-lock.json rename to Example project - Github_pages/quiz-app/package-lock.json diff --git a/quiz-app/package.json b/Example project - Github_pages/quiz-app/package.json similarity index 100% rename from quiz-app/package.json rename to Example project - Github_pages/quiz-app/package.json diff --git a/quiz-app/public/favicon.ico b/Example project - Github_pages/quiz-app/public/favicon.ico similarity index 100% rename from quiz-app/public/favicon.ico rename to Example project - Github_pages/quiz-app/public/favicon.ico diff --git a/quiz-app/public/index.html b/Example project - Github_pages/quiz-app/public/index.html similarity index 100% rename from quiz-app/public/index.html rename to Example project - Github_pages/quiz-app/public/index.html diff --git a/quiz-app/public/routes.json b/Example project - Github_pages/quiz-app/public/routes.json similarity index 100% rename from quiz-app/public/routes.json rename to Example project - Github_pages/quiz-app/public/routes.json diff --git a/quiz-app/src/App.vue b/Example project - Github_pages/quiz-app/src/App.vue similarity index 100% rename from quiz-app/src/App.vue rename to Example project - Github_pages/quiz-app/src/App.vue diff --git a/quiz-app/src/assets/translations/en.json b/Example project - Github_pages/quiz-app/src/assets/translations/en.json similarity index 100% rename from quiz-app/src/assets/translations/en.json rename to Example project - Github_pages/quiz-app/src/assets/translations/en.json diff --git a/quiz-app/src/assets/translations/es.json b/Example project - Github_pages/quiz-app/src/assets/translations/es.json similarity index 100% rename from quiz-app/src/assets/translations/es.json rename to Example project - Github_pages/quiz-app/src/assets/translations/es.json diff --git a/quiz-app/src/assets/translations/fr.json b/Example project - Github_pages/quiz-app/src/assets/translations/fr.json similarity index 100% rename from quiz-app/src/assets/translations/fr.json rename to Example project - Github_pages/quiz-app/src/assets/translations/fr.json diff --git a/quiz-app/src/assets/translations/index.js b/Example project - Github_pages/quiz-app/src/assets/translations/index.js similarity index 100% rename from quiz-app/src/assets/translations/index.js rename to Example project - Github_pages/quiz-app/src/assets/translations/index.js diff --git a/quiz-app/src/assets/translations/it.json b/Example project - Github_pages/quiz-app/src/assets/translations/it.json similarity index 100% rename from quiz-app/src/assets/translations/it.json rename to Example project - Github_pages/quiz-app/src/assets/translations/it.json diff --git a/quiz-app/src/assets/translations/ja.json b/Example project - Github_pages/quiz-app/src/assets/translations/ja.json similarity index 100% rename from quiz-app/src/assets/translations/ja.json rename to Example project - Github_pages/quiz-app/src/assets/translations/ja.json diff --git a/quiz-app/src/assets/translations/ptbr.json b/Example project - Github_pages/quiz-app/src/assets/translations/ptbr.json similarity index 100% rename from quiz-app/src/assets/translations/ptbr.json rename to Example project - Github_pages/quiz-app/src/assets/translations/ptbr.json diff --git a/quiz-app/src/assets/translations/tr.json b/Example project - Github_pages/quiz-app/src/assets/translations/tr.json similarity index 100% rename from quiz-app/src/assets/translations/tr.json rename to Example project - Github_pages/quiz-app/src/assets/translations/tr.json diff --git a/quiz-app/src/components/Quiz.vue b/Example project - Github_pages/quiz-app/src/components/Quiz.vue similarity index 100% rename from quiz-app/src/components/Quiz.vue rename to Example project - Github_pages/quiz-app/src/components/Quiz.vue diff --git a/quiz-app/src/main.js b/Example project - Github_pages/quiz-app/src/main.js similarity index 100% rename from quiz-app/src/main.js rename to Example project - Github_pages/quiz-app/src/main.js diff --git a/quiz-app/src/router/index.js b/Example project - Github_pages/quiz-app/src/router/index.js similarity index 100% rename from quiz-app/src/router/index.js rename to Example project - Github_pages/quiz-app/src/router/index.js diff --git a/quiz-app/src/views/Home.vue b/Example project - Github_pages/quiz-app/src/views/Home.vue similarity index 100% rename from quiz-app/src/views/Home.vue rename to Example project - Github_pages/quiz-app/src/views/Home.vue diff --git a/quiz-app/src/views/NotFound.vue b/Example project - Github_pages/quiz-app/src/views/NotFound.vue similarity index 100% rename from quiz-app/src/views/NotFound.vue rename to Example project - Github_pages/quiz-app/src/views/NotFound.vue diff --git a/sketchnotes/LICENSE.md b/Example project - Github_pages/sketchnotes/LICENSE.md similarity index 100% rename from sketchnotes/LICENSE.md rename to Example project - Github_pages/sketchnotes/LICENSE.md diff --git a/sketchnotes/README.md b/Example project - Github_pages/sketchnotes/README.md similarity index 100% rename from sketchnotes/README.md rename to Example project - Github_pages/sketchnotes/README.md diff --git a/sketchnotes/ml-fairness.png b/Example project - Github_pages/sketchnotes/ml-fairness.png similarity index 100% rename from sketchnotes/ml-fairness.png rename to Example project - Github_pages/sketchnotes/ml-fairness.png diff --git a/sketchnotes/ml-history.png b/Example project - Github_pages/sketchnotes/ml-history.png similarity index 100% rename from sketchnotes/ml-history.png rename to Example project - Github_pages/sketchnotes/ml-history.png diff --git a/sketchnotes/ml-realworld.png b/Example project - Github_pages/sketchnotes/ml-realworld.png similarity index 100% rename from sketchnotes/ml-realworld.png rename to Example project - Github_pages/sketchnotes/ml-realworld.png diff --git a/sketchnotes/ml-regression.png b/Example project - Github_pages/sketchnotes/ml-regression.png similarity index 100% rename from sketchnotes/ml-regression.png rename to Example project - Github_pages/sketchnotes/ml-regression.png diff --git a/sketchnotes/ml-reinforcement.png b/Example project - Github_pages/sketchnotes/ml-reinforcement.png similarity index 100% rename from sketchnotes/ml-reinforcement.png rename to Example project - Github_pages/sketchnotes/ml-reinforcement.png diff --git a/sketchnotes/ml-timeseries.png b/Example project - Github_pages/sketchnotes/ml-timeseries.png similarity index 100% rename from sketchnotes/ml-timeseries.png rename to Example project - Github_pages/sketchnotes/ml-timeseries.png diff --git a/translations/README.es.md b/Example project - Github_pages/translations/README.es.md similarity index 100% rename from translations/README.es.md rename to Example project - Github_pages/translations/README.es.md diff --git a/translations/README.hi.md b/Example project - Github_pages/translations/README.hi.md similarity index 100% rename from translations/README.hi.md rename to Example project - Github_pages/translations/README.hi.md diff --git a/translations/README.it.md b/Example project - Github_pages/translations/README.it.md similarity index 100% rename from translations/README.it.md rename to Example project - Github_pages/translations/README.it.md diff --git a/translations/README.ja.md b/Example project - Github_pages/translations/README.ja.md similarity index 100% rename from translations/README.ja.md rename to Example project - Github_pages/translations/README.ja.md diff --git a/translations/README.ko.md b/Example project - Github_pages/translations/README.ko.md similarity index 100% rename from translations/README.ko.md rename to Example project - Github_pages/translations/README.ko.md diff --git a/translations/README.ms.md b/Example project - Github_pages/translations/README.ms.md similarity index 100% rename from translations/README.ms.md rename to Example project - Github_pages/translations/README.ms.md diff --git a/translations/README.pt-br.md b/Example project - Github_pages/translations/README.pt-br.md similarity index 100% rename from translations/README.pt-br.md rename to Example project - Github_pages/translations/README.pt-br.md diff --git a/translations/README.pt.md b/Example project - Github_pages/translations/README.pt.md similarity index 100% rename from translations/README.pt.md rename to Example project - Github_pages/translations/README.pt.md diff --git a/translations/README.tr.md b/Example project - Github_pages/translations/README.tr.md similarity index 100% rename from translations/README.tr.md rename to Example project - Github_pages/translations/README.tr.md diff --git a/translations/README.zh-cn.md b/Example project - Github_pages/translations/README.zh-cn.md similarity index 100% rename from translations/README.zh-cn.md rename to Example project - Github_pages/translations/README.zh-cn.md diff --git a/translations/Readme.ta.md b/Example project - Github_pages/translations/Readme.ta.md similarity index 100% rename from translations/Readme.ta.md rename to Example project - Github_pages/translations/Readme.ta.md diff --git a/README.md b/README.md index d6fde993..03636e01 100644 --- a/README.md +++ b/README.md @@ -1,18 +1,8 @@ -[![GitHub license](https://img.shields.io/github/license/microsoft/ML-For-Beginners.svg)](https://github.com/microsoft/ML-For-Beginners/blob/master/LICENSE) -[![GitHub contributors](https://img.shields.io/github/contributors/microsoft/ML-For-Beginners.svg)](https://GitHub.com/microsoft/ML-For-Beginners/graphs/contributors/) -[![GitHub issues](https://img.shields.io/github/issues/microsoft/ML-For-Beginners.svg)](https://GitHub.com/microsoft/ML-For-Beginners/issues/) -[![GitHub pull-requests](https://img.shields.io/github/issues-pr/microsoft/ML-For-Beginners.svg)](https://GitHub.com/microsoft/ML-For-Beginners/pulls/) -[![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg?style=flat-square)](http://makeapullrequest.com) - -[![GitHub watchers](https://img.shields.io/github/watchers/microsoft/ML-For-Beginners.svg?style=social&label=Watch)](https://GitHub.com/microsoft/ML-For-Beginners/watchers/) -[![GitHub forks](https://img.shields.io/github/forks/microsoft/ML-For-Beginners.svg?style=social&label=Fork)](https://GitHub.com/microsoft/ML-For-Beginners/network/) -[![GitHub stars](https://img.shields.io/github/stars/microsoft/ML-For-Beginners.svg?style=social&label=Star)](https://GitHub.com/microsoft/ML-For-Beginners/stargazers/) # Introduction to Deep Learning for HA AI Track - A Curriculum > 🤩 Welcome to the Honors Academy AI Track Resource Hub! 🤩 - Dive into the world of **Deep Learning** with the **Eindhoven University of Technology's Honors Academy AI Track **. This dedicated platform is tailored to provide our ambitious students with a comprehensive collection of materials, insights, and tools to excel in their AI endeavors. Whether you're embarking on a deep learning journey or exploring the intricacies of machine learning, our curated resources are here to guide you every step of the way. Our commitment is to ensure that you have a solid foundation to kickstart your projects. From essential basics to advanced techniques, our materials encompass a wide spectrum of AI knowledge. Moreover, our expertly crafted tips and tricks are designed to enhance your project's efficiency and effectiveness. But that's not all! Dive deeper with our additional resources that offer a broader perspective and connect theoretical knowledge with practical application. @@ -43,7 +33,7 @@ Embrace the future of AI with confidence. Let's embark on this transformative jo **Teachers**, we have [included some suggestions](for-teachers.md) on how to use this curriculum. ---- +---fdfd ## Video walkthroughs