leestott
164a279210
|
3 weeks ago | |
|---|---|---|
| .. | ||
| README.md | 3 weeks ago | |
| assignment.md | 3 weeks ago | |
README.md
Introduction to Machine Learning
Pre-lecture quiz
🎥 Click the image above for a short video that walks you through this lesson.
Welcome to this course on classical machine learning for beginners! Whether you're completely new to the topic or an experienced ML practitioner looking to refresh your knowledge, we're glad to have you here! We aim to create a welcoming starting point for your ML journey and would love to hear your feedback to improve this course.
🎥 Click the image above for a video: MIT's John Guttag introduces machine learning.
Getting Started with Machine Learning
Before diving into this curriculum, make sure your computer is set up to run notebooks locally.
- Set up your machine with these videos. Use the following links to learn how to install Python on your system and set up a text editor for development.
- Learn Python. It's recommended to have a basic understanding of Python, a programming language widely used by data scientists and utilized in this course.
- Learn Node.js and JavaScript. We occasionally use JavaScript in this course for building web apps, so you'll need Node.js and npm installed, along with Visual Studio Code for both Python and JavaScript development.
- Create a GitHub account. If you found us on GitHub, you might already have an account. If not, create one and fork this curriculum to use on your own. (Feel free to give us a star, too 😊)
- Explore Scikit-learn. Familiarize yourself with Scikit-learn, a set of ML libraries referenced throughout these lessons.
What is Machine Learning?
The term "machine learning" is one of the most popular and widely used buzzwords today. If you have any familiarity with technology, you've likely heard it at least once, regardless of your field. However, the mechanics of machine learning remain a mystery to many. For beginners, the subject can sometimes feel overwhelming. That's why it's important to understand what machine learning truly is and learn about it step by step through practical examples.
The Hype Curve
Google Trends shows the recent "hype curve" of the term "machine learning."
A Mysterious Universe
We live in a universe filled with fascinating mysteries. Great scientists like Stephen Hawking, Albert Einstein, and many others have dedicated their lives to uncovering meaningful information about the world around us. This quest for knowledge is part of the human condition: as children, we learn new things and gradually understand the structure of our world as we grow.
The Child's Brain
A child's brain and senses perceive their surroundings and gradually learn hidden patterns of life. These patterns help the child develop logical rules to identify and understand what they've learned. This learning process makes humans the most advanced living beings on Earth. By continuously discovering hidden patterns and innovating upon them, we improve ourselves throughout our lives. This ability to learn and adapt is linked to a concept called brain plasticity. On a surface level, we can draw motivational parallels between the human brain's learning process and the principles of machine learning.
The Human Brain
The human brain perceives information from the real world, processes it, makes rational decisions, and takes actions based on circumstances. This is what we call intelligent behavior. When we program a machine to mimic this intelligent behavior, we call it artificial intelligence (AI).
Some Terminology
Although the terms are often confused, machine learning (ML) is a significant subset of artificial intelligence. ML focuses on using specialized algorithms to uncover meaningful insights and hidden patterns from data, supporting rational decision-making processes.
AI, ML, Deep Learning
A diagram showing the relationships between AI, ML, deep learning, and data science. Infographic by Jen Looper inspired by this graphic.
Concepts to Cover
In this curriculum, we will focus on the core concepts of machine learning that every beginner should know. We will explore "classical machine learning," primarily using Scikit-learn, a popular library for learning the basics. A solid understanding of machine learning is essential for grasping broader concepts in artificial intelligence or deep learning, and we aim to provide that foundation 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 of ML
What We Will Not Cover
- Deep learning
- Neural networks
- AI
To keep the learning experience manageable, we will avoid the complexities of neural networks, "deep learning" (which involves building multi-layered models using neural networks), and AI. These topics will be covered in a separate curriculum. Additionally, we plan to offer a data science curriculum in the future to focus on that aspect of this broader field.
Why Study Machine Learning?
From a systems perspective, machine learning is the creation of automated systems that can learn hidden patterns from data to make intelligent decisions.
This concept is loosely inspired by how the human brain learns from the data it perceives in the world.
✅ Take a moment to think about why a business might prefer using machine learning strategies over creating a hard-coded, rules-based system.
Applications of Machine Learning
Machine learning applications are everywhere, as ubiquitous as the data generated by our smartphones, connected devices, and other systems. Given the immense potential of state-of-the-art ML algorithms, researchers are exploring their ability to solve complex, real-world problems across multiple disciplines, often with remarkable results.
Examples of Applied ML
Machine learning can be used in many ways:
- Predicting the likelihood of disease based on a patient's medical history or reports.
- Using weather data to forecast weather events.
- Analyzing text to understand sentiment.
- Detecting fake news to prevent the spread of misinformation.
Fields like finance, economics, earth science, space exploration, biomedical engineering, cognitive science, and even the humanities have adopted machine learning to tackle data-intensive challenges in their domains.
Conclusion
Machine learning automates the discovery of patterns by extracting meaningful insights from real-world or generated data. It has proven to be highly valuable in business, healthcare, finance, and other fields.
In the near future, understanding the basics of machine learning will become essential for people in any domain due to its widespread adoption.
🚀 Challenge
Sketch, on paper or using an online app like Excalidraw, your understanding of the differences between AI, ML, deep learning, and data science. Include examples of problems that each technique is well-suited to solve.
Post-lecture quiz
Review & Self-Study
To learn more about working with ML algorithms in the cloud, follow this Learning Path.
Take a Learning Path to explore the basics of ML.
Assignment
Disclaimer:
This document has been translated using the AI translation service Co-op Translator. While we aim for accuracy, please note that automated translations may include errors or inaccuracies. The original document in its native language should be regarded as the authoritative source. For critical information, professional human translation is advised. We are not responsible for any misunderstandings or misinterpretations resulting from the use of this translation.