diff --git a/translations/ar/1-Introduction/README.md b/translations/ar/1-Introduction/README.md index 8703b4465..e6afa0a4a 100644 --- a/translations/ar/1-Introduction/README.md +++ b/translations/ar/1-Introduction/README.md @@ -11,7 +11,7 @@ CO_OP_TRANSLATOR_METADATA: في هذا القسم من المنهج الدراسي، ستتعرف على المفاهيم الأساسية التي تشكل مجال تعلم الآلة، ما هو، وتتعرف على تاريخه والتقنيات التي يستخدمها الباحثون للعمل معه. دعونا نستكشف هذا العالم الجديد من تعلم الآلة معًا! -![globe](../../../translated_images/globe.59f26379ceb40428672b4d9a568044618a2bf6292ecd53a5c481b90e3fa805eb.ar.jpg) +![globe](../../../translated_images/globe.59f26379ceb40428.ar.jpg) > صورة بواسطة Bill Oxford على Unsplash ### الدروس diff --git a/translations/ar/2-Regression/1-Tools/solution/R/lesson_1-R.ipynb b/translations/ar/2-Regression/1-Tools/solution/R/lesson_1-R.ipynb index ddcee21e7..0492a31f3 100644 --- a/translations/ar/2-Regression/1-Tools/solution/R/lesson_1-R.ipynb +++ b/translations/ar/2-Regression/1-Tools/solution/R/lesson_1-R.ipynb @@ -50,7 +50,7 @@ " width=\"630\"/>\n", "
عمل فني بواسطة @allison_horst
\n", "\n", - "\n" + "\n" ], "metadata": { "id": "LWNNzfqd6feZ" diff --git a/translations/ar/2-Regression/2-Data/solution/R/lesson_2-R.ipynb b/translations/ar/2-Regression/2-Data/solution/R/lesson_2-R.ipynb index c089ef1bc..0de6b02a5 100644 --- a/translations/ar/2-Regression/2-Data/solution/R/lesson_2-R.ipynb +++ b/translations/ar/2-Regression/2-Data/solution/R/lesson_2-R.ipynb @@ -227,7 +227,7 @@ "
عمل فني بواسطة @allison_horst
\n", "\n", "\n", - "\n" + "\n" ], "metadata": { "id": "o4jLY5-VZO2C" @@ -530,7 +530,7 @@ "
رسم توضيحي من إعداد داساني ماديبالي
\n", "\n", "\n", - "\n", + "\n", "\n", "هناك مقولة *حكيمة* تقول:\n", "\n", diff --git a/translations/ar/2-Regression/3-Linear/solution/R/lesson_3-R.ipynb b/translations/ar/2-Regression/3-Linear/solution/R/lesson_3-R.ipynb index 864b0ae95..1d63cdcfe 100644 --- a/translations/ar/2-Regression/3-Linear/solution/R/lesson_3-R.ipynb +++ b/translations/ar/2-Regression/3-Linear/solution/R/lesson_3-R.ipynb @@ -565,7 +565,7 @@ "
رسم توضيحي بواسطة داساني ماديبالي
\n", "\n", "\n", - "\n" + "\n" ], "metadata": { "id": "YqXjLuWavNxW" @@ -806,7 +806,7 @@ "
رسم توضيحي من إعداد داساني ماديبالي
\n", "\n", "\n", - "\n" + "\n" ], "metadata": { "id": "HOCqJXLTwtWI" diff --git a/translations/ar/2-Regression/4-Logistic/solution/R/lesson_4-R.ipynb b/translations/ar/2-Regression/4-Logistic/solution/R/lesson_4-R.ipynb index 47cbd34ac..76d52e3bf 100644 --- a/translations/ar/2-Regression/4-Logistic/solution/R/lesson_4-R.ipynb +++ b/translations/ar/2-Regression/4-Logistic/solution/R/lesson_4-R.ipynb @@ -6,7 +6,7 @@ "source": [ "## بناء نموذج الانحدار اللوجستي - الدرس الرابع\n", "\n", - "![مخطط معلوماتي عن الانحدار اللوجستي مقابل الانحدار الخطي](../../../../../../translated_images/linear-vs-logistic.ba180bf95e7ee66721ba10ebf2dac2666acbd64a88b003c83928712433a13c7d.ar.png)\n", + "![مخطط معلوماتي عن الانحدار اللوجستي مقابل الانحدار الخطي](../../../../../../translated_images/linear-vs-logistic.ba180bf95e7ee667.ar.png)\n", "\n", "#### **[اختبار ما قبل المحاضرة](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/15/)**\n", "\n", @@ -78,7 +78,7 @@ "\n", "الانحدار اللوجستي لا يقدم نفس الميزات التي يقدمها الانحدار الخطي. الأول يقدم توقعًا حول `فئة ثنائية` (\"برتقالي أو ليس برتقالي\")، بينما الثاني قادر على توقع `قيم مستمرة`، على سبيل المثال، بناءً على مصدر القرع ووقت الحصاد، *كم ستزداد قيمته*.\n", "\n", - "![رسم توضيحي بواسطة Dasani Madipalli](../../../../../../translated_images/pumpkin-classifier.562771f104ad5436b87d1c67bca02a42a17841133556559325c0a0e348e5b774.ar.png)\n", + "![رسم توضيحي بواسطة Dasani Madipalli](../../../../../../translated_images/pumpkin-classifier.562771f104ad5436.ar.png)\n", "\n", "### تصنيفات أخرى\n", "\n", @@ -88,7 +88,7 @@ "\n", "- **رتبي**، والذي يتضمن فئات مرتبة، وهو مفيد إذا أردنا ترتيب النتائج بشكل منطقي، مثل القرع الذي يتم ترتيبه حسب عدد محدود من الأحجام (صغير جدًا، صغير، متوسط، كبير، كبير جدًا، كبير جدًا جدًا).\n", "\n", - "![الانحدار متعدد الفئات مقابل الرتبي](../../../../../../translated_images/multinomial-vs-ordinal.36701b4850e37d86c9dd49f7bef93a2f94dbdb8fe03443eb68f0542f97f28f29.ar.png)\n", + "![الانحدار متعدد الفئات مقابل الرتبي](../../../../../../translated_images/multinomial-vs-ordinal.36701b4850e37d86.ar.png)\n", "\n", "#### **المتغيرات لا يجب أن تكون مترابطة**\n", "\n", diff --git a/translations/ar/2-Regression/README.md b/translations/ar/2-Regression/README.md index 1927acbc3..d088a68b9 100644 --- a/translations/ar/2-Regression/README.md +++ b/translations/ar/2-Regression/README.md @@ -12,7 +12,7 @@ CO_OP_TRANSLATOR_METADATA: في أمريكا الشمالية، غالبًا ما يتم نحت القرع إلى وجوه مخيفة للاحتفال بعيد الهالوين. دعونا نكتشف المزيد عن هذه الخضروات المثيرة! -![jack-o-lanterns](../../../translated_images/jack-o-lanterns.181c661a9212457d7756f37219f660f1358af27554d856e5a991f16b4e15337c.ar.jpg) +![jack-o-lanterns](../../../translated_images/jack-o-lanterns.181c661a9212457d.ar.jpg) > صورة بواسطة Beth Teutschmann على Unsplash ## ما ستتعلمه diff --git a/translations/ar/3-Web-App/README.md b/translations/ar/3-Web-App/README.md index 3822263b1..a2b18a692 100644 --- a/translations/ar/3-Web-App/README.md +++ b/translations/ar/3-Web-App/README.md @@ -11,7 +11,7 @@ CO_OP_TRANSLATOR_METADATA: في هذا القسم من المنهج، ستتعرف على موضوع عملي في التعلم الآلي: كيفية حفظ نموذج Scikit-learn كملف يمكن استخدامه لإجراء التنبؤات داخل تطبيق ويب. بمجرد حفظ النموذج، ستتعلم كيفية استخدامه في تطبيق ويب مبني باستخدام Flask. ستقوم أولاً بإنشاء نموذج باستخدام بعض البيانات المتعلقة بمشاهدات الأجسام الطائرة المجهولة (UFO)! بعد ذلك، ستبني تطبيق ويب يسمح لك بإدخال عدد من الثواني مع قيمة خط العرض وخط الطول للتنبؤ بالدولة التي أبلغت عن رؤية جسم طائر مجهول. -![UFO Parking](../../../translated_images/ufo.9e787f5161da9d4d1dafc537e1da09be8210f2ee996cb638aa5cee1d92867a04.ar.jpg) +![UFO Parking](../../../translated_images/ufo.9e787f5161da9d4d.ar.jpg) صورة بواسطة Michael Herren على Unsplash diff --git a/translations/ar/4-Classification/README.md b/translations/ar/4-Classification/README.md index c634f330a..ad6b2d0b3 100644 --- a/translations/ar/4-Classification/README.md +++ b/translations/ar/4-Classification/README.md @@ -13,7 +13,7 @@ CO_OP_TRANSLATOR_METADATA: في آسيا والهند، تتميز تقاليد الطعام بتنوعها الكبير ولذتها الفائقة! دعونا نلقي نظرة على بيانات حول المأكولات الإقليمية لفهم مكوناتها بشكل أفضل. -![بائع طعام تايلاندي](../../../translated_images/thai-food.c47a7a7f9f05c21892a1f9dc7bf30669e6d18dfda420c5c7ebb4153f6a304edd.ar.jpg) +![بائع طعام تايلاندي](../../../translated_images/thai-food.c47a7a7f9f05c218.ar.jpg) > الصورة بواسطة Lisheng Chang على Unsplash ## ما الذي ستتعلمه diff --git a/translations/ar/5-Clustering/README.md b/translations/ar/5-Clustering/README.md index 88f9e9bad..875bed87c 100644 --- a/translations/ar/5-Clustering/README.md +++ b/translations/ar/5-Clustering/README.md @@ -15,7 +15,7 @@ CO_OP_TRANSLATOR_METADATA: الجمهور النيجيري المتنوع لديه أذواق موسيقية متنوعة. باستخدام البيانات المستخرجة من Spotify (مستوحاة من [هذه المقالة](https://towardsdatascience.com/country-wise-visual-analysis-of-music-taste-using-spotify-api-seaborn-in-python-77f5b749b421))، دعونا نلقي نظرة على بعض الموسيقى الشعبية في نيجيريا. تتضمن هذه المجموعة من البيانات معلومات حول درجات "القابلية للرقص"، "الصوتية"، مستوى الصوت، "الكلامية"، الشعبية والطاقة للأغاني المختلفة. سيكون من المثير اكتشاف الأنماط في هذه البيانات! -![جهاز تشغيل الأسطوانات](../../../translated_images/turntable.f2b86b13c53302dc106aa741de9dc96ac372864cf458dd6f879119857aab01da.ar.jpg) +![جهاز تشغيل الأسطوانات](../../../translated_images/turntable.f2b86b13c53302dc.ar.jpg) > صورة بواسطة Marcela Laskoski على Unsplash diff --git a/translations/ar/6-NLP/README.md b/translations/ar/6-NLP/README.md index 9b913387e..7e3b6c40d 100644 --- a/translations/ar/6-NLP/README.md +++ b/translations/ar/6-NLP/README.md @@ -17,7 +17,7 @@ CO_OP_TRANSLATOR_METADATA: في هذه الدروس، سنتعلم أساسيات معالجة اللغة الطبيعية من خلال بناء روبوتات محادثة صغيرة لفهم كيف يساعد التعلم الآلي في جعل هذه المحادثات أكثر "ذكاءً". ستعود بالزمن إلى الوراء، وتتحدث مع إليزابيث بينيت والسيد دارسي من رواية جين أوستن الكلاسيكية، **كبرياء وتحامل**، التي نُشرت عام 1813. بعد ذلك، ستُعمّق معرفتك من خلال تعلم تحليل المشاعر عبر مراجعات الفنادق في أوروبا. -![كتاب كبرياء وتحامل وشاي](../../../translated_images/p&p.279f1c49ecd889419e4ce6206525e9aa30d32a976955cd24daa636c361c6391f.ar.jpg) +![كتاب كبرياء وتحامل وشاي](../../../translated_images/p&p.279f1c49ecd88941.ar.jpg) > صورة بواسطة Elaine Howlin على Unsplash ## الدروس diff --git a/translations/ar/7-TimeSeries/README.md b/translations/ar/7-TimeSeries/README.md index ef7439d17..474eb214b 100644 --- a/translations/ar/7-TimeSeries/README.md +++ b/translations/ar/7-TimeSeries/README.md @@ -17,7 +17,7 @@ CO_OP_TRANSLATOR_METADATA: تركيزنا الإقليمي هو استخدام الكهرباء عالميًا، وهو مجموعة بيانات مثيرة للاهتمام للتعلم عن كيفية التنبؤ باستخدام الطاقة في المستقبل بناءً على أنماط الأحمال السابقة. يمكنك أن ترى كيف يمكن أن يكون هذا النوع من التنبؤ مفيدًا للغاية في بيئة الأعمال. -![شبكة الكهرباء](../../../translated_images/electric-grid.0c21d5214db09ffae93c06a87ca2abbb9ba7475ef815129c5b423d7f9a7cf136.ar.jpg) +![شبكة الكهرباء](../../../translated_images/electric-grid.0c21d5214db09ffa.ar.jpg) صورة بواسطة [Peddi Sai hrithik](https://unsplash.com/@shutter_log?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText) لأبراج كهرباء على طريق في راجستان على [Unsplash](https://unsplash.com/s/photos/electric-india?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText) diff --git a/translations/ar/8-Reinforcement/README.md b/translations/ar/8-Reinforcement/README.md index d04670cbd..6af01ec09 100644 --- a/translations/ar/8-Reinforcement/README.md +++ b/translations/ar/8-Reinforcement/README.md @@ -13,7 +13,7 @@ CO_OP_TRANSLATOR_METADATA: تخيل أن لديك بيئة محاكاة مثل سوق الأسهم. ماذا يحدث إذا فرضت تنظيمًا معينًا؟ هل سيكون له تأثير إيجابي أم سلبي؟ إذا حدث شيء سلبي، عليك أن تأخذ هذا _التعزيز السلبي_، تتعلم منه، وتغير المسار. وإذا كان هناك نتيجة إيجابية، عليك أن تبني على هذا _التعزيز الإيجابي_. -![بيتر والذئب](../../../translated_images/peter.779730f9ba3a8a8d9290600dcf55f2e491c0640c785af7ac0d64f583c49b8864.ar.png) +![بيتر والذئب](../../../translated_images/peter.779730f9ba3a8a8d.ar.png) > بيتر وأصدقاؤه بحاجة للهروب من الذئب الجائع! الصورة بواسطة [جين لوبر](https://twitter.com/jenlooper) diff --git a/translations/ar/9-Real-World/README.md b/translations/ar/9-Real-World/README.md index cab2a1b18..4a6b66409 100644 --- a/translations/ar/9-Real-World/README.md +++ b/translations/ar/9-Real-World/README.md @@ -11,7 +11,7 @@ CO_OP_TRANSLATOR_METADATA: في هذا القسم من المنهج الدراسي، ستتعرف على بعض تطبيقات العالم الحقيقي لتعلم الآلة الكلاسيكي. لقد قمنا بالبحث عبر الإنترنت للعثور على أوراق بحثية ومقالات حول تطبيقات استخدمت هذه الاستراتيجيات، مع تجنب الشبكات العصبية، التعلم العميق والذكاء الاصطناعي قدر الإمكان. تعرف على كيفية استخدام تعلم الآلة في أنظمة الأعمال، التطبيقات البيئية، التمويل، الفنون والثقافة، والمزيد. -![chess](../../../translated_images/chess.e704a268781bdad85d1876b6c2295742fa0d856e7dcf3659147052df9d3db205.ar.jpg) +![chess](../../../translated_images/chess.e704a268781bdad8.ar.jpg) > صورة بواسطة Alexis Fauvet على Unsplash diff --git a/translations/ar/README.md b/translations/ar/README.md index cbf733b5d..eb4e1ccaa 100644 --- a/translations/ar/README.md +++ b/translations/ar/README.md @@ -1,86 +1,86 @@ [![ترخيص GitHub](https://img.shields.io/github/license/microsoft/ML-For-Beginners.svg)](https://github.com/microsoft/ML-For-Beginners/blob/master/LICENSE) [![مساهمو GitHub](https://img.shields.io/github/contributors/microsoft/ML-For-Beginners.svg)](https://GitHub.com/microsoft/ML-For-Beginners/graphs/contributors/) -[![قضايا GitHub](https://img.shields.io/github/issues/microsoft/ML-For-Beginners.svg)](https://GitHub.com/microsoft/ML-For-Beginners/issues/) +[![مشكلات GitHub](https://img.shields.io/github/issues/microsoft/ML-For-Beginners.svg)](https://GitHub.com/microsoft/ML-For-Beginners/issues/) [![طلبات سحب GitHub](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) +[![مرحبًا بالـ PRs](https://img.shields.io/badge/PRs-welcome-brightgreen.svg?style=flat-square)](http://makeapullrequest.com) -[![مراقبو GitHub](https://img.shields.io/github/watchers/microsoft/ML-For-Beginners.svg?style=social&label=Watch)](https://GitHub.com/microsoft/ML-For-Beginners/watchers/) -[![مشروعات GitHub](https://img.shields.io/github/forks/microsoft/ML-For-Beginners.svg?style=social&label=Fork)](https://GitHub.com/microsoft/ML-For-Beginners/network/) +[![المتابعون على GitHub](https://img.shields.io/github/watchers/microsoft/ML-For-Beginners.svg?style=social&label=Watch)](https://GitHub.com/microsoft/ML-For-Beginners/watchers/) +[![Forks على GitHub](https://img.shields.io/github/forks/microsoft/ML-For-Beginners.svg?style=social&label=Fork)](https://GitHub.com/microsoft/ML-For-Beginners/network/) [![نجوم GitHub](https://img.shields.io/github/stars/microsoft/ML-For-Beginners.svg?style=social&label=Star)](https://GitHub.com/microsoft/ML-For-Beginners/stargazers/) -### 🌐 دعم لغات متعددة +### 🌐 دعم متعدد اللغات -#### مدعوم عبر GitHub Action (مؤتمت ومحدث دائمًا) +#### مدعوم عبر إجراء GitHub (مؤتمت ومحدّث دائمًا) -[العربية](./README.md) | [البنغالية](../bn/README.md) | [البلغارية](../bg/README.md) | [البورمية (ميانمار)](../my/README.md) | [الصينية (المبسطة)](../zh/README.md) | [الصينية (التقليدية، هونغ كونغ)](../hk/README.md) | [الصينية (التقليدية، ماكاو)](../mo/README.md) | [الصينية (التقليدية، تايوان)](../tw/README.md) | [الكرواتية](../hr/README.md) | [التشيكية](../cs/README.md) | [الدانماركية](../da/README.md) | [الهولندية](../nl/README.md) | [الإستونية](../et/README.md) | [الفنلندية](../fi/README.md) | [الفرنسية](../fr/README.md) | [الألمانية](../de/README.md) | [اليونانية](../el/README.md) | [العبرية](../he/README.md) | [الهندية](../hi/README.md) | [الهنغارية](../hu/README.md) | [الإندونيسية](../id/README.md) | [الإيطالية](../it/README.md) | [اليابانية](../ja/README.md) | [الكانادية](../kn/README.md) | [الكورية](../ko/README.md) | [الليتوانية](../lt/README.md) | [الماليزية](../ms/README.md) | [المالايالامية](../ml/README.md) | [الماراثية](../mr/README.md) | [النيبالية](../ne/README.md) | [البيجن النيجيري](../pcm/README.md) | [النرويجية](../no/README.md) | [الفارسية (فارسية)](../fa/README.md) | [البولندية](../pl/README.md) | [البرتغالية (البرازيل)](../br/README.md) | [البرتغالية (البرتغال)](../pt/README.md) | [البنجابية (غورموكهي)](../pa/README.md) | [الرومانية](../ro/README.md) | [الروسية](../ru/README.md) | [الصربية (السيريلية)](../sr/README.md) | [السلوفاكية](../sk/README.md) | [السلوفينية](../sl/README.md) | [الإسبانية](../es/README.md) | [السواحلية](../sw/README.md) | [السويدية](../sv/README.md) | [التاغالوغ (الفلبينية)](../tl/README.md) | [التاميل](../ta/README.md) | [التيلجو](../te/README.md) | [التايلاندية](../th/README.md) | [التركية](../tr/README.md) | [الأوكرانية](../uk/README.md) | [الأردية](../ur/README.md) | [الفيتنامية](../vi/README.md) +[العربية](./README.md) | [البنغالية](../bn/README.md) | [البلغارية](../bg/README.md) | [البرمية (ميانمار)](../my/README.md) | [الصينية (مبسطة)](../zh/README.md) | [الصينية (تقليدية، هونغ كونغ)](../hk/README.md) | [الصينية (تقليدية، ماكاو)](../mo/README.md) | [الصينية (تقليدية، تايوان)](../tw/README.md) | [الكرواتية](../hr/README.md) | [التشيكية](../cs/README.md) | [الدنماركية](../da/README.md) | [الهولندية](../nl/README.md) | [الإستونية](../et/README.md) | [الفنلندية](../fi/README.md) | [الفرنسية](../fr/README.md) | [الألمانية](../de/README.md) | [اليونانية](../el/README.md) | [العبرية](../he/README.md) | [الهندية](../hi/README.md) | [الهنغارية](../hu/README.md) | [الإندونيسية](../id/README.md) | [الإيطالية](../it/README.md) | [اليابانية](../ja/README.md) | [الكانادية](../kn/README.md) | [الكورية](../ko/README.md) | [اللتوانية](../lt/README.md) | [الماليزية](../ms/README.md) | [المالايالامية](../ml/README.md) | [الماراثية](../mr/README.md) | [النيبالية](../ne/README.md) | [البيجن النيجيري](../pcm/README.md) | [النرويجية](../no/README.md) | [الفارسية (الفارسي)](../fa/README.md) | [البولندية](../pl/README.md) | [البرتغالية (البرازيل)](../br/README.md) | [البرتغالية (البرتغال)](../pt/README.md) | [البنجابية (Gurmukhi)](../pa/README.md) | [الرومانية](../ro/README.md) | [الروسية](../ru/README.md) | [الصربية (السيريلية)](../sr/README.md) | [السلوفاكية](../sk/README.md) | [السلوفينية](../sl/README.md) | [الإسبانية](../es/README.md) | [السواحيلية](../sw/README.md) | [السويدية](../sv/README.md) | [التاغالوغية (الفلبينية)](../tl/README.md) | [التاميلية](../ta/README.md) | [التيلوغو](../te/README.md) | [التايلاندية](../th/README.md) | [التركية](../tr/README.md) | [الأوكرانية](../uk/README.md) | [الأردية](../ur/README.md) | [الفيتنامية](../vi/README.md) #### انضم إلى مجتمعنا -[![خادم Microsoft Foundry على Discord](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) +[![خادم Microsoft Foundry في Discord](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) -نقوم بسلسلة "تعلم مع الذكاء الاصطناعي" على Discord، اعرف المزيد وانضم إلينا في [سلسلة تعلم مع الذكاء الاصطناعي](https://aka.ms/learnwithai/discord) من 18 - 30 سبتمبر 2025. ستحصل على نصائح وحيل حول استخدام GitHub Copilot لعلوم البيانات. +نقوم بتشغيل سلسلة Learn with AI على Discord، تعرف على المزيد وانضم إلينا في [Learn with AI Series](https://aka.ms/learnwithai/discord) من 18 إلى 30 سبتمبر 2025. ستحصل على نصائح وحيل لاستخدام GitHub Copilot في علم البيانات. -![سلسلة تعلم مع الذكاء الاصطناعي](../../translated_images/3.9b58fd8d6c373c20c588c5070c4948a826ab074426c28ceb5889641294373dfc.ar.png) +![سلسلة Learn with AI](../../translated_images/3.9b58fd8d6c373c20.ar.png) # تعلم الآلة للمبتدئين - منهج دراسي > 🌍 سافر حول العالم بينما نستكشف تعلم الآلة من خلال ثقافات العالم 🌍 -يسعد فريق Cloud Advocates في Microsoft أن يقدم منهجًا دراسيًا لمدة 12 أسبوعًا مكونًا من 26 درسًا حول موضوع تعلم الآلة. في هذا المنهج، ستتعلم ما يُطلق عليه أحيانًا "تعلم الآلة الكلاسيكي"، باستخدام مكتبة Scikit-learn بشكل أساسي وتجنب التعلم العميق، والذي يتم تغطيته في [منهج "الذكاء الاصطناعي للمبتدئين"](https://aka.ms/ai4beginners). اقترن هذه الدروس مع [منهج "علوم البيانات للمبتدئين"](https://aka.ms/ds4beginners) أيضًا! +يسعد فريق Cloud Advocates في Microsoft أن يقدم منهجًا دراسيًا مدته 12 أسبوعًا يتضمن 26 درسًا حول موضوع **تعلم الآلة**. في هذا المنهج، ستتعلم ما يُطلق عليه أحيانًا **تعلم الآلة الكلاسيكي**، باستخدام مكتبة Scikit-learn بشكل أساسي وتجنب التعلم العميق، الذي يتم تغطيته في [منهج "الذكاء الاصطناعي للمبتدئين"](https://aka.ms/ai4beginners). يمكنك إقران هذه الدروس مع [منهج "علم البيانات للمبتدئين"](https://aka.ms/ds4beginners) أيضًا! -سافر معنا حول العالم بينما نطبق هذه التقنيات الكلاسيكية على بيانات من مناطق عديدة حول العالم. يتضمن كل درس اختبارات قبل وبعد الدرس، وإرشادات مكتوبة لإكمال الدرس، وحل، ومهمة، والمزيد. تتيح منا منهجية التعليم القائمة على المشاريع أن تتعلم أثناء البناء، وهي طريقة مثبتة لترسيخ المهارات الجديدة. +سافر معنا حول العالم بينما نطبق هذه التقنيات الكلاسيكية على بيانات من مناطق متعددة في العالم. يتضمن كل درس اختبارات قبل وبعد الدرس، وإرشادات مكتوبة لإكمال الدرس، وحلًا، ومهمة، والمزيد. تتيح لنا منهجية التعلم القائمة على المشاريع أن تتعلم أثناء البناء، وهي طريقة مثبتة لجعل المهارات الجديدة "تثبت". **✍️ شكر حار لمؤلفينا** Jen Looper, Stephen Howell, Francesca Lazzeri, Tomomi Imura, Cassie Breviu, Dmitry Soshnikov, Chris Noring, Anirban Mukherjee, Ornella Altunyan, Ruth Yakubu and Amy Boyd **🎨 شكر أيضًا لرسامينا** Tomomi Imura, Dasani Madipalli, and Jen Looper -**🙏 شكر خاص 🙏 لمؤلفي ومراجعي ومساهمي المحتوى من سفراء طلاب Microsoft لدينا**، وعلى وجه الخصوص Rishit Dagli, Muhammad Sakib Khan Inan, Rohan Raj, Alexandru Petrescu, Abhishek Jaiswal, Nawrin Tabassum, Ioan Samuila, و Snigdha Agarwal +**🙏 شكر خاص 🙏 لمؤلفي ومراجعي ومساهمي المحتوى من سفراء طلاب Microsoft**، ولا سيما Rishit Dagli, Muhammad Sakib Khan Inan, Rohan Raj, Alexandru Petrescu, Abhishek Jaiswal, Nawrin Tabassum, Ioan Samuila, و Snigdha Agarwal -**🤩 امتنان إضافي لسفراء طلاب Microsoft Eric Wanjau, Jasleen Sondhi, و Vidushi Gupta على دروس R الخاصة بنا!** +**🤩 امتنان إضافي إلى سفراء طلاب Microsoft Eric Wanjau, Jasleen Sondhi, و Vidushi Gupta لدروس R الخاصة بنا!** # البدء اتبع هذه الخطوات: -1. **استنساخ المستودع (Fork the Repository)**: انقر على زر "Fork" في الزاوية العلوية اليمنى من هذه الصفحة. -2. **استنساخ المستودع محليًا (Clone the Repository)**: `git clone https://github.com/microsoft/ML-For-Beginners.git` +1. **استنسخ المستودع (Fork the Repository)**: Click on the "Fork" button at the top-right corner of this page. +2. **استنساخ المستودع (Clone the Repository)**: `git clone https://github.com/microsoft/ML-For-Beginners.git` -> [اعثر على جميع الموارد الإضافية لهذا المقرر في مجموعة Microsoft Learn الخاصة بنا](https://learn.microsoft.com/en-us/collections/qrqzamz1nn2wx3?WT.mc_id=academic-77952-bethanycheum) +> [اعثر على جميع الموارد الإضافية لهذه الدورة في مجموعة Microsoft Learn الخاصة بنا](https://learn.microsoft.com/en-us/collections/qrqzamz1nn2wx3?WT.mc_id=academic-77952-bethanycheum) -> 🔧 **تحتاج مساعدة؟** اطلع على دليل [استكشاف الأخطاء وإصلاحها](TROUBLESHOOTING.md) لحلول المشاكل الشائعة المتعلقة بالتثبيت والإعداد وتشغيل الدروس. +> 🔧 **هل تحتاج مساعدة؟** اطلع على [دليل استكشاف الأخطاء وإصلاحها](TROUBLESHOOTING.md) للحصول على حلول للمشكلات الشائعة المتعلقة بالتثبيت والإعداد وتشغيل الدروس. -**[الطلاب](https://aka.ms/student-page)**، لاستخدام هذا المنهج، انسخ المستودع بكامله إلى حساب GitHub الخاص بك وأكمل التمارين بنفسك أو مع مجموعة: +**[الطلاب](https://aka.ms/student-page)**، لاستخدام هذا المنهج، انسخ المستودع بأكمله إلى حساب GitHub الخاص بك وأكمل التمارين بنفسك أو مع مجموعة: -- ابدأ باختبار قبل المحاضرة. -- اقرأ المحاضرة وأكمل الأنشطة، وتوقف وتأمل في كل نقطة تحقق معرفية. -- حاول إنشاء المشاريع من خلال فهم الدروس بدلاً من تشغيل كود الحل؛ ومع ذلك فإن ذلك الكود متاح في مجلدات `/solution` في كل درس موجه بالمشروع. -- خض اختبار ما بعد المحاضرة. +- ابدأ باختبار تمهيدي قبل المحاضرة. +- اقرأ المحاضرة وأكمل الأنشطة، وتوقف وفكر عند كل نقطة تحقق معرفي. +- حاول إنشاء المشاريع من خلال فهم الدروس بدلًا من تشغيل كود الحل مباشرة؛ ومع ذلك يتوفر هذا الكود في مجلدات `/solution` في كل درس موجه بالمشروع. +- أكمل اختبار ما بعد المحاضرة. - أكمل التحدي. -- أكمل المهمة. -- بعد إكمال مجموعة دروس، زر [لوحة النقاش](https://github.com/microsoft/ML-For-Beginners/discussions) و"تعلّم بصوتٍ عالٍ" بملء مصفوفة PAT المناسبة. الـ 'PAT' هي أداة تقييم التقدم وهي مقياس تعبئه لمزيد من تعلمك. يمكنك أيضًا التفاعل مع PATs الآخرين لكي نتعلم معًا. +- أكمل الواجب. +- بعد إكمال مجموعة دروس، قم بزيارة [لوحة النقاش](https://github.com/microsoft/ML-For-Beginners/discussions) و"تعلّم بصوت عالٍ" بملء نموذج التقييم PAT المناسب. الـ 'PAT' هي أداة تقييم التقدم وهي مقياس تملأه لتعزيز تعلمك. يمكنك أيضًا التفاعل مع PATs الأخرى حتى نتعلم سويًا. -> للمزيد من الدراسة، نوصي بمتابعة هذه الوحدات ومسارات التعلم في [Microsoft Learn](https://docs.microsoft.com/en-us/users/jenlooper-2911/collections/k7o7tg1gp306q4?WT.mc_id=academic-77952-leestott). +> لمزيد من الدراسة، نوصي بمتابعة هذه الوحدات ومسارات التعلم في [Microsoft Learn](https://docs.microsoft.com/en-us/users/jenlooper-2911/collections/k7o7tg1gp306q4?WT.mc_id=academic-77952-leestott). -**المعلمون**, لقد قمنا [بتضمين بعض الاقتراحات](for-teachers.md) حول كيفية استخدام هذا المنهج الدراسي. +**المعلمون**, لقد قمنا [بتضمين بعض الاقتراحات](for-teachers.md) حول كيفية استخدام هذا المنهج. --- ## شروحات الفيديو -بعض الدروس متاحة كفيديوهات قصيرة. يمكنك العثور على كل هذه الفيديوهات ضمن الدروس، أو على [قائمة تشغيل ML للمبتدئين على قناة Microsoft Developer على YouTube](https://aka.ms/ml-beginners-videos) بالنقر على الصورة أدناه. +بعض الدروس متاحة كفيديو قصير. يمكنك العثور على كل هذه الفيديوهات مضمّنة داخل الدروس، أو على [قائمة تشغيل ML للمبتدئين على قناة Microsoft Developer على YouTube](https://aka.ms/ml-beginners-videos) بالنقر على الصورة أدناه. -[![بانر ML للمبتدئين](../../translated_images/ml-for-beginners-video-banner.63f694a100034bc6251134294459696e070a3a9a04632e9fe6a24aa0de4a7384.ar.png)](https://aka.ms/ml-beginners-videos) +[![لافتة ML للمبتدئين](../../translated_images/ml-for-beginners-video-banner.63f694a100034bc6.ar.png)](https://aka.ms/ml-beginners-videos) --- @@ -88,82 +88,82 @@ CO_OP_TRANSLATOR_METADATA: [![فيديو ترويجي](../../images/ml.gif)](https://youtu.be/Tj1XWrDSYJU) -**Gif بواسطة** [Mohit Jaisal](https://linkedin.com/in/mohitjaisal) +**GIF بواسطة** [Mohit Jaisal](https://linkedin.com/in/mohitjaisal) -> 🎥 انقر على الصورة أعلاه لمشاهدة فيديو حول المشروع والأشخاص الذين أنشأوه! +> 🎥 انقر على الصورة أعلاه لمشاهدة فيديو عن المشروع والأشخاص الذين أنشأوه! --- -## المنهجية التعليمية +## المنهجية التربوية -اخترنا مبدئين بيداغوجيين أثناء بناء هذا المنهج: التأكد من أنه عملي ومبني على المشاريع، وأنه يتضمن اختبارات متكررة. بالإضافة إلى ذلك، يمتلك هذا المنهج موضوعًا مشتركًا ليمنحه تماسكًا. +اخترنا مبدأين بيداغوجيين أثناء بناء هذا المنهج: التأكد من أنه عملي **قائم على المشاريع** وأنه يتضمن **اختبارات متكررة**. بالإضافة إلى ذلك، يحتوي هذا المنهج على **موضوع** مشترك لمنحه تماسكًا. -من خلال ضمان توافق المحتوى مع المشاريع، يصبح المسار أكثر جاذبية للطلاب وسيُعزز الاحتفاظ بالمفاهيم. بالإضافة إلى ذلك، يضع اختبار منخفض المخاطر قبل المحاضرة نية الطالب نحو تعلم موضوع ما، بينما يضمن الاختبار الثاني بعد المحاضرة مزيدًا من الاحتفاظ. صُمم هذا المنهج ليكون مرنًا وممتعًا ويمكن أخذه كاملًا أو جزئيًا. تبدأ المشاريع صغيرة وتصبح أكثر تعقيدًا تدريجيًا بنهاية دورة الاثني عشر أسبوعًا. يتضمن هذا المنهج أيضًا خاتمة عن تطبيقات تعلم الآلة الواقعية، والتي يمكن استخدامها كرصيد إضافي أو كأساس للنقاش. +من خلال التأكد من توافق المحتوى مع المشاريع، يصبح المسار أكثر جاذبية للطلاب ويزداد احتفاظهم بالمفاهيم. بالإضافة إلى ذلك، يضع اختبار منخفض المخاطر قبل الحصة نية الطالب نحو تعلم موضوع ما، في حين يضمن اختبار ثانٍ بعد الحصة مزيدًا من الاحتفاظ. صُمم هذا المنهج ليكون مرنًا وممتعًا ويمكن اتباعه ككل أو جزئيًا. تبدأ المشاريع صغيرة وتصبح أكثر تعقيدًا تدريجيًا بنهاية دورة الـ 12 أسبوعًا. كما يتضمن هذا المنهج خاتمة حول تطبيقات تعلم الآلة في العالم الحقيقي، والتي يمكن استخدامها كدرجة إضافية أو كقاعدة للنقاش. -> اعثر على [ميثاق السلوك](CODE_OF_CONDUCT.md)، [إرشادات المساهمة](CONTRIBUTING.md)، [إرشادات الترجمة](TRANSLATIONS.md)، و[دليل استكشاف الأخطاء وإصلاحها](TROUBLESHOOTING.md). نرحب بتعليقاتكم البناءة! +> اطلع على [مدونة قواعد السلوك](CODE_OF_CONDUCT.md)، و[إرشادات المساهمة](CONTRIBUTING.md)، و[الترجمة](TRANSLATIONS.md)، و[دليل استكشاف الأخطاء وإصلاحها](TROUBLESHOOTING.md). نرحب بتغذيتكم الراجعة البنّاءة! ## كل درس يتضمن -- ملاحظة تخطيطية اختيارية +- مذكرة رسومية اختيارية - فيديو تكميلي اختياري -- شروحات فيديو (بعض الدروس فقط) -- [اختبار تحفيزي قبل المحاضرة](https://ff-quizzes.netlify.app/en/ml/) +- عرض فيديو توضيحي (بعض الدروس فقط) +- [اختبار إحماء قبل المحاضرة](https://ff-quizzes.netlify.app/en/ml/) - درس مكتوب -- للدروس القائمة على المشاريع، إرشادات خطوة بخطوة حول كيفية بناء المشروع -- نقاط تحقق معرفية +- للدروس القائمة على المشاريع، أدلة خطوة بخطوة حول كيفية بناء المشروع +- اختبارات للتحقق من الفهم - تحدٍ -- قراءات تكملية -- مهمة -- [اختبار بعد المحاضرة](https://ff-quizzes.netlify.app/en/ml/) +- قراءة تكملية +- واجب +- [اختبار ما بعد المحاضرة](https://ff-quizzes.netlify.app/en/ml/) -> **ملاحظة حول اللغات**: تُكتب هذه الدروس أساسًا بلغة Python، لكن العديد منها متوفر أيضًا بلغة R. لإكمال درس R، اذهب إلى مجلد `/solution` وابحث عن دروس R. تتضمن ملفات بلاحقة .rmd والتي تمثل ملف **R Markdown** الذي يمكن تعريفه ببساطة على أنه تضمين لـ `code chunks` (بلغة R أو لغات أخرى) و`YAML header` (الذي يوجّه كيفية تنسيق المخرجات مثل PDF) داخل `Markdown document`. وبهذا، فإنه يعمل كإطار تأليف نموذجي لعلوم البيانات لأنه يسمح لك بدمج كودك ومخرجاته وأفكارك عبر كتابتها في Markdown. علاوة على ذلك، يمكن تحويل مستندات R Markdown إلى صيغ إخراج مثل PDF أو HTML أو Word. +> **ملاحظة حول اللغات**: تم كتابة هذه الدروس في المقام الأول بلغة Python، لكن العديد منها متاح أيضًا بلغة R. لإكمال درس R، انتقل إلى مجلد `/solution` وابحث عن دروس R. تتضمن امتداد .rmd الذي يمثل ملف **R Markdown** والذي يمكن تعريفه ببساطة على أنه تضمين لـ `code chunks` (بلغة R أو لغات أخرى) و `YAML header` (الذي يوجّه كيفية تنسيق المخرجات مثل PDF) في `Markdown document`. لذلك، يعمل كإطار تأليف نموذجي لعلم البيانات لأنه يسمح لك بدمج كودك ومخرجاته وأفكارك عن طريق كتابتها في Markdown. علاوة على ذلك، يمكن عرض مستندات R Markdown إلى صيغ إخراج مثل PDF أو HTML أو Word. -> **ملاحظة حول الاختبارات**: تحتوي جميع الاختبارات على [مجلد Quiz App](../../quiz-app)، بإجمالي 52 اختبارًا كل منها مكون من ثلاثة أسئلة. ترتبط هذه الاختبارات من داخل الدروس لكن يمكن تشغيل تطبيق الاختبارات محليًا؛ اتبع التعليمات في مجلد `quiz-app` لاستضافته محليًا أو نشره على Azure. +> **ملاحظة حول الاختبارات**: جميع الاختبارات موجودة في [مجلد تطبيق الاختبار](../../quiz-app)، لعدد إجمالي 52 اختبارًا، كل منها يحتوي على ثلاثة أسئلة. يتم ربطها من داخل الدروس لكن يمكن تشغيل تطبيق الاختبار محليًا؛ اتبع التعليمات في مجلد `quiz-app` لاستضافته محليًا أو نشره على Azure. -| Lesson Number | Topic | Lesson Grouping | Learning Objectives | Linked Lesson | Author | +| رقم الدرس | الموضوع | مجموعة الدروس | أهداف التعلم | الدرس المرتبط | المؤلف | | :-----------: | :------------------------------------------------------------: | :-------------------------------------------------: | ------------------------------------------------------------------------------------------------------------------------------- | :--------------------------------------------------------------------------------------------------------------------------------------: | :--------------------------------------------------: | -| 01 | مقدمة في التعلم الآلي | [مقدمة](1-Introduction/README.md) | تعرّف على المفاهيم الأساسية خلف التعلم الآلي | [درس](1-Introduction/1-intro-to-ML/README.md) | محمد | -| 02 | تاريخ التعلم الآلي | [مقدمة](1-Introduction/README.md) | تعرّف على تاريخ هذا المجال | [درس](1-Introduction/2-history-of-ML/README.md) | جين وإيمي | -| 03 | العدالة والتعلم الآلي | [مقدمة](1-Introduction/README.md) | ما هي القضايا الفلسفية المهمة المتعلقة بالعدالة التي ينبغي على الطلاب مراعاتها عند بناء وتطبيق نماذج التعلم الآلي؟ | [درس](1-Introduction/3-fairness/README.md) | تومومي | -| 04 | تقنيات التعلم الآلي | [مقدمة](1-Introduction/README.md) | ما التقنيات التي يستخدمها باحثو التعلم الآلي لبناء النماذج؟ | [درس](1-Introduction/4-techniques-of-ML/README.md) | كريس وجين | -| 05 | مقدمة في الانحدار | [الانحدار](2-Regression/README.md) | ابدأ باستخدام Python وScikit-learn لنماذج الانحدار | [Python](2-Regression/1-Tools/README.md) • [R](../../2-Regression/1-Tools/solution/R/lesson_1.html) | جين • إريك وانجاو | -| 06 | أسعار اليقطين في أمريكا الشمالية 🎃 | [الانحدار](2-Regression/README.md) | تصوّر ونظّف البيانات استعدادًا للتعلم الآلي | [Python](2-Regression/2-Data/README.md) • [R](../../2-Regression/2-Data/solution/R/lesson_2.html) | جين • إريك وانجاو | -| 07 | أسعار اليقطين في أمريكا الشمالية 🎃 | [الانحدار](2-Regression/README.md) | بناء نماذج انحدار خطية ومتعددة الحدود | [Python](2-Regression/3-Linear/README.md) • [R](../../2-Regression/3-Linear/solution/R/lesson_3.html) | جين وديمتري • إريك وانجاو | -| 08 | أسعار اليقطين في أمريكا الشمالية 🎃 | [الانحدار](2-Regression/README.md) | بناء نموذج انحدار لوجستي | [Python](2-Regression/4-Logistic/README.md) • [R](../../2-Regression/4-Logistic/solution/R/lesson_4.html) | جين • إريك وانجاو | -| 09 | تطبيق ويب 🔌 | [تطبيق ويب](3-Web-App/README.md) | بناء تطبيق ويب لاستخدام نموذجك المدرب | [Python](3-Web-App/1-Web-App/README.md) | جين | -| 10 | مقدمة في التصنيف | [التصنيف](4-Classification/README.md) | نظّف وحضّر وصوّر بياناتك؛ مقدمة في التصنيف | [Python](4-Classification/1-Introduction/README.md) • [R](../../4-Classification/1-Introduction/solution/R/lesson_10.html) | جين وكاسي • إريك وانجاو | -| 11 | أطباق آسيوية وهندية شهية 🍜 | [التصنيف](4-Classification/README.md) | مقدمة إلى المصنّفات | [Python](4-Classification/2-Classifiers-1/README.md) • [R](../../4-Classification/2-Classifiers-1/solution/R/lesson_11.html) | جين وكاسي • إريك وانجاو | -| 12 | أطباق آسيوية وهندية شهية 🍜 | [التصنيف](4-Classification/README.md) | المزيد من المصنّفات | [Python](4-Classification/3-Classifiers-2/README.md) • [R](../../4-Classification/3-Classifiers-2/solution/R/lesson_12.html) | جين وكاسي • إريك وانجاو | -| 13 | أطباق آسيوية وهندية شهية 🍜 | [التصنيف](4-Classification/README.md) | بناء تطبيق ويب للتوصية باستخدام نموذجك | [Python](4-Classification/4-Applied/README.md) | جين | -| 14 | مقدمة في التجميع | [التجميع](5-Clustering/README.md) | نظّف وحضّر وصوّر بياناتك؛ مقدمة في التجميع | [Python](5-Clustering/1-Visualize/README.md) • [R](../../5-Clustering/1-Visualize/solution/R/lesson_14.html) | جين • إريك وانجاو | -| 15 | استكشاف الأذواق الموسيقية النيجيرية 🎧 | [التجميع](5-Clustering/README.md) | استكشاف طريقة التجميع K-Means | [Python](5-Clustering/2-K-Means/README.md) • [R](../../5-Clustering/2-K-Means/solution/R/lesson_15.html) | جين • إريك وانجاو | -| 16 | مقدمة في معالجة اللغة الطبيعية ☕️ | [معالجة اللغة الطبيعية](6-NLP/README.md) | تعرّف على أساسيات معالجة اللغة الطبيعية من خلال بناء روبوت بسيط | [Python](6-NLP/1-Introduction-to-NLP/README.md) | ستيفن | -| 17 | مهام معالجة اللغة الشائعة ☕️ | [معالجة اللغة الطبيعية](6-NLP/README.md) | عمّق معرفتك في معالجة اللغة الطبيعية بفهم المهام الشائعة المطلوبة عند التعامل مع تراكيب اللغة | [Python](6-NLP/2-Tasks/README.md) | ستيفن | -| 18 | الترجمة وتحليل المشاعر ♥️ | [معالجة اللغة الطبيعية](6-NLP/README.md) | الترجمة وتحليل المشاعر باستخدام أعمال جاين أوستن | [Python](6-NLP/3-Translation-Sentiment/README.md) | ستيفن | -| 19 | فنادق رومانسية في أوروبا ♥️ | [معالجة اللغة الطبيعية](6-NLP/README.md) | تحليل المشاعر لمراجعات الفنادق 1 | [Python](6-NLP/4-Hotel-Reviews-1/README.md) | ستيفن | -| 20 | فنادق رومانسية في أوروبا ♥️ | [معالجة اللغة الطبيعية](6-NLP/README.md) | تحليل المشاعر لمراجعات الفنادق 2 | [Python](6-NLP/5-Hotel-Reviews-2/README.md) | ستيفن | -| 21 | مقدمة في التنبؤ بالسلاسل الزمنية | [السلاسل الزمنية](7-TimeSeries/README.md) | مقدمة في التنبؤ بالسلاسل الزمنية | [Python](7-TimeSeries/1-Introduction/README.md) | فرانشيسكا | -| 22 | ⚡️ استهلاك الطاقة العالمي ⚡️ - التنبؤ بالسلاسل الزمنية باستخدام ARIMA | [السلاسل الزمنية](7-TimeSeries/README.md) | التنبؤ بالسلاسل الزمنية باستخدام ARIMA | [Python](7-TimeSeries/2-ARIMA/README.md) | فرانشيسكا | -| 23 | ⚡️ استهلاك الطاقة العالمي ⚡️ - التنبؤ بالسلاسل الزمنية باستخدام SVR | [السلاسل الزمنية](7-TimeSeries/README.md) | التنبؤ بالسلاسل الزمنية باستخدام Support Vector Regressor | [Python](7-TimeSeries/3-SVR/README.md) | أنيربان | -| 24 | مقدمة في التعلم المعزز | [التعلم المعزز](8-Reinforcement/README.md) | مقدمة في التعلم المعزز باستخدام Q-Learning | [Python](8-Reinforcement/1-QLearning/README.md) | ديمتري | -| 25 | ساعد بيتر على تجنب الذئب! 🐺 | [التعلم المعزز](8-Reinforcement/README.md) | بيئة Gym للتعلم المعزز | [Python](8-Reinforcement/2-Gym/README.md) | ديمتري | -| Postscript | سيناريوهات وتطبيقات التعلم الآلي في العالم الحقيقي | [التعلم الآلي في العالم الحقيقي](9-Real-World/README.md) | تطبيقات حقيقية مثيرة ومكشفة للتعلم الآلي التقليدي | [درس](9-Real-World/1-Applications/README.md) | الفريق | -| Postscript | تصحيح نماذج التعلم الآلي باستخدام لوحة RAI | [التعلم الآلي في العالم الحقيقي](9-Real-World/README.md) | تصحيح نماذج التعلم الآلي باستخدام مكونات لوحة Responsible AI | [درس](9-Real-World/2-Debugging-ML-Models/README.md) | روث ياكوبو | +| 01 | مقدمة في تعلم الآلة | [مقدمة](1-Introduction/README.md) | تعلّم المفاهيم الأساسية وراء تعلم الآلة | [الدرس](1-Introduction/1-intro-to-ML/README.md) | Muhammad | +| 02 | تاريخ تعلم الآلة | [مقدمة](1-Introduction/README.md) | تعرّف على التاريخ الكامن وراء هذا المجال | [الدرس](1-Introduction/2-history-of-ML/README.md) | Jen و Amy | +| 03 | العدالة وتعلم الآلة | [مقدمة](1-Introduction/README.md) | ما هي القضايا الفلسفية الهامة حول العدالة التي يجب أن يأخذها الطلاب بعين الاعتبار عند بناء وتطبيق نماذج تعلم الآلة؟ | [الدرس](1-Introduction/3-fairness/README.md) | Tomomi | +| 04 | تقنيات تعلم الآلة | [مقدمة](1-Introduction/README.md) | ما هي التقنيات التي يستخدمها باحثو تعلم الآلة لبناء النماذج؟ | [الدرس](1-Introduction/4-techniques-of-ML/README.md) | Chris و Jen | +| 05 | مقدمة في الانحدار | [الانحدار](2-Regression/README.md) | ابدأ مع Python و Scikit-learn لنماذج الانحدار | [Python](2-Regression/1-Tools/README.md) • [R](../../2-Regression/1-Tools/solution/R/lesson_1.html) | Jen • Eric Wanjau | +| 06 | أسعار اليقطين في أمريكا الشمالية 🎃 | [الانحدار](2-Regression/README.md) | تصور ونظّف البيانات كتحضير لتعلم الآلة | [Python](2-Regression/2-Data/README.md) • [R](../../2-Regression/2-Data/solution/R/lesson_2.html) | Jen • Eric Wanjau | +| 07 | أسعار اليقطين في أمريكا الشمالية 🎃 | [الانحدار](2-Regression/README.md) | بناء نماذج الانحدار الخطي والمتعدد الحدود | [Python](2-Regression/3-Linear/README.md) • [R](../../2-Regression/3-Linear/solution/R/lesson_3.html) | Jen و Dmitry • Eric Wanjau | +| 08 | أسعار اليقطين في أمريكا الشمالية 🎃 | [الانحدار](2-Regression/README.md) | بناء نموذج الانحدار اللوجستي | [Python](2-Regression/4-Logistic/README.md) • [R](../../2-Regression/4-Logistic/solution/R/lesson_4.html) | Jen • Eric Wanjau | +| 09 | تطبيق ويب 🔌 | [تطبيق ويب](3-Web-App/README.md) | بناء تطبيق ويب لاستخدام نموذجك المدرب | [Python](3-Web-App/1-Web-App/README.md) | Jen | +| 10 | مقدمة في التصنيف | [التصنيف](4-Classification/README.md) | نظّف، حضّر، وصوّر بياناتك؛ مقدمة في التصنيف | [Python](4-Classification/1-Introduction/README.md) • [R](../../4-Classification/1-Introduction/solution/R/lesson_10.html) | Jen و Cassie • Eric Wanjau | +| 11 | مأكولات آسيوية وهندية لذيذة 🍜 | [التصنيف](4-Classification/README.md) | مقدمة للمصنّفات | [Python](4-Classification/2-Classifiers-1/README.md) • [R](../../4-Classification/2-Classifiers-1/solution/R/lesson_11.html) | Jen و Cassie • Eric Wanjau | +| 12 | مأكولات آسيوية وهندية لذيذة 🍜 | [التصنيف](4-Classification/README.md) | المزيد من المصنّفات | [Python](4-Classification/3-Classifiers-2/README.md) • [R](../../4-Classification/3-Classifiers-2/solution/R/lesson_12.html) | Jen و Cassie • Eric Wanjau | +| 13 | مأكولات آسيوية وهندية لذيذة 🍜 | [التصنيف](4-Classification/README.md) | بناء تطبيق ويب موصيّ باستخدام نموذجك | [Python](4-Classification/4-Applied/README.md) | Jen | +| 14 | مقدمة في التجميع | [التجميع](5-Clustering/README.md) | نظّف، حضّر، وصوّر بياناتك؛ مقدمة في التجميع | [Python](5-Clustering/1-Visualize/README.md) • [R](../../5-Clustering/1-Visualize/solution/R/lesson_14.html) | Jen • Eric Wanjau | +| 15 | استكشاف الأذواق الموسيقية النيجيرية 🎧 | [التجميع](5-Clustering/README.md) | استكشاف طريقة التجميع K-Means | [Python](5-Clustering/2-K-Means/README.md) • [R](../../5-Clustering/2-K-Means/solution/R/lesson_15.html) | Jen • Eric Wanjau | +| 16 | مقدمة في معالجة اللغة الطبيعية ☕️ | [معالجة اللغة الطبيعية](6-NLP/README.md) | تعلّم أساسيات معالجة اللغة الطبيعية ببناء روبوت بسيط | [Python](6-NLP/1-Introduction-to-NLP/README.md) | Stephen | +| 17 | مهام معالجة اللغة الشائعة ☕️ | [معالجة اللغة الطبيعية](6-NLP/README.md) | تعمّق في معرفتك بمعالجة اللغة من خلال فهم المهام الشائعة المطلوبة عند التعامل مع هياكل اللغة | [Python](6-NLP/2-Tasks/README.md) | Stephen | +| 18 | الترجمة وتحليل المشاعر ♥️ | [معالجة اللغة الطبيعية](6-NLP/README.md) | الترجمة وتحليل المشاعر مع Jane Austen | [Python](6-NLP/3-Translation-Sentiment/README.md) | Stephen | +| 19 | فنادق رومانسية في أوروبا ♥️ | [معالجة اللغة الطبيعية](6-NLP/README.md) | تحليل المشاعر مع مراجعات فنادق 1 | [Python](6-NLP/4-Hotel-Reviews-1/README.md) | Stephen | +| 20 | فنادق رومانسية في أوروبا ♥️ | [معالجة اللغة الطبيعية](6-NLP/README.md) | تحليل المشاعر مع مراجعات فنادق 2 | [Python](6-NLP/5-Hotel-Reviews-2/README.md) | Stephen | +| 21 | مقدمة في التنبؤ بالسلاسل الزمنية | [السلاسل الزمنية](7-TimeSeries/README.md) | مقدمة في التنبؤ بالسلاسل الزمنية | [Python](7-TimeSeries/1-Introduction/README.md) | Francesca | +| 22 | ⚡️ استهلاك الطاقة العالمي ⚡️ - التنبؤ بالسلاسل الزمنية باستخدام ARIMA | [السلاسل الزمنية](7-TimeSeries/README.md) | التنبؤ بالسلاسل الزمنية باستخدام ARIMA | [Python](7-TimeSeries/2-ARIMA/README.md) | Francesca | +| 23 | ⚡️ استهلاك الطاقة العالمي ⚡️ - التنبؤ بالسلاسل الزمنية باستخدام SVR | [السلاسل الزمنية](7-TimeSeries/README.md) | التنبؤ بالسلاسل الزمنية باستخدام Support Vector Regressor | [Python](7-TimeSeries/3-SVR/README.md) | Anirban | +| 24 | مقدمة في التعلم التعزيزي | [التعلم التعزيزي](8-Reinforcement/README.md) | مقدمة في التعلم التعزيزي باستخدام Q-Learning | [Python](8-Reinforcement/1-QLearning/README.md) | Dmitry | +| 25 | ساعد بيتر على تجنب الذئب! 🐺 | [التعلم التعزيزي](8-Reinforcement/README.md) | بيئة Gym للتعلم التعزيزي | [Python](8-Reinforcement/2-Gym/README.md) | Dmitry | +| ملحق | سيناريوهات وتطبيقات تعلم الآلة في العالم الحقيقي | [ML in the Wild](9-Real-World/README.md) | تطبيقات مثيرة وكاشفة في العالم الحقيقي لتعلم الآلة الكلاسيكي | [الدرس](9-Real-World/1-Applications/README.md) | الفريق | +| ملحق | تصحيح النماذج في تعلم الآلة باستخدام لوحة RAI | [ML in the Wild](9-Real-World/README.md) | تصحيح نماذج تعلم الآلة باستخدام مكونات لوحة معلومات Responsible AI | [الدرس](9-Real-World/2-Debugging-ML-Models/README.md) | Ruth Yakubu | > [اعثر على جميع الموارد الإضافية لهذه الدورة في مجموعة Microsoft Learn الخاصة بنا](https://learn.microsoft.com/en-us/collections/qrqzamz1nn2wx3?WT.mc_id=academic-77952-bethanycheum) ## الوصول دون اتصال -يمكنك تشغيل هذه الوثائق دون اتصال باستخدام [Docsify](https://docsify.js.org/#/). قم بعمل fork لهذا المستودع، [ثبّت Docsify](https://docsify.js.org/#/quickstart) على جهازك المحلي، ثم في المجلد الجذري لهذا المستودع، اكتب `docsify serve`. سيتم تقديم الموقع على المنفذ 3000 على مضيفك المحلي: `localhost:3000`. +يمكنك تشغيل هذه الوثائق دون اتصال باستخدام [Docsify](https://docsify.js.org/#/). قم بفورك لهذا المستودع، [قم بتثبيت Docsify](https://docsify.js.org/#/quickstart) على جهازك المحلي، ثم في المجلد الجذر لهذا المستودع اكتب `docsify serve`. سيتم تقديم الموقع على المنفذ 3000 على مضيفك المحلي: `localhost:3000`. ## ملفات PDF -اعثر على ملف PDF للمناهج مع الروابط [هنا](https://microsoft.github.io/ML-For-Beginners/pdf/readme.pdf). +اعثر على ملف PDF للمنهج مع روابط [هنا](https://microsoft.github.io/ML-For-Beginners/pdf/readme.pdf). ## 🎒 دورات أخرى -يقدّم فريقنا دورات أخرى! اطلع على: +فريقنا يقدم دورات أخرى! اطلع على: ### LangChain @@ -176,7 +176,7 @@ CO_OP_TRANSLATOR_METADATA: [![AZD للمبتدئين](https://img.shields.io/badge/AZD%20for%20Beginners-0078D4?style=for-the-badge&labelColor=E5E7EB&color=0078D4)](https://github.com/microsoft/AZD-for-beginners?WT.mc_id=academic-105485-koreyst) [![Edge AI للمبتدئين](https://img.shields.io/badge/Edge%20AI%20for%20Beginners-00B8E4?style=for-the-badge&labelColor=E5E7EB&color=00B8E4)](https://github.com/microsoft/edgeai-for-beginners?WT.mc_id=academic-105485-koreyst) [![MCP للمبتدئين](https://img.shields.io/badge/MCP%20for%20Beginners-009688?style=for-the-badge&labelColor=E5E7EB&color=009688)](https://github.com/microsoft/mcp-for-beginners?WT.mc_id=academic-105485-koreyst) -[![AI Agents للمبتدئين](https://img.shields.io/badge/AI%20Agents%20for%20Beginners-00C49A?style=for-the-badge&labelColor=E5E7EB&color=00C49A)](https://github.com/microsoft/ai-agents-for-beginners?WT.mc_id=academic-105485-koreyst) +[![وكلاء AI للمبتدئين](https://img.shields.io/badge/AI%20Agents%20for%20Beginners-00C49A?style=for-the-badge&labelColor=E5E7EB&color=00C49A)](https://github.com/microsoft/ai-agents-for-beginners?WT.mc_id=academic-105485-koreyst) --- @@ -200,18 +200,18 @@ CO_OP_TRANSLATOR_METADATA: --- ### سلسلة Copilot -[![Copilot للبرمجة المرافقة بالذكاء الاصطناعي](https://img.shields.io/badge/Copilot%20for%20AI%20Paired%20Programming-FACC15?style=for-the-badge&labelColor=E5E7EB&color=FACC15)](https://aka.ms/GitHubCopilotAI?WT.mc_id=academic-105485-koreyst) +[![Copilot للبرمجة المشتركة بالذكاء الاصطناعي](https://img.shields.io/badge/Copilot%20for%20AI%20Paired%20Programming-FACC15?style=for-the-badge&labelColor=E5E7EB&color=FACC15)](https://aka.ms/GitHubCopilotAI?WT.mc_id=academic-105485-koreyst) [![Copilot لـ C#/.NET](https://img.shields.io/badge/Copilot%20for%20C%23/.NET-FBBF24?style=for-the-badge&labelColor=E5E7EB&color=FBBF24)](https://github.com/microsoft/mastering-github-copilot-for-dotnet-csharp-developers?WT.mc_id=academic-105485-koreyst) [![مغامرة Copilot](https://img.shields.io/badge/Copilot%20Adventure-FDE68A?style=for-the-badge&labelColor=E5E7EB&color=FDE68A)](https://github.com/microsoft/CopilotAdventures?WT.mc_id=academic-105485-koreyst) ## الحصول على المساعدة -إذا واجهت عائقًا أو كان لديك أي أسئلة حول بناء تطبيقات الذكاء الاصطناعي. انضم إلى المتعلمين والمطورين ذوي الخبرة في المناقشات حول MCP. إنه مجتمع داعم حيث تُرحّب بالأسئلة وتُشارك المعرفة بحرية. +إذا علقت أو كانت لديك أي أسئلة حول بناء تطبيقات الذكاء الاصطناعي، انضم إلى المتعلمين الآخرين والمطورين ذوي الخبرة في مناقشات MCP. إنه مجتمع داعم حيث تُرحب بالأسئلة وتُشارك المعرفة بحرية. -[![Microsoft Foundry Discord](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) +[![خادم Microsoft Foundry على Discord](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) -إذا كانت لديك ملاحظات على المنتج أو واجهت أخطاء أثناء البناء قم بزيارة: +إذا كان لديك ملاحظات حول المنتج أو أخطاء أثناء البناء فقم بزيارة: [![منتدى مطوري Microsoft Foundry](https://img.shields.io/badge/GitHub-Microsoft_Foundry_Developer_Forum-blue?style=for-the-badge&logo=github&color=000000&logoColor=fff)](https://aka.ms/foundry/forum) @@ -219,5 +219,5 @@ CO_OP_TRANSLATOR_METADATA: إخلاء المسؤولية: -تمت ترجمة هذا المستند باستخدام خدمة الترجمة بالذكاء الاصطناعي [Co‑op Translator](https://github.com/Azure/co-op-translator). بينما نسعى إلى الدقة، يُرجى العلم بأن الترجمات الآلية قد تحتوي على أخطاء أو عدم دقة. يجب اعتبار المستند الأصلي بلغته الأصلية المصدر المعتمد والنهائي. للمعلومات الحساسة أو الحرجة، يُنصح بالاستعانة بترجمة بشرية محترفة. نحن غير مسؤولين عن أي سوء فهم أو تفسير ناتج عن استخدام هذه الترجمة. +تمت ترجمة هذه الوثيقة باستخدام خدمة الترجمة الآلية [Co-op Translator] (https://github.com/Azure/co-op-translator). بينما نسعى إلى الدقة، يُرجى العلم أن الترجمات الآلية قد تحتوي على أخطاء أو عدم دقة. يجب اعتبار الوثيقة الأصلية بلغتها الأصلية المصدر الموثوق به. للمعلومات الحرجة، يوصى بالاستعانة بترجمة بشرية مهنية. نحن غير مسؤولين عن أي سوء فهم أو تفسير ينشأ عن استخدام هذه الترجمة. \ No newline at end of file diff --git a/translations/bg/README.md b/translations/bg/README.md index 46790f4cf..da32949c0 100644 --- a/translations/bg/README.md +++ b/translations/bg/README.md @@ -1,86 +1,86 @@ -[![GitHub лиценз](https://img.shields.io/github/license/microsoft/ML-For-Beginners.svg)](https://github.com/microsoft/ML-For-Beginners/blob/master/LICENSE) -[![GitHub сътрудници](https://img.shields.io/github/contributors/microsoft/ML-For-Beginners.svg)](https://GitHub.com/microsoft/ML-For-Beginners/graphs/contributors/) -[![GitHub проблеми](https://img.shields.io/github/issues/microsoft/ML-For-Beginners.svg)](https://GitHub.com/microsoft/ML-For-Beginners/issues/) -[![GitHub pull-заявки](https://img.shields.io/github/issues-pr/microsoft/ML-For-Beginners.svg)](https://GitHub.com/microsoft/ML-For-Beginners/pulls/) -[![PR заявки - добре дошли](https://img.shields.io/badge/PRs-welcome-brightgreen.svg?style=flat-square)](http://makeapullrequest.com) +[![Лиценз на GitHub](https://img.shields.io/github/license/microsoft/ML-For-Beginners.svg)](https://github.com/microsoft/ML-For-Beginners/blob/master/LICENSE) +[![Приносители в GitHub](https://img.shields.io/github/contributors/microsoft/ML-For-Beginners.svg)](https://GitHub.com/microsoft/ML-For-Beginners/graphs/contributors/) +[![Проблеми в GitHub](https://img.shields.io/github/issues/microsoft/ML-For-Beginners.svg)](https://GitHub.com/microsoft/ML-For-Beginners/issues/) +[![Извиквания за pull в GitHub](https://img.shields.io/github/issues-pr/microsoft/ML-For-Beginners.svg)](https://GitHub.com/microsoft/ML-For-Beginners/pulls/) +[![PRs са добре дошли](https://img.shields.io/badge/PRs-welcome-brightgreen.svg?style=flat-square)](http://makeapullrequest.com) -[![GitHub наблюдатели](https://img.shields.io/github/watchers/microsoft/ML-For-Beginners.svg?style=social&label=Watch)](https://GitHub.com/microsoft/ML-For-Beginners/watchers/) -[![GitHub форкове](https://img.shields.io/github/forks/microsoft/ML-For-Beginners.svg?style=social&label=Fork)](https://GitHub.com/microsoft/ML-For-Beginners/network/) -[![GitHub звезди](https://img.shields.io/github/stars/microsoft/ML-For-Beginners.svg?style=social&label=Star)](https://GitHub.com/microsoft/ML-For-Beginners/stargazers/) +[![Наблюдатели в GitHub](https://img.shields.io/github/watchers/microsoft/ML-For-Beginners.svg?style=social&label=Watch)](https://GitHub.com/microsoft/ML-For-Beginners/watchers/) +[![Forks в GitHub](https://img.shields.io/github/forks/microsoft/ML-For-Beginners.svg?style=social&label=Fork)](https://GitHub.com/microsoft/ML-For-Beginners/network/) +[![Звезди в GitHub](https://img.shields.io/github/stars/microsoft/ML-For-Beginners.svg?style=social&label=Star)](https://GitHub.com/microsoft/ML-For-Beginners/stargazers/) -### 🌐 Поддръжка на множество езици +### 🌐 Многоезична поддръжка -#### Поддържа се чрез GitHub Action (автоматично и винаги актуализирано) +#### Поддържа се чрез GitHub Action (автоматизирано и винаги актуално) -[Арабски](../ar/README.md) | [Бенгалски](../bn/README.md) | [Български](./README.md) | [Бирмански (Мианмар)](../my/README.md) | [Китайски (опростен)](../zh/README.md) | [Китайски (традиционен, Хонконг)](../hk/README.md) | [Китайски (традиционен, Макао)](../mo/README.md) | [Китайски (традиционен, Тайван)](../tw/README.md) | [Хърватски](../hr/README.md) | [Чешки](../cs/README.md) | [Датски](../da/README.md) | [Нидерландски](../nl/README.md) | [Естонски](../et/README.md) | [Фински](../fi/README.md) | [Френски](../fr/README.md) | [Немски](../de/README.md) | [Гръцки](../el/README.md) | [Иврит](../he/README.md) | [Хинди](../hi/README.md) | [Унгарски](../hu/README.md) | [Индонезийски](../id/README.md) | [Италиански](../it/README.md) | [Японски](../ja/README.md) | [Каннада](../kn/README.md) | [Корейски](../ko/README.md) | [Литовски](../lt/README.md) | [Малайски](../ms/README.md) | [Малаялам](../ml/README.md) | [Маратхи](../mr/README.md) | [Непали](../ne/README.md) | [Нигерийски Пиджин](../pcm/README.md) | [Норвежки](../no/README.md) | [Персийски (фарси)](../fa/README.md) | [Полски](../pl/README.md) | [Португалски (Бразилия)](../br/README.md) | [Португалски (Португалия)](../pt/README.md) | [Пенджабски (Гурумухи)](../pa/README.md) | [Румънски](../ro/README.md) | [Руски](../ru/README.md) | [Сръбски (кирилица)](../sr/README.md) | [Словашки](../sk/README.md) | [Словенски](../sl/README.md) | [Испански](../es/README.md) | [Суахили](../sw/README.md) | [Шведски](../sv/README.md) | [Тагалог (филипински)](../tl/README.md) | [Тамилски](../ta/README.md) | [Телугу](../te/README.md) | [Тайски](../th/README.md) | [Турски](../tr/README.md) | [Украински](../uk/README.md) | [Урду](../ur/README.md) | [Виетнамски](../vi/README.md) +[Арабски](../ar/README.md) | [Бенгалски](../bn/README.md) | [Български](./README.md) | [Бирмански (Мианмар)](../my/README.md) | [Китайски (опростен)](../zh/README.md) | [Китайски (традиционен, Хонконг)](../hk/README.md) | [Китайски (традиционен, Макао)](../mo/README.md) | [Китайски (традиционен, Тайван)](../tw/README.md) | [Хърватски](../hr/README.md) | [Чешки](../cs/README.md) | [Датски](../da/README.md) | [Нидерландски](../nl/README.md) | [Естонски](../et/README.md) | [Фински](../fi/README.md) | [Френски](../fr/README.md) | [Немски](../de/README.md) | [Гръцки](../el/README.md) | [Иврит](../he/README.md) | [Хинди](../hi/README.md) | [Унгарски](../hu/README.md) | [Индонезийски](../id/README.md) | [Италиански](../it/README.md) | [Японски](../ja/README.md) | [Каннада](../kn/README.md) | [Корейски](../ko/README.md) | [Литовски](../lt/README.md) | [Малайски](../ms/README.md) | [Малаялам](../ml/README.md) | [Марати](../mr/README.md) | [Непалски](../ne/README.md) | [Нигерийски пиджин](../pcm/README.md) | [Норвежки](../no/README.md) | [Персийски (фарси)](../fa/README.md) | [Полски](../pl/README.md) | [Португалски (Бразилия)](../br/README.md) | [Португалски (Португалия)](../pt/README.md) | [Пенджабски (Гурмухи)](../pa/README.md) | [Румънски](../ro/README.md) | [Руски](../ru/README.md) | [Сръбски (кирилица)](../sr/README.md) | [Словашки](../sk/README.md) | [Словенски](../sl/README.md) | [Испански](../es/README.md) | [Свахили](../sw/README.md) | [Шведски](../sv/README.md) | [Тагалог (филипински)](../tl/README.md) | [Тамилски](../ta/README.md) | [Телугу](../te/README.md) | [Тайски](../th/README.md) | [Турски](../tr/README.md) | [Украински](../uk/README.md) | [Урду](../ur/README.md) | [Виетнамски](../vi/README.md) #### Присъединете се към нашата общност -[![Discord на Microsoft Foundry](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) +[![Microsoft Foundry Discord](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) -Имаме текуща серия в Discord „Научете с AI“, научете повече и се присъединете към нас на [Серия 'Научете с AI'](https://aka.ms/learnwithai/discord) от 18 - 30 септември 2025 г. Ще получите съвети и трикове за използване на GitHub Copilot за Наука за данни. +Имаме поредица в Discord „Научи с ИИ“, която е в ход — научете повече и се присъединете към нас на [Серия „Научи с ИИ“](https://aka.ms/learnwithai/discord) от 18 до 30 септември 2025 г. Ще получите съвети и трикове за използване на GitHub Copilot за наука за данните. -![Серия Научете с AI](../../translated_images/3.9b58fd8d6c373c20c588c5070c4948a826ab074426c28ceb5889641294373dfc.bg.png) +![Серия „Научи с ИИ“](../../translated_images/3.9b58fd8d6c373c20.bg.png) # Машинно обучение за начинаещи - Учебна програма -> 🌍 Пътувайте по целия свят, докато изследваме Машинното обучение чрез световните култури 🌍 +> 🌍 Пътувайте по целия свят, докато изследваме машинното обучение чрез световните култури 🌍 -Cloud Advocates в Microsoft с удоволствие предлагат 12-седмична учебна програма от 26 урока, изцяло посветена на **Машинното обучение**. В тази учебна програма ще научите за това, което понякога се нарича **класическо машинно обучение**, като използвате основно Scikit-learn като библиотека и избягвате дълбокото обучение, което е разгледано в нашата [Учебна програма 'AI за начинаещи'](https://aka.ms/ai4beginners). Сдвоете тези уроци и с нашата ['Наука за данни за начинаещи' учебна програма](https://aka.ms/ds4beginners) също! +Cloud Advocates в Microsoft с удоволствие предлагат 12-седмична, 26-урочна учебна програма, посветена на **Machine Learning**. В тази учебна програма ще научите за това, което понякога се нарича **класическо машинно обучение**, използвайки основно Scikit-learn като библиотека и избягвайки дълбокото обучение, което е разгледано в нашата [учебна програма „AI for Beginners“](https://aka.ms/ai4beginners). Комбинирайте тези уроци и с нашата [учебна програма „Data Science for Beginners“](https://aka.ms/ds4beginners)! -Пътувайте с нас по света, докато прилагаме тези класически техники към данни от много райони на света. Всеки урок включва предварителни и след-урочни тестове, писмени инструкции за завършване на урока, решение, задача и други. Нашият проектно-базиран подход ви позволява да учите чрез изграждане — доказан начин новите умения да се усвоят. +Пътувайте с нас по света, докато прилагаме тези класически техники към данни от множество райони на света. Всеки урок включва тестове преди и след урока, писмени инструкции за завършване на урока, решение, задание и още. Нашият проектно-ориентиран подход ви позволява да учите, докато изграждате — доказан начин новите умения да „залепнат“. -**✍️ Големи благодарности на нашите автори** Jen Looper, Stephen Howell, Francesca Lazzeri, Tomomi Imura, Cassie Breviu, Dmitry Soshnikov, Chris Noring, Anirban Mukherjee, Ornella Altunyan, Ruth Yakubu и Amy Boyd +**✍️ Сърдечни благодарности на нашите автори** Jen Looper, Stephen Howell, Francesca Lazzeri, Tomomi Imura, Cassie Breviu, Dmitry Soshnikov, Chris Noring, Anirban Mukherjee, Ornella Altunyan, Ruth Yakubu и Amy Boyd **🎨 Благодарности и на нашите илюстратори** Tomomi Imura, Dasani Madipalli и Jen Looper -**🙏 Специални благодарности 🙏 на нашите Microsoft Student Ambassador автори, рецензенти и сътрудници по съдържанието**, по-специално Rishit Dagli, Muhammad Sakib Khan Inan, Rohan Raj, Alexandru Petrescu, Abhishek Jaiswal, Nawrin Tabassum, Ioan Samuila и Snigdha Agarwal +**🙏 Специални благодарности 🙏 на нашите Microsoft Student Ambassador автори, рецензенти и допринесли със съдържание**, по-специално Rishit Dagli, Muhammad Sakib Khan Inan, Rohan Raj, Alexandru Petrescu, Abhishek Jaiswal, Nawrin Tabassum, Ioan Samuila и Snigdha Agarwal -**🤩 Допълнителни благодарности на Microsoft Student Ambassadors Eric Wanjau, Jasleen Sondhi и Vidushi Gupta за нашите R уроци!** +**🤩 Допълнителна благодарност към Microsoft Student Ambassadors Eric Wanjau, Jasleen Sondhi и Vidushi Gupta за нашите R уроци!** # Първи стъпки Следвайте тези стъпки: -1. **Направете форк на хранилището**: Кликнете върху бутона "Fork" в горния десен ъгъл на тази страница. +1. **Направете Fork на хранилището**: Кликнете върху бутона „Fork“ в горния десен ъгъл на тази страница. 2. **Клонирайте хранилището**: `git clone https://github.com/microsoft/ML-For-Beginners.git` -> [Намерете всички допълнителни ресурси за този курс в нашата колекция Microsoft Learn](https://learn.microsoft.com/en-us/collections/qrqzamz1nn2wx3?WT.mc_id=academic-77952-bethanycheum) +> [намерете всички допълнителни ресурси за този курс в нашата колекция в Microsoft Learn](https://learn.microsoft.com/en-us/collections/qrqzamz1nn2wx3?WT.mc_id=academic-77952-bethanycheum) -> 🔧 **Нужна помощ?** Проверете нашето [Ръководство за отстраняване на неизправности](TROUBLESHOOTING.md) за решения на често срещани проблеми при инсталиране, настройка и стартиране на уроци. +> 🔧 **Нуждаете се от помощ?** Проверете нашето [Ръководство за отстраняване на проблеми](TROUBLESHOOTING.md) за решения на често срещани проблеми при инсталиране, настройка и изпълнение на уроците. -**[Студенти](https://aka.ms/student-page)**, за да използвате тази учебна програма, направете форк на цялото хранилище в своя GitHub акаунт и изпълнявайте упражненията сами или в група: +**[Студенти](https://aka.ms/student-page)**, за да използвате тази учебна програма, форкнете цялото репо във вашия собствен GitHub акаунт и завършете упражненията сами или в група: - Започнете с предварителен тест преди лекцията. -- Прочетете лекцията и изпълнете дейностите, спирайки и обмисляйки всеки контрол на знанията. -- Опитайте да създадете проектите, като разберете уроците вместо да стартирате кода за решение; този код обаче е наличен в папките `/solution` във всеки урок, ориентиран към проект. -- Направете следлекционния тест. +- Прочетете лекцията и изпълнете дейностите, спирайки и размишлявайки при всяка проверка на знанията. +- Опитайте се да създадете проектите, като разбирате уроците, вместо просто да стартирате решението; това решение обаче е налично в папките `/solution` във всеки урок, ориентиран към проект. +- Направете теста след лекцията. - Завършете предизвикателството. -- Завършете задачата. -- След като завършите група уроци, посетете [Дискусионния форум](https://github.com/microsoft/ML-For-Beginners/discussions) и "учете на глас", като попълните подходящата рубрика PAT. 'PAT' е Инструмент за оценяване на напредъка (Progress Assessment Tool), който представлява рубрика, която попълвате, за да подпомогнете ученето си. Можете също да реагирате на други PAT, за да учим заедно. +- Изпълнете задачата. +- След като завършите група от уроци, посетете [Дискусионния борд](https://github.com/microsoft/ML-For-Beginners/discussions) и „учете на глас“, като попълните подходящата рубрика PAT. 'PAT' е Progress Assessment Tool — рубрика, която попълвате, за да задълбочите обучението си. Можете също така да реагирате на други PAT, за да учим заедно. -> За допълнително изучаване препоръчваме да следвате тези [модули и учебни пътеки на Microsoft Learn](https://docs.microsoft.com/en-us/users/jenlooper-2911/collections/k7o7tg1gp306q4?WT.mc_id=academic-77952-leestott). +> За по-нататъшно обучение, препоръчваме да следвате тези модули и учебни пътеки в [Microsoft Learn](https://docs.microsoft.com/en-us/users/jenlooper-2911/collections/k7o7tg1gp306q4?WT.mc_id=academic-77952-leestott). -**Учители**, ние сме [включили някои предложения](for-teachers.md) относно това как да използвате тази учебна програма. +**Учители**, включили сме [някои предложения](for-teachers.md) за това как да използвате тази учебна програма. --- -## Видео ръководства +## Видео уроци -Някои от уроците са налични като кратки видеа. Можете да намерите всички тях в самите уроци или в [плейлиста "ML за начинаещи" в канала на Microsoft Developer в YouTube](https://aka.ms/ml-beginners-videos), като кликнете върху изображението по-долу. +Някои от уроците са налични като кратки видео форми. Можете да ги намерите в самите уроци или в [плейлиста ML for Beginners в канала Microsoft Developer в YouTube](https://aka.ms/ml-beginners-videos), като кликнете върху изображението по-долу. -[![Банер ML за начинаещи](../../translated_images/ml-for-beginners-video-banner.63f694a100034bc6251134294459696e070a3a9a04632e9fe6a24aa0de4a7384.bg.png)](https://aka.ms/ml-beginners-videos) +[![Банер 'ML for beginners'](../../translated_images/ml-for-beginners-video-banner.63f694a100034bc6.bg.png)](https://aka.ms/ml-beginners-videos) --- @@ -88,7 +88,7 @@ Cloud Advocates в Microsoft с удоволствие предлагат 12-с [![Промо видео](../../images/ml.gif)](https://youtu.be/Tj1XWrDSYJU) -**Gif от** [Mohit Jaisal](https://linkedin.com/in/mohitjaisal) +**GIF от** [Mohit Jaisal](https://linkedin.com/in/mohitjaisal) > 🎥 Кликнете върху изображението по-горе за видео за проекта и хората, които го създадоха! @@ -96,65 +96,65 @@ Cloud Advocates в Microsoft с удоволствие предлагат 12-с ## Педагогика -При изграждането на тази учебна програма сме избрали две педагогически основи: да бъде практическа и проектно-базирана и да включва чести тестове. Освен това тази учебна програма има обща тематика, която ѝ придава кохезия. +По време на създаването на тази учебна програма избрахме два педагогически принципа: да е практическа и ориентирана към проекти и да включва чести тестове. Освен това тази учебна програма има обща тема, която й придава единство. -Като гарантираме, че съдържанието е свързано с проекти, процесът става по-ангажиращ за студентите и усвояването на концепциите се увеличава. Освен това ниско-рисков тест преди занятие задава намерението на студента към изучаването на тема, докато втори тест след занятието осигурява допълнително задържане. Тази учебна програма е проектирана да бъде гъвкава и забавна и може да се изучава цялата или частично. Проектите започват малки и стават все по-сложни към края на 12-седмичния цикъл. Тази учебна програма включва и допълнение за реални приложения на МЛ, което може да се използва като допълнителна оценка или като основа за дискусия. +Като гарантираме, че съдържанието е свързано с проекти, процесът става по-ангажиращ за студентите и задържането на понятията се увеличава. Освен това подготвителен тест с нисък залог преди занятията задава намерението на студента към изучаването на тема, докато втори тест след занятието осигурява допълнително задържане. Тази учебна програма е проектирана да бъде гъвкава и забавна и може да бъде премината изцяло или частично. Проектите започват малки и стават все по-сложни до края на 12-седмичния цикъл. Тази учебна програма включва и пощриптум за приложенията на ML в реалния свят, който може да се използва като допълнителни кредити или като основа за дискусия. -> Намерете нашите ръководства за [Кодекс на поведение](CODE_OF_CONDUCT.md), [Принос](CONTRIBUTING.md), [Преводи](TRANSLATIONS.md) и [Отстраняване на неизправности](TROUBLESHOOTING.md). Очакваме вашата конструктивна обратна връзка! +> Намерете нашите указания за [Кодекс на поведение](CODE_OF_CONDUCT.md), [Принос](CONTRIBUTING.md), [Преводи](TRANSLATIONS.md) и [Отстраняване на проблеми](TROUBLESHOOTING.md). Очакваме вашата конструктивна обратна връзка! -## Всеки урок включва +## Всяки урок включва -- по желание скично резюме +- по избор sketchnote - по избор допълнително видео -- видео ръководство (само в някои уроци) -- [предварителен тест за загрявка преди лекция](https://ff-quizzes.netlify.app/en/ml/) +- видео разходка (само някои уроци) +- [подгряващ тест преди лекцията](https://ff-quizzes.netlify.app/en/ml/) - писмен урок -- за проектно-базирани уроци, стъпка по стъпка ръководства как да се изгради проектът +- за уроци, базирани на проекти, стъпка по стъпка ръководства за изграждане на проекта - проверки на знанията - предизвикателство - допълнително четиво - задача -- [следлекционен тест](https://ff-quizzes.netlify.app/en/ml/) +- [тест след лекцията](https://ff-quizzes.netlify.app/en/ml/) -> **Бележка относно езиците**: Тези уроци са предимно написани на Python, но много от тях са налични и на R. За да завършите урок на R, отидете в папката `/solution` и потърсете R уроците. Те включват разширение .rmd, което представлява файл на R Markdown — формат, който може да се опише като вграждане на `code chunks` (на R или други езици) и `YAML header` (който указва как да се форматират изходните файлове като PDF) в `Markdown document`. Като такъв, той служи като примерна рамка за авторство за науката за данни, тъй като ви позволява да комбинирате кода си, неговия изход и вашите бележки, като ги записвате в Markdown. Освен това R Markdown документите могат да бъдат рендирани в изходни формати като PDF, HTML или Word. +> **Бележка за езиците**: Тези уроци са предимно написани на Python, но много от тях са налични и на R. За да завършите урок на R, отидете в папката `/solution` и потърсете уроците на R. Те включват разширение .rmd, което представлява **R Markdown** файл, който може просто да се определи като вграждане на `code chunks` (на R или други езици) и `YAML header` (който указва как да се форматират изходи като PDF) в `Markdown document`. Като такъв, той служи като примерна рамка за авторство за наука за данните, тъй като ви позволява да комбинирате своя код, неговия изход и мислите си, като ги записвате в Markdown. Освен това, R Markdown документите могат да се рендерират в изходни формати като PDF, HTML или Word. -> **Бележка относно тестовете**: Всички тестове са в [папката на приложението за тестове](../../quiz-app), общо 52 теста с по три въпроса всеки. Те са свързани от уроците, но приложението за тестове може да се стартира локално; следвайте инструкциите в папката `quiz-app`, за да го хостнете локално или да го разположите в Azure. +> **Бележка за тестовете**: Всички тестове са в [папката Quiz App](../../quiz-app), общо 52 теста по три въпроса всеки. Те са свързани от самите уроци, но quiz app може да се пусне локално; следвайте инструкциите в папката `quiz-app`, за да хостнете локално или да деплойнете в Azure. | Номер на урока | Тема | Групиране на урока | Учебни цели | Свързан урок | Автор | | :-----------: | :------------------------------------------------------------: | :-------------------------------------------------: | ------------------------------------------------------------------------------------------------------------------------------- | :--------------------------------------------------------------------------------------------------------------------------------------: | :--------------------------------------------------: | | 01 | Въведение в машинното обучение | [Въведение](1-Introduction/README.md) | Научете основните концепции зад машинното обучение | [Урок](1-Introduction/1-intro-to-ML/README.md) | Muhammad | -| 02 | История на машинното обучение | [Въведение](1-Introduction/README.md) | Научете историята зад тази област | [Урок](1-Introduction/2-history-of-ML/README.md) | Jen and Amy | -| 03 | Справедливост и машинно обучение | [Въведение](1-Introduction/README.md) | Кои са важните философски въпроси, свързани със справедливостта, които студентите трябва да вземат предвид при изграждането и прилагането на модели за машинно обучение? | [Урок](1-Introduction/3-fairness/README.md) | Tomomi | -| 04 | Техники за машинно обучение | [Въведение](1-Introduction/README.md) | Какви техники използват изследователите по машинно обучение за изграждане на модели? | [Урок](1-Introduction/4-techniques-of-ML/README.md) | Chris and Jen | -| 05 | Въведение в регресията | [Регресия](2-Regression/README.md) | Започнете с Python и Scikit-learn за регресионни модели | [Python](2-Regression/1-Tools/README.md) • [R](../../2-Regression/1-Tools/solution/R/lesson_1.html) | Jen • Eric Wanjau | -| 06 | Цени на тикви в Северна Америка 🎃 | [Регресия](2-Regression/README.md) | Визуализирайте и почистете данните в подготовка за машинно обучение | [Python](2-Regression/2-Data/README.md) • [R](../../2-Regression/2-Data/solution/R/lesson_2.html) | Jen • Eric Wanjau | -| 07 | Цени на тикви в Северна Америка 🎃 | [Регресия](2-Regression/README.md) | Изградете линейни и полиномиални регресионни модели | [Python](2-Regression/3-Linear/README.md) • [R](../../2-Regression/3-Linear/solution/R/lesson_3.html) | Jen and Dmitry • Eric Wanjau | -| 08 | Цени на тикви в Северна Америка 🎃 | [Регресия](2-Regression/README.md) | Изградете логистичен регресионен модел | [Python](2-Regression/4-Logistic/README.md) • [R](../../2-Regression/4-Logistic/solution/R/lesson_4.html) | Jen • Eric Wanjau | -| 09 | Уеб приложение 🔌 | [Уеб приложение](3-Web-App/README.md) | Изградете уеб приложение за използване на вашия обучен модел | [Python](3-Web-App/1-Web-App/README.md) | Jen | -| 10 | Въведение в класификация | [Класификация](4-Classification/README.md) | Почистете, подгответе и визуализирайте данните си; въведение в класификация | [Python](4-Classification/1-Introduction/README.md) • [R](../../4-Classification/1-Introduction/solution/R/lesson_10.html) | Jen and Cassie • Eric Wanjau | -| 11 | Вкусни азиатски и индийски кухни 🍜 | [Класификация](4-Classification/README.md) | Въведение в класификаторите | [Python](4-Classification/2-Classifiers-1/README.md) • [R](../../4-Classification/2-Classifiers-1/solution/R/lesson_11.html) | Jen and Cassie • Eric Wanjau | -| 12 | Вкусни азиатски и индийски кухни 🍜 | [Класификация](4-Classification/README.md) | Още класификатори | [Python](4-Classification/3-Classifiers-2/README.md) • [R](../../4-Classification/3-Classifiers-2/solution/R/lesson_12.html) | Jen and Cassie • Eric Wanjau | -| 13 | Вкусни азиатски и индийски кухни 🍜 | [Класификация](4-Classification/README.md) | Изградете уеб приложение за препоръки, използвайки вашия модел | [Python](4-Classification/4-Applied/README.md) | Jen | -| 14 | Въведение в клъстерирането | [Клъстериране](5-Clustering/README.md) | Почистете, подгответе и визуализирайте данните си; въведение в клъстерирането | [Python](5-Clustering/1-Visualize/README.md) • [R](../../5-Clustering/1-Visualize/solution/R/lesson_14.html) | Jen • Eric Wanjau | -| 15 | Изследване на музикалните вкусове в Нигерия 🎧 | [Клъстериране](5-Clustering/README.md) | Изследвайте метода K-Means за клъстериране | [Python](5-Clustering/2-K-Means/README.md) • [R](../../5-Clustering/2-K-Means/solution/R/lesson_15.html) | Jen • Eric Wanjau | -| 16 | Въведение в обработката на естествен език ☕️ | [Обработка на естествен език](6-NLP/README.md) | Научете основите на обработката на естествен език, като изградите прост бот | [Python](6-NLP/1-Introduction-to-NLP/README.md) | Stephen | -| 17 | Чести задачи в обработката на естествен език ☕️ | [Обработка на естествен език](6-NLP/README.md) | Задълбочете знанията си по обработката на естествен език, като разберете общите задачи, необходими при работа с езикови структури | [Python](6-NLP/2-Tasks/README.md) | Stephen | -| 18 | Превод и анализ на настроенията ♥️ | [Обработка на естествен език](6-NLP/README.md) | Превод и анализ на настроенията с Джейн Остин | [Python](6-NLP/3-Translation-Sentiment/README.md) | Stephen | -| 19 | Романтични хотели в Европа ♥️ | [Обработка на естествен език](6-NLP/README.md) | Анализ на настроенията с ревюта на хотели 1 | [Python](6-NLP/4-Hotel-Reviews-1/README.md) | Stephen | -| 20 | Романтични хотели в Европа ♥️ | [Обработка на естествен език](6-NLP/README.md) | Анализ на настроенията с ревюта на хотели 2 | [Python](6-NLP/5-Hotel-Reviews-2/README.md) | Stephen | -| 21 | Въведение в прогнозиране на времеви редове | [Времеви редове](7-TimeSeries/README.md) | Въведение в прогнозиране на времеви редове | [Python](7-TimeSeries/1-Introduction/README.md) | Francesca | -| 22 | ⚡️ Световна употреба на електроенергия ⚡️ - прогнозиране на времеви редове с ARIMA | [Времеви редове](7-TimeSeries/README.md) | Прогнозиране на времеви редове с ARIMA | [Python](7-TimeSeries/2-ARIMA/README.md) | Francesca | -| 23 | ⚡️ Световна употреба на електроенергия ⚡️ - прогнозиране на времеви редове със SVR | [Времеви редове](7-TimeSeries/README.md) | Прогнозиране на времеви редове със Support Vector Regressor | [Python](7-TimeSeries/3-SVR/README.md) | Anirban | -| 24 | Въведение в обучението чрез подсилване | [Обучение чрез подсилване](8-Reinforcement/README.md) | Въведение в обучението чрез подсилване с Q-Learning | [Python](8-Reinforcement/1-QLearning/README.md) | Dmitry | -| 25 | Помогнете на Питър да избегне вълка! 🐺 | [Обучение чрез подсилване](8-Reinforcement/README.md) | Gym за обучение чрез подсилване | [Python](8-Reinforcement/2-Gym/README.md) | Dmitry | -| Postscript | Сценарии и приложения на ML в реалния свят | [ML в реалния свят](9-Real-World/README.md) | Интересни и показателни приложения в реалния свят на класическото машинно обучение | [Урок](9-Real-World/1-Applications/README.md) | Екип | -| Postscript | Отстраняване на грешки в ML модели с RAI табло | [ML в реалния свят](9-Real-World/README.md) | Отстраняване на грешки в модели на машинно обучение с помощта на компоненти на таблото Responsible AI | [Урок](9-Real-World/2-Debugging-ML-Models/README.md) | Ruth Yakubu | +| 02 | История на машинното обучение | [Въведение](1-Introduction/README.md) | Научете историята, стояща зад тази област | [Урок](1-Introduction/2-history-of-ML/README.md) | Jen and Amy | +| 03 | Справедливост и машинно обучение | [Въведение](1-Introduction/README.md) | Кои са важните философски въпроси, свързани със справедливостта, които студентите трябва да вземат предвид при изграждането и прилагането на ML модели? | [Урок](1-Introduction/3-fairness/README.md) | Tomomi | +| 04 | Техники за машинното обучение | [Въведение](1-Introduction/README.md) | Какви техники използват изследователите в ML за изграждане на ML модели? | [Урок](1-Introduction/4-techniques-of-ML/README.md) | Chris and Jen | +| 05 | Въведение в регресията | [Regression](2-Regression/README.md) | Започнете с Python и Scikit-learn за регресионни модели | [Python](2-Regression/1-Tools/README.md) • [R](../../2-Regression/1-Tools/solution/R/lesson_1.html) | Jen • Eric Wanjau | +| 06 | Цени на тиквите в Северна Америка 🎃 | [Regression](2-Regression/README.md) | Визуализирайте и почистете данните в подготовка за ML | [Python](2-Regression/2-Data/README.md) • [R](../../2-Regression/2-Data/solution/R/lesson_2.html) | Jen • Eric Wanjau | +| 07 | Цени на тиквите в Северна Америка 🎃 | [Regression](2-Regression/README.md) | Изградете линейни и полиномиални регресионни модели | [Python](2-Regression/3-Linear/README.md) • [R](../../2-Regression/3-Linear/solution/R/lesson_3.html) | Jen and Dmitry • Eric Wanjau | +| 08 | Цени на тиквите в Северна Америка 🎃 | [Regression](2-Regression/README.md) | Изградете логистичен регресионен модел | [Python](2-Regression/4-Logistic/README.md) • [R](../../2-Regression/4-Logistic/solution/R/lesson_4.html) | Jen • Eric Wanjau | +| 09 | Уеб приложение 🔌 | [Уеб приложение](3-Web-App/README.md) | Създайте уеб приложение за използване на вашия обучен модел | [Python](3-Web-App/1-Web-App/README.md) | Jen | +| 10 | Въведение в класификацията | [Classification](4-Classification/README.md) | Почистете, подгответе и визуализирайте данните си; въведение в класификация | [Python](4-Classification/1-Introduction/README.md) • [R](../../4-Classification/1-Introduction/solution/R/lesson_10.html) | Jen and Cassie • Eric Wanjau | +| 11 | Вкусни азиатски и индийски кухни 🍜 | [Classification](4-Classification/README.md) | Въведение в класификаторите | [Python](4-Classification/2-Classifiers-1/README.md) • [R](../../4-Classification/2-Classifiers-1/solution/R/lesson_11.html) | Jen and Cassie • Eric Wanjau | +| 12 | Вкусни азиатски и индийски кухни 🍜 | [Classification](4-Classification/README.md) | Още класификатори | [Python](4-Classification/3-Classifiers-2/README.md) • [R](../../4-Classification/3-Classifiers-2/solution/R/lesson_12.html) | Jen and Cassie • Eric Wanjau | +| 13 | Вкусни азиатски и индийски кухни 🍜 | [Classification](4-Classification/README.md) | Създайте уеб приложение за препоръки, използвайки модела си | [Python](4-Classification/4-Applied/README.md) | Jen | +| 14 | Въведение в клъстеризацията | [Clustering](5-Clustering/README.md) | Почистете, подгответе и визуализирайте данните си; въведение в клъстеризацията | [Python](5-Clustering/1-Visualize/README.md) • [R](../../5-Clustering/1-Visualize/solution/R/lesson_14.html) | Jen • Eric Wanjau | +| 15 | Изследване на музикалните вкусове в Нигерия 🎧 | [Clustering](5-Clustering/README.md) | Проучете метода за клъстеризация K-Means | [Python](5-Clustering/2-K-Means/README.md) • [R](../../5-Clustering/2-K-Means/solution/R/lesson_15.html) | Jen • Eric Wanjau | +| 16 | Въведение в обработката на естествен език ☕️ | [Natural language processing](6-NLP/README.md) | Научете основите на NLP, като изградите прост бот | [Python](6-NLP/1-Introduction-to-NLP/README.md) | Stephen | +| 17 | Чести задачи в NLP ☕️ | [Natural language processing](6-NLP/README.md) | Задълбочете знанията си по NLP, като разберете общите задачи, необходими при работа с езикови структури | [Python](6-NLP/2-Tasks/README.md) | Stephen | +| 18 | Превод и анализ на настроенията ♥️ | [Natural language processing](6-NLP/README.md) | Превод и анализ на настроенията с Джейн Остин | [Python](6-NLP/3-Translation-Sentiment/README.md) | Stephen | +| 19 | Романтични хотели в Европа ♥️ | [Natural language processing](6-NLP/README.md) | Анализ на настроенията с хотелски отзиви 1 | [Python](6-NLP/4-Hotel-Reviews-1/README.md) | Stephen | +| 20 | Романтични хотели в Европа ♥️ | [Natural language processing](6-NLP/README.md) | Анализ на настроенията с хотелски отзиви 2 | [Python](6-NLP/5-Hotel-Reviews-2/README.md) | Stephen | +| 21 | Въведение в прогнозиране на времеви редове | [Time series](7-TimeSeries/README.md) | Въведение в прогнозиране на времеви редове | [Python](7-TimeSeries/1-Introduction/README.md) | Francesca | +| 22 | ⚡️ Световна употреба на енергия ⚡️ - time series forecasting with ARIMA | [Time series](7-TimeSeries/README.md) | Прогнозиране на времеви редове с ARIMA | [Python](7-TimeSeries/2-ARIMA/README.md) | Francesca | +| 23 | ⚡️ Световна употреба на енергия ⚡️ - time series forecasting with SVR | [Time series](7-TimeSeries/README.md) | Прогнозиране на времеви редове с Support Vector Regressor | [Python](7-TimeSeries/3-SVR/README.md) | Anirban | +| 24 | Въведение в обучение чрез подсилване | [Обучение чрез подсилване](8-Reinforcement/README.md) | Въведение в обучение чрез подсилване с Q-Learning | [Python](8-Reinforcement/1-QLearning/README.md) | Dmitry | +| 25 | Помогнете на Петър да избегне вълка! 🐺 | [Обучение чрез подсилване](8-Reinforcement/README.md) | Gym за обучение чрез подсилване | [Python](8-Reinforcement/2-Gym/README.md) | Dmitry | +| Postscript | Реални ML сценарии и приложения | [ML in the Wild](9-Real-World/README.md) | Интересни и показателни реални приложения на класическото ML | [Урок](9-Real-World/1-Applications/README.md) | Екип | +| Postscript | Отстраняване на грешки в модели в ML с помощта на RAI табло | [ML in the Wild](9-Real-World/README.md) | Отстраняване на грешки в модели в машинното обучение, използвайки компоненти на таблото Responsible AI | [Урок](9-Real-World/2-Debugging-ML-Models/README.md) | Ruth Yakubu | > [намерете всички допълнителни ресурси за този курс в нашата колекция Microsoft Learn](https://learn.microsoft.com/en-us/collections/qrqzamz1nn2wx3?WT.mc_id=academic-77952-bethanycheum) ## Офлайн достъп -Можете да стартирате тази документация офлайн, като използвате [Docsify](https://docsify.js.org/#/). Форкнете това хранилище, [инсталирайте Docsify](https://docsify.js.org/#/quickstart) на вашия локален компютър, и след това в главната папка на това хранилище въведете `docsify serve`. Уебсайтът ще бъде достъпен на порт 3000 на вашия localhost: `localhost:3000`. +Можете да стартирате тази документация офлайн, като използвате [Docsify](https://docsify.js.org/#/). Форкнете това repo, [инсталирайте Docsify](https://docsify.js.org/#/quickstart) на вашата локална машина, и след това в коренната папка на това repo изпълнете `docsify serve`. Уебсайтът ще бъде обслужван на порт 3000 на вашия localhost: `localhost:3000`. ## PDF файлове @@ -163,7 +163,7 @@ Cloud Advocates в Microsoft с удоволствие предлагат 12-с ## 🎒 Други курсове -Екипът ни създава други курсове! Вижте: +Нашият екип създава и други курсове! Разгледайте: ### LangChain @@ -172,7 +172,7 @@ Cloud Advocates в Microsoft с удоволствие предлагат 12-с --- -### Azure / Edge / MCP / Agents +### Azure / Edge / MCP / Агенти [![AZD за начинаещи](https://img.shields.io/badge/AZD%20for%20Beginners-0078D4?style=for-the-badge&labelColor=E5E7EB&color=0078D4)](https://github.com/microsoft/AZD-for-beginners?WT.mc_id=academic-105485-koreyst) [![Edge AI за начинаещи](https://img.shields.io/badge/Edge%20AI%20for%20Beginners-00B8E4?style=for-the-badge&labelColor=E5E7EB&color=00B8E4)](https://github.com/microsoft/edgeai-for-beginners?WT.mc_id=academic-105485-koreyst) [![MCP за начинаещи](https://img.shields.io/badge/MCP%20for%20Beginners-009688?style=for-the-badge&labelColor=E5E7EB&color=009688)](https://github.com/microsoft/mcp-for-beginners?WT.mc_id=academic-105485-koreyst) @@ -183,15 +183,15 @@ Cloud Advocates в Microsoft с удоволствие предлагат 12-с ### Серия за генеративен AI [![Генеративен AI за начинаещи](https://img.shields.io/badge/Generative%20AI%20for%20Beginners-8B5CF6?style=for-the-badge&labelColor=E5E7EB&color=8B5CF6)](https://github.com/microsoft/generative-ai-for-beginners?WT.mc_id=academic-105485-koreyst) [![Генеративен AI (.NET)](https://img.shields.io/badge/Generative%20AI%20(.NET)-9333EA?style=for-the-badge&labelColor=E5E7EB&color=9333EA)](https://github.com/microsoft/Generative-AI-for-beginners-dotnet?WT.mc_id=academic-105485-koreyst) -[![Генеративен AI (Java)](https://img.shields.io/badge/Generative%20AI%20(Java)-C084FC?style=for-the-badge&labelColor=E5E7EB&color=C084FC)](https://github.com/microsoft/generative-ai-for-beginners-java?WT.mc_id=academic-105485-koreyst) -[![Генеративен AI (JavaScript)](https://img.shields.io/badge/Generative%20AI%20(JavaScript)-E879F9?style=for-the-badge&labelColor=E5E7EB&color=E879F9)](https://github.com/microsoft/generative-ai-with-javascript?WT.mc_id=academic-105485-koreyst) +[![Генеративен ИИ (Java)](https://img.shields.io/badge/Generative%20AI%20(Java)-C084FC?style=for-the-badge&labelColor=E5E7EB&color=C084FC)](https://github.com/microsoft/generative-ai-for-beginners-java?WT.mc_id=academic-105485-koreyst) +[![Генеративен ИИ (JavaScript)](https://img.shields.io/badge/Generative%20AI%20(JavaScript)-E879F9?style=for-the-badge&labelColor=E5E7EB&color=E879F9)](https://github.com/microsoft/generative-ai-with-javascript?WT.mc_id=academic-105485-koreyst) --- ### Основно обучение -[![ML за начинаещи](https://img.shields.io/badge/ML%20for%20Beginners-22C55E?style=for-the-badge&labelColor=E5E7EB&color=22C55E)](https://aka.ms/ml-beginners?WT.mc_id=academic-105485-koreyst) -[![Наука за данните за начинаещи](https://img.shields.io/badge/Data%20Science%20for%20Beginners-84CC16?style=for-the-badge&labelColor=E5E7EB&color=84CC16)](https://aka.ms/datascience-beginners?WT.mc_id=academic-105485-koreyst) -[![AI за начинаещи](https://img.shields.io/badge/AI%20for%20Beginners-A3E635?style=for-the-badge&labelColor=E5E7EB&color=A3E635)](https://aka.ms/ai-beginners?WT.mc_id=academic-105485-koreyst) +[![Машинно обучение за начинаещи](https://img.shields.io/badge/ML%20for%20Beginners-22C55E?style=for-the-badge&labelColor=E5E7EB&color=22C55E)](https://aka.ms/ml-beginners?WT.mc_id=academic-105485-koreyst) +[![Наука за данни за начинаещи](https://img.shields.io/badge/Data%20Science%20for%20Beginners-84CC16?style=for-the-badge&labelColor=E5E7EB&color=84CC16)](https://aka.ms/datascience-beginners?WT.mc_id=academic-105485-koreyst) +[![Изкуствен интелект за начинаещи](https://img.shields.io/badge/AI%20for%20Beginners-A3E635?style=for-the-badge&labelColor=E5E7EB&color=A3E635)](https://aka.ms/ai-beginners?WT.mc_id=academic-105485-koreyst) [![Киберсигурност за начинаещи](https://img.shields.io/badge/Cybersecurity%20for%20Beginners-F97316?style=for-the-badge&labelColor=E5E7EB&color=F97316)](https://github.com/microsoft/Security-101?WT.mc_id=academic-96948-sayoung) [![Уеб разработка за начинаещи](https://img.shields.io/badge/Web%20Dev%20for%20Beginners-EC4899?style=for-the-badge&labelColor=E5E7EB&color=EC4899)](https://aka.ms/webdev-beginners?WT.mc_id=academic-105485-koreyst) [![IoT за начинаещи](https://img.shields.io/badge/IoT%20for%20Beginners-14B8A6?style=for-the-badge&labelColor=E5E7EB&color=14B8A6)](https://aka.ms/iot-beginners?WT.mc_id=academic-105485-koreyst) @@ -200,24 +200,24 @@ Cloud Advocates в Microsoft с удоволствие предлагат 12-с --- ### Серия Copilot -[![Copilot за AI при съвместно програмиране](https://img.shields.io/badge/Copilot%20for%20AI%20Paired%20Programming-FACC15?style=for-the-badge&labelColor=E5E7EB&color=FACC15)](https://aka.ms/GitHubCopilotAI?WT.mc_id=academic-105485-koreyst) +[![Copilot за двойно програмиране с ИИ](https://img.shields.io/badge/Copilot%20for%20AI%20Paired%20Programming-FACC15?style=for-the-badge&labelColor=E5E7EB&color=FACC15)](https://aka.ms/GitHubCopilotAI?WT.mc_id=academic-105485-koreyst) [![Copilot за C#/.NET](https://img.shields.io/badge/Copilot%20for%20C%23/.NET-FBBF24?style=for-the-badge&labelColor=E5E7EB&color=FBBF24)](https://github.com/microsoft/mastering-github-copilot-for-dotnet-csharp-developers?WT.mc_id=academic-105485-koreyst) -[![Copilot приключение](https://img.shields.io/badge/Copilot%20Adventure-FDE68A?style=for-the-badge&labelColor=E5E7EB&color=FDE68A)](https://github.com/microsoft/CopilotAdventures?WT.mc_id=academic-105485-koreyst) +[![Copilot Приключение](https://img.shields.io/badge/Copilot%20Adventure-FDE68A?style=for-the-badge&labelColor=E5E7EB&color=FDE68A)](https://github.com/microsoft/CopilotAdventures?WT.mc_id=academic-105485-koreyst) ## Получаване на помощ -Ако се затрудните или имате въпроси относно изграждането на AI приложения, присъединете се към други учащи се и опитни разработчици в дискусии за MCP. Това е подкрепяща общност, където въпросите са добре дошли и знанието се споделя свободно. +Ако закъсате или имате въпроси относно изграждането на ИИ приложения. Присъединете се към други учащи и опитни разработчици в дискусиите за MCP. Това е подкрепяща общност, в която въпросите са добре дошли и знанията се споделят свободно. [![Discord на Microsoft Foundry](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) -Ако имате обратна връзка за продукта или грешки по време на разработката, посетете: +Ако имате обратна връзка за продукта или грешки по време на разработка, посетете: -[![Форум на Microsoft Foundry за разработчици](https://img.shields.io/badge/GitHub-Microsoft_Foundry_Developer_Forum-blue?style=for-the-badge&logo=github&color=000000&logoColor=fff)](https://aka.ms/foundry/forum) +[![Форум за разработчици Microsoft Foundry](https://img.shields.io/badge/GitHub-Microsoft_Foundry_Developer_Forum-blue?style=for-the-badge&logo=github&color=000000&logoColor=fff)](https://aka.ms/foundry/forum) --- -**Отказ от отговорност**: -Този документ е преведен с помощта на AI преводаческа услуга [Co-op Translator](https://github.com/Azure/co-op-translator). Въпреки че се стремим към точност, моля имайте предвид, че автоматизираните преводи могат да съдържат грешки или неточности. Оригиналният документ на оригиналния му език трябва да се счита за авторитетен източник. За критична информация се препоръчва професионален човешки превод. Не носим отговорност за никакви недоразумения или погрешни тълкувания, произтичащи от използването на този превод. +Отказ от отговорност: +Този документ е преведен с помощта на услуга за превод с изкуствен интелект Co-op Translator (https://github.com/Azure/co-op-translator). Въпреки че се стремим към точност, имайте предвид, че автоматизираните преводи могат да съдържат грешки или неточности. Оригиналният документ на оригиналния език трябва да се счита за авторитетен източник. За критична информация се препоръчва професионален превод, извършен от човешки преводач. Не носим отговорност за никакви недоразумения или неправилни тълкувания, произтичащи от използването на този превод. \ No newline at end of file diff --git a/translations/bn/1-Introduction/README.md b/translations/bn/1-Introduction/README.md index f4d170cc0..77b41ddc6 100644 --- a/translations/bn/1-Introduction/README.md +++ b/translations/bn/1-Introduction/README.md @@ -11,7 +11,7 @@ CO_OP_TRANSLATOR_METADATA: এই পাঠক্রমের এই অংশে, আপনি মেশিন লার্নিং ক্ষেত্রের মূল ধারণাগুলি, এটি কী, এর ইতিহাস এবং গবেষকরা এটি নিয়ে কাজ করার জন্য যে কৌশলগুলি ব্যবহার করেন তা সম্পর্কে জানতে পারবেন। চলুন একসাথে এই নতুন মেশিন লার্নিং-এর জগৎটি অন্বেষণ করি! -![globe](../../../translated_images/globe.59f26379ceb40428672b4d9a568044618a2bf6292ecd53a5c481b90e3fa805eb.bn.jpg) +![globe](../../../translated_images/globe.59f26379ceb40428.bn.jpg) > ছবি বিল অক্সফোর্ড এর তোলা আনস্প্ল্যাশ-এ ### পাঠসমূহ diff --git a/translations/bn/2-Regression/1-Tools/solution/R/lesson_1-R.ipynb b/translations/bn/2-Regression/1-Tools/solution/R/lesson_1-R.ipynb index ea9b57590..69e536a27 100644 --- a/translations/bn/2-Regression/1-Tools/solution/R/lesson_1-R.ipynb +++ b/translations/bn/2-Regression/1-Tools/solution/R/lesson_1-R.ipynb @@ -48,7 +48,7 @@ " width=\"630\"/>\n", "
চিত্রকর্ম: @allison_horst
\n", "\n", - "\n" + "\n" ], "metadata": { "id": "LWNNzfqd6feZ" diff --git a/translations/bn/2-Regression/2-Data/solution/R/lesson_2-R.ipynb b/translations/bn/2-Regression/2-Data/solution/R/lesson_2-R.ipynb index 7ab7536c8..bdac94b37 100644 --- a/translations/bn/2-Regression/2-Data/solution/R/lesson_2-R.ipynb +++ b/translations/bn/2-Regression/2-Data/solution/R/lesson_2-R.ipynb @@ -50,7 +50,7 @@ "
চিত্রকর্ম: @allison_horst
\n", "\n", "\n", - "\n" + "\n" ], "metadata": { "id": "Pg5aexcOPqAZ" @@ -231,7 +231,7 @@ "
চিত্রকর্ম: @allison_horst
\n", "\n", "\n", - "\n" + "\n" ], "metadata": { "id": "o4jLY5-VZO2C" @@ -534,7 +534,7 @@ "
ইনফোগ্রাফিক: দাসানি মাদিপল্লি
\n", "\n", "\n", - "\n", + "\n", "\n", "একটি *জ্ঞানী* কথা আছে যা এভাবে বলা হয়:\n", "\n", diff --git a/translations/bn/2-Regression/3-Linear/solution/R/lesson_3-R.ipynb b/translations/bn/2-Regression/3-Linear/solution/R/lesson_3-R.ipynb index 9725812e1..e32e6cbf3 100644 --- a/translations/bn/2-Regression/3-Linear/solution/R/lesson_3-R.ipynb +++ b/translations/bn/2-Regression/3-Linear/solution/R/lesson_3-R.ipynb @@ -804,7 +804,7 @@ "
ইনফোগ্রাফিক: দাসানি মাদিপল্লি
\n", "\n", "\n", - "\n" + "\n" ], "metadata": { "id": "HOCqJXLTwtWI" diff --git a/translations/bn/2-Regression/4-Logistic/solution/R/lesson_4-R.ipynb b/translations/bn/2-Regression/4-Logistic/solution/R/lesson_4-R.ipynb index 60ec24621..d0c2a6e49 100644 --- a/translations/bn/2-Regression/4-Logistic/solution/R/lesson_4-R.ipynb +++ b/translations/bn/2-Regression/4-Logistic/solution/R/lesson_4-R.ipynb @@ -6,7 +6,7 @@ "source": [ "## লজিস্টিক রিগ্রেশন মডেল তৈরি করুন - পাঠ ৪\n", "\n", - "![লজিস্টিক বনাম লিনিয়ার রিগ্রেশন ইনফোগ্রাফিক](../../../../../../translated_images/linear-vs-logistic.ba180bf95e7ee66721ba10ebf2dac2666acbd64a88b003c83928712433a13c7d.bn.png)\n", + "![লজিস্টিক বনাম লিনিয়ার রিগ্রেশন ইনফোগ্রাফিক](../../../../../../translated_images/linear-vs-logistic.ba180bf95e7ee667.bn.png)\n", "\n", "#### **[পাঠের পূর্ববর্তী কুইজ](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/15/)**\n", "\n", @@ -78,7 +78,7 @@ "\n", "লজিস্টিক রিগ্রেশন লিনিয়ার রিগ্রেশনের মতো একই বৈশিষ্ট্য প্রদান করে না। প্রথমটি একটি `বাইনারি বিভাগ` (\"কমলা বা কমলা নয়\") সম্পর্কে পূর্বাভাস দেয়, যেখানে দ্বিতীয়টি `ধারাবাহিক মান` পূর্বাভাস দিতে সক্ষম, যেমন কুমড়ার উৎপত্তি এবং ফসল তোলার সময় দেওয়া হলে, *এর দাম কতটা বাড়বে*।\n", "\n", - "![দাসানি মাদিপালির ইনফোগ্রাফিক](../../../../../../translated_images/pumpkin-classifier.562771f104ad5436b87d1c67bca02a42a17841133556559325c0a0e348e5b774.bn.png)\n", + "![দাসানি মাদিপালির ইনফোগ্রাফিক](../../../../../../translated_images/pumpkin-classifier.562771f104ad5436.bn.png)\n", "\n", "### অন্যান্য শ্রেণীবিভাগ\n", "\n", @@ -88,7 +88,7 @@ "\n", "- **অর্ডিনাল**, যেখানে ক্রমানুসারে বিভাগ থাকে, যা আমাদের ফলাফলগুলোকে যৌক্তিকভাবে সাজাতে সাহায্য করে, যেমন আমাদের কুমড়াগুলো যা একটি নির্দিষ্ট সংখ্যক আকারে সাজানো থাকে (মিনি, ছোট, মাঝারি, বড়, এক্সএল, ডাবল এক্সএল)।\n", "\n", - "![মাল্টিনোমিয়াল বনাম অর্ডিনাল রিগ্রেশন](../../../../../../translated_images/multinomial-vs-ordinal.36701b4850e37d86c9dd49f7bef93a2f94dbdb8fe03443eb68f0542f97f28f29.bn.png)\n", + "![মাল্টিনোমিয়াল বনাম অর্ডিনাল রিগ্রেশন](../../../../../../translated_images/multinomial-vs-ordinal.36701b4850e37d86.bn.png)\n", "\n", "#### **ভেরিয়েবলগুলোর মধ্যে সম্পর্ক থাকা জরুরি নয়**\n", "\n", diff --git a/translations/bn/2-Regression/README.md b/translations/bn/2-Regression/README.md index fdb109623..c476a3c8b 100644 --- a/translations/bn/2-Regression/README.md +++ b/translations/bn/2-Regression/README.md @@ -12,7 +12,7 @@ CO_OP_TRANSLATOR_METADATA: উত্তর আমেরিকায়, হ্যালোউইনের জন্য কুমড়া প্রায়ই ভয়ঙ্কর মুখে খোদাই করা হয়। চলুন এই চমৎকার সবজিগুলো সম্পর্কে আরও জানি! -![জ্যাক-ও-ল্যান্টার্নস](../../../translated_images/jack-o-lanterns.181c661a9212457d7756f37219f660f1358af27554d856e5a991f16b4e15337c.bn.jpg) +![জ্যাক-ও-ল্যান্টার্নস](../../../translated_images/jack-o-lanterns.181c661a9212457d.bn.jpg) > ছবি: Beth Teutschmann এর তোলা Unsplash এ ## আপনি কী শিখবেন diff --git a/translations/bn/3-Web-App/README.md b/translations/bn/3-Web-App/README.md index 9455e5391..335cd22cd 100644 --- a/translations/bn/3-Web-App/README.md +++ b/translations/bn/3-Web-App/README.md @@ -11,7 +11,7 @@ CO_OP_TRANSLATOR_METADATA: এই পাঠ্যক্রমের এই অংশে, আপনি একটি প্রয়োগকৃত মেশিন লার্নিং বিষয়ের সাথে পরিচিত হবেন: কীভাবে আপনার Scikit-learn মডেলকে একটি ফাইলে সংরক্ষণ করবেন যা একটি ওয়েব অ্যাপ্লিকেশনের মধ্যে পূর্বাভাস দেওয়ার জন্য ব্যবহার করা যেতে পারে। মডেলটি সংরক্ষণ করার পরে, আপনি শিখবেন কীভাবে এটি Flask-এ তৈরি একটি ওয়েব অ্যাপে ব্যবহার করবেন। প্রথমে, আপনি কিছু ডেটা ব্যবহার করে একটি মডেল তৈরি করবেন যা UFO দেখার ঘটনার উপর ভিত্তি করে! এরপর, আপনি একটি ওয়েব অ্যাপ তৈরি করবেন যা আপনাকে সেকেন্ডের একটি সংখ্যা, একটি অক্ষাংশ এবং দ্রাঘিমাংশের মান ইনপুট দিয়ে পূর্বাভাস করতে দেবে কোন দেশ UFO দেখার রিপোর্ট করেছে। -![UFO পার্কিং](../../../translated_images/ufo.9e787f5161da9d4d1dafc537e1da09be8210f2ee996cb638aa5cee1d92867a04.bn.jpg) +![UFO পার্কিং](../../../translated_images/ufo.9e787f5161da9d4d.bn.jpg) ছবি তুলেছেন মাইকেল হেরেন আনস্প্ল্যাশ-এ diff --git a/translations/bn/4-Classification/README.md b/translations/bn/4-Classification/README.md index f25c7d5dd..d380e3e49 100644 --- a/translations/bn/4-Classification/README.md +++ b/translations/bn/4-Classification/README.md @@ -13,7 +13,7 @@ CO_OP_TRANSLATOR_METADATA: এশিয়া এবং ভারতে খাবারের ঐতিহ্য অত্যন্ত বৈচিত্র্যময় এবং খুবই সুস্বাদু! চলুন আঞ্চলিক খাবারের উপাদান সম্পর্কে বোঝার জন্য ডেটা দেখি। -![থাই খাবার বিক্রেতা](../../../translated_images/thai-food.c47a7a7f9f05c21892a1f9dc7bf30669e6d18dfda420c5c7ebb4153f6a304edd.bn.jpg) +![থাই খাবার বিক্রেতা](../../../translated_images/thai-food.c47a7a7f9f05c218.bn.jpg) > ছবি লিশেং চ্যাং এর তোলা আনস্প্ল্যাশ এ ## আপনি কী শিখবেন diff --git a/translations/bn/5-Clustering/README.md b/translations/bn/5-Clustering/README.md index 551155292..b0bb9cbba 100644 --- a/translations/bn/5-Clustering/README.md +++ b/translations/bn/5-Clustering/README.md @@ -15,7 +15,7 @@ CO_OP_TRANSLATOR_METADATA: নাইজেরিয়ার বৈচিত্র্যময় শ্রোতাদের সঙ্গীতের রুচিও বৈচিত্র্যময়। Spotify থেকে সংগৃহীত ডেটা ব্যবহার করে (এই [প্রবন্ধটি](https://towardsdatascience.com/country-wise-visual-analysis-of-music-taste-using-spotify-api-seaborn-in-python-77f5b749b421) দ্বারা অনুপ্রাণিত), আসুন নাইজেরিয়ায় জনপ্রিয় কিছু সঙ্গীত দেখি। এই ডেটাসেটে বিভিন্ন গানের 'danceability' স্কোর, 'acousticness', শব্দের উচ্চতা, 'speechiness', জনপ্রিয়তা এবং এনার্জি সম্পর্কিত তথ্য অন্তর্ভুক্ত রয়েছে। এই ডেটায় প্যাটার্ন খুঁজে বের করাটা বেশ মজার হবে! -![একটি টার্নটেবিল](../../../translated_images/turntable.f2b86b13c53302dc106aa741de9dc96ac372864cf458dd6f879119857aab01da.bn.jpg) +![একটি টার্নটেবিল](../../../translated_images/turntable.f2b86b13c53302dc.bn.jpg) > ছবি তুলেছেন Marcela Laskoski Unsplash-এ diff --git a/translations/bn/6-NLP/README.md b/translations/bn/6-NLP/README.md index 2250b5a21..7cb6afe9c 100644 --- a/translations/bn/6-NLP/README.md +++ b/translations/bn/6-NLP/README.md @@ -17,7 +17,7 @@ CO_OP_TRANSLATOR_METADATA: এই পাঠগুলোতে আমরা ছোট ছোট কথোপকথনকারী বট তৈরি করে NLP-এর মৌলিক বিষয়গুলো শিখব, যাতে মেশিন লার্নিং কীভাবে এই কথোপকথনগুলোকে আরও 'স্মার্ট' করে তুলতে সাহায্য করে তা বোঝা যায়। আপনি সময়ের পিছনে ভ্রমণ করবেন, জেন অস্টেনের ক্লাসিক উপন্যাস **Pride and Prejudice**, যা ১৮১৩ সালে প্রকাশিত হয়েছিল, থেকে এলিজাবেথ বেনেট এবং মিস্টার ডার্সির সাথে কথা বলবেন। এরপর, ইউরোপের হোটেল রিভিউয়ের মাধ্যমে অনুভূতি বিশ্লেষণ সম্পর্কে শিখে আপনার জ্ঞান আরও বাড়াবেন। -![Pride and Prejudice বই এবং চা](../../../translated_images/p&p.279f1c49ecd889419e4ce6206525e9aa30d32a976955cd24daa636c361c6391f.bn.jpg) +![Pride and Prejudice বই এবং চা](../../../translated_images/p&p.279f1c49ecd88941.bn.jpg) > ছবি Elaine Howlin এর তোলা Unsplash এ ## পাঠসমূহ diff --git a/translations/bn/7-TimeSeries/README.md b/translations/bn/7-TimeSeries/README.md index c7ceb886c..ffed7e18c 100644 --- a/translations/bn/7-TimeSeries/README.md +++ b/translations/bn/7-TimeSeries/README.md @@ -17,7 +17,7 @@ CO_OP_TRANSLATOR_METADATA: আমাদের আঞ্চলিক ফোকাস হলো বিশ্বব্যাপী বিদ্যুৎ ব্যবহার, যা একটি আকর্ষণীয় ডেটাসেট যা অতীতের লোডের প্যাটার্নের উপর ভিত্তি করে ভবিষ্যতের বিদ্যুৎ ব্যবহারের পূর্বাভাস সম্পর্কে শেখার সুযোগ দেয়। আপনি দেখতে পাবেন যে এই ধরনের পূর্বাভাস ব্যবসায়িক পরিবেশে কতটা কার্যকর হতে পারে। -![electric grid](../../../translated_images/electric-grid.0c21d5214db09ffae93c06a87ca2abbb9ba7475ef815129c5b423d7f9a7cf136.bn.jpg) +![electric grid](../../../translated_images/electric-grid.0c21d5214db09ffa.bn.jpg) ছবি [Peddi Sai hrithik](https://unsplash.com/@shutter_log?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText) কর্তৃক, রাজস্থানের একটি রাস্তায় বৈদ্যুতিক টাওয়ারের। [Unsplash](https://unsplash.com/s/photos/electric-india?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText) থেকে নেওয়া। diff --git a/translations/bn/8-Reinforcement/README.md b/translations/bn/8-Reinforcement/README.md index 6466602c6..3196046a9 100644 --- a/translations/bn/8-Reinforcement/README.md +++ b/translations/bn/8-Reinforcement/README.md @@ -13,7 +13,7 @@ CO_OP_TRANSLATOR_METADATA: ধরুন আপনার কাছে একটি সিমুলেটেড পরিবেশ আছে, যেমন শেয়ার বাজার। যদি আপনি একটি নির্দিষ্ট নিয়ম আরোপ করেন, তাহলে কী ঘটে? এর ইতিবাচক বা নেতিবাচক প্রভাব কি? যদি কিছু নেতিবাচক ঘটে, তাহলে আপনাকে এই _নেতিবাচক রিইনফোর্সমেন্ট_ থেকে শিখতে হবে এবং পথ পরিবর্তন করতে হবে। যদি এটি ইতিবাচক ফলাফল হয়, তাহলে আপনাকে সেই _ইতিবাচক রিইনফোর্সমেন্ট_ এর উপর ভিত্তি করে এগিয়ে যেতে হবে। -![পিটার এবং নেকড়ে](../../../translated_images/peter.779730f9ba3a8a8d9290600dcf55f2e491c0640c785af7ac0d64f583c49b8864.bn.png) +![পিটার এবং নেকড়ে](../../../translated_images/peter.779730f9ba3a8a8d.bn.png) > পিটার এবং তার বন্ধুরা ক্ষুধার্ত নেকড়ের হাত থেকে পালাতে হবে! ছবি: [জেন লুপার](https://twitter.com/jenlooper) diff --git a/translations/bn/9-Real-World/README.md b/translations/bn/9-Real-World/README.md index 9eb376ba9..00ec80bb8 100644 --- a/translations/bn/9-Real-World/README.md +++ b/translations/bn/9-Real-World/README.md @@ -11,7 +11,7 @@ CO_OP_TRANSLATOR_METADATA: এই পাঠক্রমের এই অংশে, আপনাকে ক্লাসিক্যাল মেশিন লার্নিং-এর কিছু বাস্তব জীবনের প্রয়োগের সাথে পরিচয় করানো হবে। আমরা ইন্টারনেট থেকে সাদা কাগজ এবং প্রবন্ধ সংগ্রহ করেছি যেখানে এই কৌশলগুলো ব্যবহার করা হয়েছে, যতটা সম্ভব নিউরাল নেটওয়ার্ক, ডিপ লার্নিং এবং AI এড়িয়ে। শিখুন কীভাবে মেশিন লার্নিং ব্যবসায়িক সিস্টেম, পরিবেশগত প্রয়োগ, অর্থনীতি, শিল্প ও সংস্কৃতি এবং আরও অনেক ক্ষেত্রে ব্যবহার করা হয়। -![chess](../../../translated_images/chess.e704a268781bdad85d1876b6c2295742fa0d856e7dcf3659147052df9d3db205.bn.jpg) +![chess](../../../translated_images/chess.e704a268781bdad8.bn.jpg) > ছবি Alexis Fauvet এর তোলা Unsplash এ diff --git a/translations/bn/README.md b/translations/bn/README.md index 5bfd78891..8d4d06faa 100644 --- a/translations/bn/README.md +++ b/translations/bn/README.md @@ -1,8 +1,8 @@ -[আরবি](../ar/README.md) | [বাংলা](./README.md) | [বুলগেরীয়](../bg/README.md) | [বর্মী (মিয়ানমার)](../my/README.md) | [চীনা (সরলীকৃত)](../zh/README.md) | [চীনা (চিরায়ত, হংকং)](../hk/README.md) | [চীনা (চিরায়ত, ম্যাকাও)](../mo/README.md) | [চীনা (চিরায়ত, তাইওয়ান)](../tw/README.md) | [ক্রোয়েশীয়](../hr/README.md) | [চেক](../cs/README.md) | [ড্যানিশ](../da/README.md) | [ডাচ](../nl/README.md) | [এস্তোনীয়](../et/README.md) | [ফিনিশ](../fi/README.md) | [ফরাসি](../fr/README.md) | [জার্মান](../de/README.md) | [গ্রিক](../el/README.md) | [হিবরু](../he/README.md) | [হিন্দি](../hi/README.md) | [হাঙ্গেরিয়ান](../hu/README.md) | [ইন্দোনেশীয়](../id/README.md) | [ইতালিয়ান](../it/README.md) | [জাপানি](../ja/README.md) | [কন্নড়](../kn/README.md) | [কোরিয়ান](../ko/README.md) | [লিথুয়ানিয়ান](../lt/README.md) | [মালয়](../ms/README.md) | [মালয়ালম](../ml/README.md) | [মরাঠি](../mr/README.md) | [নেপালি](../ne/README.md) | [নাইজেরিয়ান পিজিন](../pcm/README.md) | [নরওয়েজিয়ান](../no/README.md) | [পার্সি (ফার্সি)](../fa/README.md) | [পোলিশ](../pl/README.md) | [পর্তুগিজ (ব্রাজিল)](../br/README.md) | [পর্তুগিজ (পর্তুগাল)](../pt/README.md) | [পাঞ্জাবি (গুরুমুখি)](../pa/README.md) | [রোমানিয়ান](../ro/README.md) | [রুশ](../ru/README.md) | [সার্বিয়ান (সিরিলিক)](../sr/README.md) | [স্লোভাক](../sk/README.md) | [স্লোভেনীয়](../sl/README.md) | [স্প্যানিশ](../es/README.md) | [সোয়াহিলি](../sw/README.md) | [সুইডিশ](../sv/README.md) | [তাগালগ (ফিলিপিনো)](../tl/README.md) | [তামিল](../ta/README.md) | [তেলুগু](../te/README.md) | [থাই](../th/README.md) | [তুর্কি](../tr/README.md) | [ইউক্রেনীয়](../uk/README.md) | [উর্দু](../ur/README.md) | [ভিয়েতনামী](../vi/README.md) +[আরবি](../ar/README.md) | [বাংলা](./README.md) | [বুলগেরিয়ান](../bg/README.md) | [বার্মিজ (মায়ানমার)](../my/README.md) | [চীনা (সরলীকৃত)](../zh/README.md) | [চীনা (প্রচলিত, হংকং)](../hk/README.md) | [চীনা (প্রচলিত, ম্যাকাও)](../mo/README.md) | [চীনা (প্রচলিত, তাইওয়ান)](../tw/README.md) | [ক্রোয়েশিয়ান](../hr/README.md) | [চেক](../cs/README.md) | [ডেনিশ](../da/README.md) | [ডাচ](../nl/README.md) | [এস্তোনিয়ান](../et/README.md) | [ফিনিশ](../fi/README.md) | [ফরাসি](../fr/README.md) | [জার্মান](../de/README.md) | [গ্রীক](../el/README.md) | [হিব্রু](../he/README.md) | [হিন্দি](../hi/README.md) | [হাঙ্গেরিয়ান](../hu/README.md) | [ইন্দোনেশীয়](../id/README.md) | [ইতালীয়](../it/README.md) | [জাপানি](../ja/README.md) | [কন্নডা](../kn/README.md) | [কোরিয়ান](../ko/README.md) | [লিথুয়ানিয়ান](../lt/README.md) | [মালয়](../ms/README.md) | [মালায়ালম](../ml/README.md) | [মরাঠি](../mr/README.md) | [নেপালি](../ne/README.md) | [নাইজেরিয়ান পিডজিন](../pcm/README.md) | [নরওয়েজিয়ান](../no/README.md) | [ফার্সি (পার্সিয়ান)](../fa/README.md) | [পোলিশ](../pl/README.md) | [পর্তুগিজ (ব্রাজিল)](../br/README.md) | [পর্তুগিজ (পর্তুগাল)](../pt/README.md) | [পাঞ্জাবি (গুরুমুখি)](../pa/README.md) | [রোমানিয়ান](../ro/README.md) | [রাশিয়ান](../ru/README.md) | [সার্বীয় (সিরিলিক)](../sr/README.md) | [স্লোভাক](../sk/README.md) | [স্লোভেনিয়ান](../sl/README.md) | [স্প্যানিশ](../es/README.md) | [সোয়াহিলি](../sw/README.md) | [সুইডিশ](../sv/README.md) | [টাগালগ (ফিলিপিনো)](../tl/README.md) | [তামিল](../ta/README.md) | [তেলেগু](../te/README.md) | [থাই](../th/README.md) | [তুর্কি](../tr/README.md) | [ইউক্রেনীয়](../uk/README.md) | [উর্দু](../ur/README.md) | [ভিয়েতনামি](../vi/README.md) -#### আমাদের কমিউনিটিতে যোগ দিন +#### আমাদের সম্প্রদায়ে যোগ দিন -[![Microsoft Foundry Discord](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) +[![Microsoft Foundry ডিসকর্ড](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) -আমাদের একটি Discord-ভিত্তিক Learn with AI সিরিজ চলছে, আরও জানুন এবং 18 - 30 সেপ্টেম্বর, 2025 তারিখে আমাদের সাথে যোগ দিন [Learn with AI Series](https://aka.ms/learnwithai/discord)। সেখানে আপনি Data Science-এর জন্য GitHub Copilot ব্যবহারের টিপস এবং কৌশল পাবেন। +আমাদের কাছে একটি Discord-ভিত্তিক "AI-এর সাথে শেখা" সিরিজ চলছে, আরো জানতে এবং আমাদের সঙ্গে যোগ দিতে যান [AI-এর সাথে শেখার সিরিজ](https://aka.ms/learnwithai/discord) এ, সময়কাল 18 - 30 সেপ্টেম্বর, 2025। আপনি GitHub Copilot ব্যবহার করে ডেটা সায়েন্সের জন্য টিপস এবং কৌশল শিখবেন। -![Learn with AI সিরিজ](../../translated_images/3.9b58fd8d6c373c20c588c5070c4948a826ab074426c28ceb5889641294373dfc.bn.png) +![AI-এর সাথে শেখার সিরিজ](../../translated_images/3.9b58fd8d6c373c20.bn.png) -# শুরুতে মেশিন লার্নিং - একটি পাঠ্যক্রম +# শুরুরদের জন্য মেশিন লার্নিং - একটি পাঠক্রম -> 🌍 বিশ্বব্যাপী ভ্রমণ করুণ এবং আমরা কীভাবে মেশিন লার্নিংকে বিশ্বের বিভিন্ন সংস্কৃতির মাধ্যমে অন্বেষণ করি 🌍 +> 🌍 বিশ্বজুড়ে ভ্রমণ করুন যখন আমরা বিশ্বের সংস্কৃতির মাধ্যমে মেশিন লার্নিং অন্বেষণ করি 🌍 -Microsoft-এর Cloud Advocates আপনাদের জন্য একটি 12-সপ্তাহ, 26-লেসনের পুরো পাঠ্যক্রম উপস্থাপন করতে আনন্দিত। এই পাঠ্যক্রমে, আপনি যা কিছুকে কখনও কখনও “ক্লাসিক মেশিন লার্নিং” বলা হয় তা শিখবেন, প্রধানত Scikit-learn লাইব্রেরি ব্যবহার করে এবং ডীপ লার্নিং এড়িয়ে চলবেন, যা আমাদের [শুরুদের জন্য AI পাঠ্যক্রম](https://aka.ms/ai4beginners)-এ কভার করা হয়েছে। এ লেসনগুলোকে আমাদের ['Data Science for Beginners' পাঠ্যক্রম](https://aka.ms/ds4beginners)-এর সঙ্গে মিলিয়ে নিন, এছাড়াও উপকারী হবে! +Microsoft-এর Cloud Advocates একটি 12 সপ্তাহ, 26-উপাঠের একটি সম্পূর্ণ পাঠক্রম উপহার দেওয়ার আনন্দ পাচ্ছে যা সম্পূর্ণরূপে **মেশিন লার্নিং** সম্পর্কে। এই পাঠক্রমে, আপনি যা কখনও কখনও **ক্লাসিকাল মেশিন লার্নিং** বলা হয় তা সম্পর্কে জানবেন, প্রধানত Scikit-learn লাইব্রেরি ব্যবহার করে এবং ডিপ লার্নিং এড়িয়ে চলা, যা আমাদের [AI for Beginners' curriculum](https://aka.ms/ai4beginners)-এ কভার করা হয়েছে। এই পাঠগুলোকে আমাদের ['Data Science for Beginners' curriculum](https://aka.ms/ds4beginners)-এর সঙ্গে মিলিয়ে নিন। -আমাদের সঙ্গে বিশ্বের বিভিন্ন স্থানের ডেটার ওপর এই ক্লাসিক কৌশলগুলি প্রয়োগ করে ভ্রমণ করুন। প্রতিটি লেকশনে আছে প্রি- এবং পোস্ট-লেকচার কুইজ, লেকচার সম্পন্ন করার লিখিত নির্দেশাবলী, একটি সমাধান, একটি অ্যাসাইনমেন্ট, এবং আরও অনেক কিছু। আমাদের প্রকল্পভিত্তিক পেডাগজি আপনাকে তৈরি করে শেখার সুযোগ দেয়, যা নতুন দক্ষতা গেঁথে থাকার প্রমাণিত উপায়। +আমাদের সঙ্গে বিশ্বের বিভিন্ন স্থান থেকে আসা ডেটার ওপর ক্লাসিক্যাল কৌশলগুলো প্রয়োগ করে ভ্রমণ করুন। প্রতিটি পাঠে আছে প্রি- ও পোস্ট-লেকচার কুইজ, লেখ্য নির্দেশিকা পাঠ সম্পন্ন করার জন্য, একটি সমাধান, একটি অ্যাসাইনমেন্ট, এবং আরো অনেক কিছু। আমাদের প্রকল্প-ভিত্তিক শিক্ষাদান পদ্ধতি আপনাকে নির্মাণ করার সময় শেখার সুযোগ দেয়, যা নতুন দক্ষতা গেঁথে রাখার প্রমাণিত উপায়। **✍️ আমাদের লেখকদের প্রতি আন্তরিক ধন্যবাদ** Jen Looper, Stephen Howell, Francesca Lazzeri, Tomomi Imura, Cassie Breviu, Dmitry Soshnikov, Chris Noring, Anirban Mukherjee, Ornella Altunyan, Ruth Yakubu এবং Amy Boyd -**🎨 আমাদের চিত্রশিল্পীদের প্রতি ধন্যবাদ** Tomomi Imura, Dasani Madipalli, এবং Jen Looper +**🎨 আমাদের Ilustrator দেরও ধন্যবাদ** Tomomi Imura, Dasani Madipalli, এবং Jen Looper -**🙏 বিশেষ ধন্যবাদ 🙏 আমাদের Microsoft Student Ambassador লেখক, রিভিউয়ার এবং কনটেন্ট প্রদানকারীদের জন্য**, বিশেষত Rishit Dagli, Muhammad Sakib Khan Inan, Rohan Raj, Alexandru Petrescu, Abhishek Jaiswal, Nawrin Tabassum, Ioan Samuila, এবং Snigdha Agarwal +**🙏 বিশেষ ধন্যবাদ 🙏 আমাদের Microsoft Student Ambassador লেখক, পর্যবেক্ষক এবং বিষয়বস্তু অবদানকারীদের**, বিশেষ করে Rishit Dagli, Muhammad Sakib Khan Inan, Rohan Raj, Alexandru Petrescu, Abhishek Jaiswal, Nawrin Tabassum, Ioan Samuila, এবং Snigdha Agarwal -**🤩 Microsoft Student Ambassadors Eric Wanjau, Jasleen Sondhi, এবং Vidushi Gupta-কে অতিরিক্ত কৃতজ্ঞতা আমাদের R লেসনগুলোর জন্য!** +**🤩 অতিরিক্ত কৃতজ্ঞতা Microsoft Student Ambassadors Eric Wanjau, Jasleen Sondhi, এবং Vidushi Gupta-কে আমাদের R পাঠগুলো জন্য!** -# শুরু করুন +# শুরু করা -এই ধাপগুলো অনুসরণ করুন: -1. **রিপোজিটরি ফর্ক করুন**: এই পৃষ্ঠার উপরের-ডান কোনায় থাকা "Fork" বাটনে ক্লিক করুন। +নিম্নলিখিত ধাপগুলো অনুসরণ করুন: +1. **রিপোজিটরি Fork করুন**: এই পৃষ্ঠার উপরের ডানদিকে অবস্থিত "Fork" বোতামে ক্লিক করুন। 2. **রিপোজিটরি ক্লোন করুন**: `git clone https://github.com/microsoft/ML-For-Beginners.git` -> [এই কোর্সের সকল অতিরিক্ত সম্পদ আমাদের Microsoft Learn সংগ্রহে খুঁজুন](https://learn.microsoft.com/en-us/collections/qrqzamz1nn2wx3?WT.mc_id=academic-77952-bethanycheum) +> [এই কোর্সের সমস্ত অতিরিক্ত সম্পদ আমাদের Microsoft Learn সংগ্রহে খুঁজুন](https://learn.microsoft.com/en-us/collections/qrqzamz1nn2wx3?WT.mc_id=academic-77952-bethanycheum) -> 🔧 **সহায়তা প্রয়োজন?** ইনস্টলেশন, সেটআপ, এবং লেসন চালানোর সাধারণ সমস্যার সমাধানের জন্য আমাদের [সমস্যা সমাধান গাইড](TROUBLESHOOTING.md) চেক করুন। +> 🔧 **সহায়তা দরকার?** ইনস্টলেশন, সেটআপ, এবং লেসন চালানোর সাধারণ সমস্যাগুলোর সমাধানের জন্য আমাদের [Troubleshooting Guide](TROUBLESHOOTING.md) দেখুন। -**[শিক্ষার্থীরা](https://aka.ms/student-page)**, এই পাঠ্যক্রমটি ব্যবহার করতে, পুরো রিপোটি আপনার GitHub একাউন্টে ফর্ক করুন এবং এককভাবে বা গ্রুপে অনুশীলনগুলো সম্পন্ন করুন: +**[ছাত্রছাত্রী](https://aka.ms/student-page)**, এই পাঠক্রম ব্যবহারের জন্য, পুরো রিপোটি আপনার নিজস্ব GitHub অ্যাকাউন্টে fork করুন এবং একা বা গ্রুপের সঙ্গে অনুশীলনগুলি সম্পন্ন করুন: -- লেকচারের পূর্বের কুইজ দিয়ে শুরু করুন। -- লেকচারটি পড়ুন এবং প্রতিটি জ্ঞান যাচাইয়ের সময় থামুন এবং প্রতিফলন করুন। -- সমাধান কোড চালানোর পরিবর্তে পাঠগুলি বুঝে প্রজেক্টগুলো তৈরি করার চেষ্টা করুন; তবে প্রতিটি প্রোজেক্ট-উদ্দেশ্য লেসনের `/solution` ফোল্ডারে সেই কোড পাওয়া যাবে। -- পোস্ট-লেকচার কুইজটি নিন। -- চ্যালেঞ্জটি সম্পন্ন করুন। +- একটি প্রি-লেকচার কুইজ দিয়ে শুরু করুন। +- লেকচার পড়ুন এবং কার্যকলাপগুলো সম্পন্ন করুন, প্রতিটি জ্ঞান-চেক এ থামুন এবং প্রতিফলন করুন। +- সমাধান কোড চালানোর বদলে পাঠগুলো বুঝে প্রকল্পগুলো তৈরি করার চেষ্টা করুন; তবুও সেই কোড প্রতিটি প্রকল্প-ভিত্তিক লেসনের `/solution` ফোল্ডারে উপলব্ধ। +- পোস্ট-লেকচার কুইজ দিন। +- চ্যালেঞ্জ সম্পন্ন করুন। - অ্যাসাইনমেন্ট সম্পন্ন করুন। -- একটি লেসন গ্রুপ সম্পন্ন করার পরে, [Discussion Board](https://github.com/microsoft/ML-For-Beginners/discussions)-এ যান এবং উপযুক্ত PAT রুব্রিক পূরণ করে "সোচ্চর্যে শিক্ষণ" করুন। একটি 'PAT' হল একটি Progress Assessment Tool যা আপনি আপনার শেখার উন্নতির জন্য পূরণ করেন। আপনি অন্য PAT-গুলোর ওপর প্রতিক্রিয়া জানাতেও পারেন যাতে আমরা একসাথে শিখতে পারি। +- একটি লেসন গ্রুপ সম্পন্ন করার পরে, [Discussion Board](https://github.com/microsoft/ML-For-Beginners/discussions) এ যান এবং উপযুক্ত PAT রুব্রিক পূরণ করে "ভাৎ করে শেখা" শেয়ার করুন। একটি 'PAT' হল একটি Progress Assessment Tool — একটি রুব্রিক যা আপনি আপনার শেখার উন্নতির জন্য পূরণ করেন। আপনি অন্যান্য PAT-এ প্রতিক্রিয়া জানাতে পারেন যাতে আমরা একসাথে শিখতে পারি। -> আরও অধ্যয়নের জন্য, আমরা এই [Microsoft Learn](https://docs.microsoft.com/en-us/users/jenlooper-2911/collections/k7o7tg1gp306q4?WT.mc_id=academic-77952-leestott) মডিউল এবং লার্নিং পাথ অনুসরণ করার পরামর্শ দিই। +> আরো অধ্যয়নের জন্য, আমরা এই [Microsoft Learn](https://docs.microsoft.com/en-us/users/jenlooper-2911/collections/k7o7tg1gp306q4?WT.mc_id=academic-77952-leestott) মডিউল এবং লার্নিং পাথগুলো অনুসরণ করার পরামর্শ দিই। -**শিক্ষকগণ**, আমরা [প্রয়োগের কিছু পরামর্শ সংযুক্ত করেছি](for-teachers.md) এই পাঠ্যক্রম কীভাবে ব্যবহার করবেন সে সম্পর্কে। +**শিক্ষকগণ**, এই পাঠক্রম কীভাবে ব্যবহার করতে পারেন সে বিষয়ে আমরা [কিছু পরামর্শ অন্তর্ভুক্ত করেছি](for-teachers.md)। --- ## ভিডিও ওয়াকথ্রু -কিছু লেসন ছোট ফর্মের ভিডিও হিসেবে উপলব্ধ। আপনি এগুলো লেসনের মধ্যে সরাসরি পেতে পারেন, অথবা নিচের ছবিতে ক্লিক করে [Microsoft Developer YouTube চ্যানেলের 'ML for Beginners' প্লেলিস্ট](https://aka.ms/ml-beginners-videos)-এ দেখতে পারেন। +কিছু পাঠ শর্ট-ফর্ম ভিডিও হিসেবে উপলব্ধ। আপনি এগুলো পাঠের ভিতরে দেখতে পাবেন, অথবা নিচের চিত্রে ক্লিক করে [Microsoft Developer YouTube চ্যানেলের ML for Beginners প্লেলিস্টে](https://aka.ms/ml-beginners-videos) যেতে পারেন। -[![ML for Beginners ব্যানার](../../translated_images/ml-for-beginners-video-banner.63f694a100034bc6251134294459696e070a3a9a04632e9fe6a24aa0de4a7384.bn.png)](https://aka.ms/ml-beginners-videos) +[![ML for Beginners ব্যানার](../../translated_images/ml-for-beginners-video-banner.63f694a100034bc6.bn.png)](https://aka.ms/ml-beginners-videos) --- ## টিমের সাথে পরিচিত হন -[![প্রচার ভিডিও](../../images/ml.gif)](https://youtu.be/Tj1XWrDSYJU) +[![প্রোমো ভিডিও](../../images/ml.gif)](https://youtu.be/Tj1XWrDSYJU) -**GIF তৈরি করেছেন** [Mohit Jaisal](https://linkedin.com/in/mohitjaisal) +**GIF করেছেন** [Mohit Jaisal](https://linkedin.com/in/mohitjaisal) -> 🎥 উপরের ছবিতে ক্লিক করে প্রকল্প এবং যারা এটিকে সৃষ্টি করেছেন তাদের সম্পর্কে একটি ভিডিও দেখুন! +> 🎥 প্রকল্প এবং যারা এটি তৈরি করেছেন তাদের সম্পর্কে একটি ভিডিও দেখতে উপরের চিত্রে ক্লিক করুন! --- -## পেডাগজি +## শিক্ষণ পদ্ধতি -এই পাঠ্যক্রম তৈরি করার সময় আমরা দুটি পেডাগজিক্যাল নীতি বেছে নিয়েছি: এটি যাতে হাতে-কলমে শেখার উপযোগী এবং প্রকল্পভিত্তিক (project-based) হয় এবং এতে বারবার কুইজ (frequent quizzes) থাকবে। উপরন্তু, এই পাঠ্যক্রমে একটি সাধারণ থিম রয়েছে যা একত্রতা প্রদান করে। +এ এই পাঠক্রমটি তৈরির সময় আমরা দুইটি শিক্ষাদান মূলনীতি বেছে নিয়েছি: এটি হস্তগতভাবে **প্রকল্প-ভিত্তিক** করা এবং এতে **ঘন ঘন কুইজ** অন্তর্ভুক্ত করা। এছাড়াও, এই পাঠক্রমের একটি সাধারণ **থিম** রয়েছে যা এটিকে সংহতি দেয়। -কনটেন্টকে প্রকল্পের সঙ্গে সরাসরি সংযুক্ত করে শিক্ষণ প্রক্রিয়াটি শিক্ষার্থীদের জন্য আরও আকর্ষণীয় করা হয় এবং ধারণাগুলোর ধারণ ক্ষমতা বাড়ে। এছাড়া, ক্লাসের আগে একটি নিম্ন-স্টেকস কুইজ শিক্ষার্থীর শেখার লক্ষ্য স্থির করে, এবং ক্লাস শেষে দ্বিতীয় কুইজ আরও ধারণ ক্ষমতা নিশ্চিত করে। এই পাঠ্যক্রমটি নমনীয় এবং মজাদার করে ডিজাইন করা হয়েছে এবং সম্পূর্ণ বা আংশিকভাবে নেওয়া যেতে পারে। প্রকল্পগুলো ছোট থেকে শুরু করে 12-সপ্তাহের চক্রের শেষে ক্রমে ক্রমে জটিলতায় বৃদ্ধি পায়। এই পাঠ্যক্রমে মেশিন লার্নিং-এর বাস্তব-জগতের অ্যাপ্লিকেশনগুলোর একটি পোস্টস্ক্রিপ্টও রয়েছে, যা অতিরিক্ত ক্রেডিট হিসেবে বা আলোচনা-ভিত্তি হিসেবে ব্যবহার করা যেতে পারে। +বিষয়বস্তু প্রকল্পের সাথে সামঞ্জস্যপূর্ণ রাখলে, শিক্ষার্থীদের জন্য প্রক্রিয়াটি আরও আকর্ষণীয় হয় এবং ধারণাগুলোর ধারণ ক্ষমতা বাড়ে। এর পাশাপাশি, ক্লাসের আগে একটি নিম্ন-স্টেক্স কুইজ ছাত্রের শেখার অভিপ্রায় নির্ধারণ করে, এবং ক্লাসের পরের কুইজ নিশ্চিত করে যে ধারণাগুলো স্থায়ী হয়েছে। এই পাঠক্রমটি নমনীয় এবং মজাদারভাবে নকশা করা হয়েছে এবং সম্পূর্ণ বা আংশিকভাবে গ্রহণ করা যায়। প্রকল্পগুলো ছোটভাবে শুরু করে এবং 12-সপ্তাহের শেষ পর্যন্ত ক্রমশ জটিল হয়ে ওঠে। এই পাঠক্রমে বাস্তব-জগতের ML অ্যাপ্লিকেশনগুলোর উপর একটি পরিশিষ্টও রয়েছে, যা অতিরিক্ত ক্রেডিট বা আলোচনার ভিত্তি হিসেবে ব্যবহার করা যেতে পারে। -> আমাদের [আচার-আচরণ কোড](CODE_OF_CONDUCT.md), [অবদান নির্দেশিকা](CONTRIBUTING.md), [অনুবাদ নির্দেশিকা](TRANSLATIONS.md), এবং [সমস্যা সমাধান নির্দেশিকা](TROUBLESHOOTING.md) খুঁজে দেখুন। আমরা আপনার গঠনমূলক প্রতিক্রিয়াকে স্বাগত জানাই! +> আমাদের [Code of Conduct](CODE_OF_CONDUCT.md), [Contributing](CONTRIBUTING.md), [Translation](TRANSLATIONS.md), এবং [Troubleshooting](TROUBLESHOOTING.md) নির্দেশিকা দেখুন। আমরা আপনার রचनাত্মক প্রতিক্রিয়া স্বাগত জানাই! -## প্রতিটি লেসনে আছে +## প্রতিটি পাঠে অন্তর্ভুক্ত - ঐচ্ছিক স্কেচনোট -- ঐচ্ছিক সহায়ক ভিডিও -- ভিডিও ওয়াকথ্রু (কিছু লেসনে মাত্র) -- [প্রাক-লেকচার ওয়ার্মআপ কুইজ](https://ff-quizzes.netlify.app/en/ml/) -- লিখিত লেসন -- প্রকল্পভিত্তিক লেসনগুলোর জন্য, প্রকল্পটি কীভাবে তৈরি করবেন তার ধাপে ধাপে নির্দেশিকা -- জ্ঞান যাচাইকরণ +- ঐচ্ছিক পরিপূরক ভিডিও +- ভিডিও ওয়াকথ্রু (কিছু পাঠের জন্যই) +- [প্রী-লেকচার ওয়ার্মআপ কুইজ](https://ff-quizzes.netlify.app/en/ml/) +- লেখ্য লেকচার +- প্রকল্প-ভিত্তিক পাঠগুলোর জন্য, প্রকল্পটি কীভাবে তৈরি করবেন সে সম্পর্কে ধাপে ধাপে গাইড +- জ্ঞান-চেক - একটি চ্যালেঞ্জ -- অতিরিক্ত পাঠ্য +- পরিপূরক পাঠ - অ্যাসাইনমেন্ট - [পোস্ট-লেকচার কুইজ](https://ff-quizzes.netlify.app/en/ml/) -> **ভাষা সম্পর্কিত একটি নোট**: এই লেসনগুলো প্রধানত Python-এ লেখা, কিন্তু অনেকগুলো R-এও উপলব্ধ। একটি R লেসন সম্পন্ন করতে, `/solution` ফোল্ডারে যান এবং R লেসনগুলো খুঁজুন। এগুলোতে .rmd এক্সটেনশন রয়েছে যা একটি **R Markdown** ফাইল নির্দেশ করে, যা সহজভাবে ব্যাখ্যা করা যায় যেমন একটি `code chunks` (R বা অন্যান্য ভাষার) এবং একটি `YAML header` (যা PDF-এর মতো আউটপুট কিভাবে ফরম্যাট হবে তা নির্ধারণ করে) একটি `Markdown document`-এ এমবেড করা। এইভাবে, এটি ডাটা সায়েন্সের জন্য একটি দৃষ্টান্তমূলক লেখনী কাঠামো হিসেবে কাজ করে, কারণ এটি আপনাকে আপনার কোড, তার আউটপুট, এবং আপনার চিন্তাগুলো একসঙ্গে Markdown-এ লিখে সংযুক্ত করার সুযোগ দেয়। উপরন্তু, R Markdown ডকুমেন্টগুলো PDF, HTML, বা Word-এর মতো আউটপুট ফরম্যাটে রেন্ডার করা যেতে পারে। +> **ভাষা সম্পর্কিত একটি নোট**: এই পাঠগুলো মূলত Python-এ লেখা, কিন্তু অনেকগুলো R-এও উপলব্ধ। একটি R লেকচার সম্পন্ন করতে, `/solution` ফোল্ডারে যান এবং R পাঠগুলো সন্ধান করুন। সেগুলোতে .rmd এক্সটেনশন থাকবে যা একটি **R Markdown** ফাইল নির্দেশ করে যা সহজভাবে `code chunks` (R বা অন্যান্য ভাষার) এবং একটি `YAML header` (যা PDF-এর মতো আউটপুট কিভাবে ফরম্যাট করা হবে তা নির্দেশ করে) মিলিয়ে একটি `Markdown document` হিসেবে এমবেড করা যায়। ফলে, এটি ডেটা সায়েন্সের জন্য একটি আদর্শ লেখন কাঠামো হিসেবে কাজ করে কারণ এতে আপনি আপনার কোড, তার আউটপুট এবং আপনার চিন্তা একসাথে Markdown-এ লিখে রাখতে পারেন। এছাড়াও, R Markdown ডকুমেন্টগুলো PDF, HTML, বা Word-এর মতো আউটপুট ফরম্যাটে রেন্ডার করা যায়। -> **কুইজ সম্পর্কিত একটি নোট**: সব কুইজ [Quiz App ফোল্ডারে](../../quiz-app) রয়েছে, মোট 52টি কুইজ, প্রতিটিতে তিনটি প্রশ্ন। এগুলো পাঠ্যগুলোর মধ্যে লিংক করা আছে কিন্তু কুইজ অ্যাপ লোকালি চালানো যায়; লোকালি হোস্ট বা Azure-এ ডিপ্লয় করার নির্দেশাবলী দেখতে `quiz-app` ফোল্ডারের নির্দেশনা অনুসরণ করুন। +> **কুইজ সম্পর্কে একটি নোট**: সব কুইজ [Quiz App folder](../../quiz-app) এ রয়েছে, মোট 52টি কুইজ আছে প্রতিটিতে তিনটি প্রশ্ন। সেগুলো লেসনের ভিতর থেকে লিঙ্ক করা হয়েছে তবে কুইজ অ্যাপটি লোকালি চালানো যেতে পারে; লোকালি হোস্ট বা Azure-এ ডিপ্লয় করার নির্দেশনার জন্য `quiz-app` ফোল্ডারের নির্দেশিকা অনুসরণ করুন। -| পাঠ নম্বর | বিষয় | পাঠ গোষ্ঠী | শেখার উদ্দেশ্য | লিংক করা পাঠ | লেখক | +| Lesson Number | Topic | Lesson Grouping | Learning Objectives | Linked Lesson | Author | | :-----------: | :------------------------------------------------------------: | :-------------------------------------------------: | ------------------------------------------------------------------------------------------------------------------------------- | :--------------------------------------------------------------------------------------------------------------------------------------: | :--------------------------------------------------: | -| 01 | মেশিন লার্নিংয়ের পরিচিতি | [পরিচিতি](1-Introduction/README.md) | মেশিন লার্নিং-এর মৌলিক ধারণাগুলো শিখুন | [পাঠ](1-Introduction/1-intro-to-ML/README.md) | Muhammad | -| 02 | মেশিন লার্নিং-র ইতিহাস | [পরিচিতি](1-Introduction/README.md) | এই ক্ষেত্রের ভিত্তি হিসেবে থাকা ইতিহাস জানুন | [পাঠ](1-Introduction/2-history-of-ML/README.md) | Jen and Amy | -| 03 | ন্যায্যতা এবং মেশিন লার্নিং | [পরিচিতি](1-Introduction/README.md) | মেশিন লার্নিং মডেল তৈরি ও প্রয়োগের সময় শিক্ষার্থীদের কোন কোন গুরুত্বপূর্ণ দার্শনিক প্রশ্নগুলোর কথা বিবেচনা করা উচিত? | [পাঠ](1-Introduction/3-fairness/README.md) | Tomomi | -| 04 | মেশিন লার্নিং-এর কৌশলসমূহ | [পরিচিতি](1-Introduction/README.md) | মেশিন লার্নিং গবেষকরা মডেল তৈরি করতে কী কী কৌশল ব্যবহার করেন? | [পাঠ](1-Introduction/4-techniques-of-ML/README.md) | Chris and Jen | -| 05 | রিগ্রেশন পরিচিতি | [রিগ্রেশন](2-Regression/README.md) | রিগ্রেশন মডেলের জন্য Python এবং Scikit-learn দিয়ে শুরু করুন | [Python](2-Regression/1-Tools/README.md) • [R](../../2-Regression/1-Tools/solution/R/lesson_1.html) | Jen • Eric Wanjau | +| 01 | মেশিন লার্নিং-এর পরিচিতি | [ভূমিকা](1-Introduction/README.md) | মেশিন লার্নিং-এর মূল ধারণাগুলো শিখুন | [পাঠ](1-Introduction/1-intro-to-ML/README.md) | Muhammad | +| 02 | মেশিন লার্নিং-এর ইতিহাস | [ভূমিকা](1-Introduction/README.md) | এই ক্ষেত্রের ইতিহাস শিখুন | [পাঠ](1-Introduction/2-history-of-ML/README.md) | Jen and Amy | +| 03 | ন্যায় ও মেশিন লার্নিং | [ভূমিকা](1-Introduction/README.md) | মডেল নির্মাণ ও প্রয়োগের সময় ছাত্রদের বিবেচনা করা উচিত এমন ন্যায়সংক্রান্ত গুরুত্বপূর্ণ দার্শনিক বিষয়গুলো কী কী? | [পাঠ](1-Introduction/3-fairness/README.md) | Tomomi | +| 04 | মেশিন লার্নিং-এর কৌশলসমূহ | [ভূমিকা](1-Introduction/README.md) | ML গবেষকরা ML মডেল গঠনের জন্য কী কী কৌশল ব্যবহার করে? | [পাঠ](1-Introduction/4-techniques-of-ML/README.md) | Chris and Jen | +| 05 | রিগ্রেশনে পরিচিতি | [রিগ্রেশন](2-Regression/README.md) | রিগ্রেশন মডেলগুলির জন্য Python এবং Scikit-learn দিয়ে শুরু করুন | [Python](2-Regression/1-Tools/README.md) • [R](../../2-Regression/1-Tools/solution/R/lesson_1.html) | Jen • Eric Wanjau | | 06 | উত্তর আমেরিকার কুমড়োর দাম 🎃 | [রিগ্রেশন](2-Regression/README.md) | মেশিন লার্নিং-এর প্রস্তুতির জন্য ডেটা ভিজ্যুয়ালাইজ ও পরিষ্কার করুন | [Python](2-Regression/2-Data/README.md) • [R](../../2-Regression/2-Data/solution/R/lesson_2.html) | Jen • Eric Wanjau | -| 07 | উত্তর আমেরিকার কুমড়োর দাম 🎃 | [রিগ্রেশন](2-Regression/README.md) | রৈখিক ও বহুপদী রিগ্রেশন মডেল তৈরি করুন | [Python](2-Regression/3-Linear/README.md) • [R](../../2-Regression/3-Linear/solution/R/lesson_3.html) | Jen and Dmitry • Eric Wanjau | +| 07 | উত্তর আমেরিকার কুমড়োর দাম 🎃 | [রিগ্রেশন](2-Regression/README.md) | রৈখিক ও বহুপদী রিগ্রেশন মডেল নির্মাণ করুন | [Python](2-Regression/3-Linear/README.md) • [R](../../2-Regression/3-Linear/solution/R/lesson_3.html) | Jen and Dmitry • Eric Wanjau | | 08 | উত্তর আমেরিকার কুমড়োর দাম 🎃 | [রিগ্রেশন](2-Regression/README.md) | একটি লজিস্টিক রিগ্রেশন মডেল তৈরি করুন | [Python](2-Regression/4-Logistic/README.md) • [R](../../2-Regression/4-Logistic/solution/R/lesson_4.html) | Jen • Eric Wanjau | -| 09 | একটি ওয়েব অ্যাপ 🔌 | [ওয়েব অ্যাপ](3-Web-App/README.md) | আপনার প্রশিক্ষিত মডেল ব্যবহার করার জন্য একটি ওয়েব অ্যাপ তৈরি করুন | [Python](3-Web-App/1-Web-App/README.md) | Jen | -| 10 | ক্লাসিফিকেশনের পরিচিতি | [ক্লাসিফিকেশন](4-Classification/README.md) | আপনার ডেটা পরিষ্কার, প্রস্তুত ও ভিজ্যুয়ালাইজ করুন; ক্লাসিফিকেশনের পরিচিতি | [Python](4-Classification/1-Introduction/README.md) • [R](../../4-Classification/1-Introduction/solution/R/lesson_10.html) | Jen and Cassie • Eric Wanjau | -| 11 | সুস্বাদু এশীয় ও ভারতীয় রন্ধনশৈলী 🍜 | [ক্লাসিফিকেশন](4-Classification/README.md) | ক্লাসিফায়ার পরিচিতি | [Python](4-Classification/2-Classifiers-1/README.md) • [R](../../4-Classification/2-Classifiers-1/solution/R/lesson_11.html) | Jen and Cassie • Eric Wanjau | -| 12 | সুস্বাদু এশীয় ও ভারতীয় রন্ধনশৈলী 🍜 | [ক্লাসিফিকেশন](4-Classification/README.md) | আরও ক্লাসিফায়ার | [Python](4-Classification/3-Classifiers-2/README.md) • [R](../../4-Classification/3-Classifiers-2/solution/R/lesson_12.html) | Jen and Cassie • Eric Wanjau | -| 13 | সুস্বাদু এশীয় ও ভারতীয় রন্ধনশৈলী 🍜 | [ক্লাসিফিকেশন](4-Classification/README.md) | আপনার মডেল ব্যবহার করে একটি রিকমেন্ডার ওয়েব অ্যাপ তৈরি করুন | [Python](4-Classification/4-Applied/README.md) | Jen | -| 14 | ক্লাস্টারিংয়ের পরিচিতি | [ক্লাস্টারিং](5-Clustering/README.md) | আপনার ডেটা পরিষ্কার, প্রস্তুত ও ভিজ্যুয়ালাইজ করুন; ক্লাস্টারিংয়ের পরিচিতি | [Python](5-Clustering/1-Visualize/README.md) • [R](../../5-Clustering/1-Visualize/solution/R/lesson_14.html) | Jen • Eric Wanjau | -| 15 | নাইজেরিয়ার সঙ্গীত স্বাদ অন্বেষণ 🎧 | [ক্লাস্টারিং](5-Clustering/README.md) | K-Means ক্লাস্টারিং পদ্ধতি অন্বেষণ করুন | [Python](5-Clustering/2-K-Means/README.md) • [R](../../5-Clustering/2-K-Means/solution/R/lesson_15.html) | Jen • Eric Wanjau | -| 16 | প্রাকৃতিক ভাষা প্রক্রিয়াকরণের পরিচিতি ☕️ | [প্রাকৃতিক ভাষা প্রক্রিয়াকরণ](6-NLP/README.md) | একটি সাধারণ বট তৈরি করে NLP-এর মৌলিক বিষয়গুলো শিখুন | [Python](6-NLP/1-Introduction-to-NLP/README.md) | Stephen | -| 17 | সাধারণ NLP কাজসমূহ ☕️ | [প্রাকৃতিক ভাষা প্রক্রিয়াকরণ](6-NLP/README.md) | ভাষার কাঠামো নিয়ে কাজ করার সময় প্রয়োজনীয় সাধারণ কাজগুলো বুঝে আপনার NLP জ্ঞান গভীর করুন | [Python](6-NLP/2-Tasks/README.md) | Stephen | -| 18 | অনুবাদ এবং সেন্টিমেন্ট বিশ্লেষণ ♥️ | [প্রাকৃতিক ভাষা প্রক্রিয়াকরণ](6-NLP/README.md) | Jane Austen-এর লেখার ওপর অনুবাদ ও সেন্টিমেন্ট বিশ্লেষণ | [Python](6-NLP/3-Translation-Sentiment/README.md) | Stephen | -| 19 | ইউরোপের রোমান্টিক হোটেলসমূহ ♥️ | [প্রাকৃতিক ভাষা প্রক্রিয়াকরণ](6-NLP/README.md) | হোটেল রিভিউ দিয়ে সেন্টিমেন্ট বিশ্লেষণ ১ | [Python](6-NLP/4-Hotel-Reviews-1/README.md) | Stephen | -| 20 | ইউরোপের রোমান্টিক হোটেলসমূহ ♥️ | [প্রাকৃতিক ভাষা প্রক্রিয়াকরণ](6-NLP/README.md) | হোটেল রিভিউ দিয়ে সেন্টিমেন্ট বিশ্লেষণ ২ | [Python](6-NLP/5-Hotel-Reviews-2/README.md) | Stephen | -| 21 | টাইম সিরিজ ফরকাস্টিং-এর পরিচিতি | [টাইম সিরিজ](7-TimeSeries/README.md) | টাইম সিরিজ ফরকাস্টিং-এর পরিচিতি | [Python](7-TimeSeries/1-Introduction/README.md) | Francesca | -| 22 | ⚡️ বিশ্ব বিদ্যুৎ ব্যবহার ⚡️ - ARIMA দিয়ে টাইম সিরিজ ফরকাস্টিং | [টাইম সিরিজ](7-TimeSeries/README.md) | ARIMA দিয়ে টাইম সিরিজ ফরকাস্টিং | [Python](7-TimeSeries/2-ARIMA/README.md) | Francesca | -| 23 | ⚡️ বিশ্ব বিদ্যুৎ ব্যবহার ⚡️ - SVR দিয়ে টাইম সিরিজ ফরকাস্টিং | [টাইম সিরিজ](7-TimeSeries/README.md) | Support Vector Regressor দিয়ে টাইম সিরিজ ফরকাস্টিং | [Python](7-TimeSeries/3-SVR/README.md) | Anirban | -| 24 | রিইনফোর্সমেন্ট লার্নিংয়ের পরিচিতি | [রিইনফোর্সমেন্ট লার্নিং](8-Reinforcement/README.md) | Q-Learning সহ রিইনফোর্সমেন্ট লার্নিংয়ের পরিচিতি | [Python](8-Reinforcement/1-QLearning/README.md) | Dmitry | +| 09 | একটি ওয়েব অ্যাপ 🔌 | [ওয়েব অ্যাপ](3-Web-App/README.md) | আপনার প্রশিক্ষিত মডেল ব্যবহার করার জন্য একটি ওয়েব অ্যাপ নির্মাণ করুন | [Python](3-Web-App/1-Web-App/README.md) | Jen | +| 10 | ক্লাসিফিকেশনে পরিচিতি | [ক্লাসিফিকেশন](4-Classification/README.md) | আপনার ডেটা পরিষ্কার, প্রস্তুত ও ভিজ্যুয়ালাইজ করুন; ক্লাসিফিকেশনের পরিচিতি | [Python](4-Classification/1-Introduction/README.md) • [R](../../4-Classification/1-Introduction/solution/R/lesson_10.html) | Jen and Cassie • Eric Wanjau | +| 11 | সুস্বাদু এশিয়ান ও ভারতীয় খাবার 🍜 | [ক্লাসিফিকেশন](4-Classification/README.md) | ক্লাসিফায়ারদের পরিচিতি | [Python](4-Classification/2-Classifiers-1/README.md) • [R](../../4-Classification/2-Classifiers-1/solution/R/lesson_11.html) | Jen and Cassie • Eric Wanjau | +| 12 | সুস্বাদু এশিয়ান ও ভারতীয় খাবার 🍜 | [ক্লাসিফিকেশন](4-Classification/README.md) | আরও ক্লাসিফায়ার | [Python](4-Classification/3-Classifiers-2/README.md) • [R](../../4-Classification/3-Classifiers-2/solution/R/lesson_12.html) | Jen and Cassie • Eric Wanjau | +| 13 | সুস্বাদু এশিয়ান ও ভারতীয় খাবার 🍜 | [ক্লাসিফিকেশন](4-Classification/README.md) | আপনার মডেল ব্যবহার করে একটি রিকমেন্ডার ওয়েব অ্যাপ তৈরি করুন | [Python](4-Classification/4-Applied/README.md) | Jen | +| 14 | ক্লাস্টারিংয়ে পরিচিতি | [ক্লাস্টারিং](5-Clustering/README.md) | আপনার ডেটা পরিষ্কার, প্রস্তুত ও ভিজ্যুয়ালাইজ করুন; ক্লাস্টারিংয়ের পরিচিতি | [Python](5-Clustering/1-Visualize/README.md) • [R](../../5-Clustering/1-Visualize/solution/R/lesson_14.html) | Jen • Eric Wanjau | +| 15 | নাইজেরিয়ান সঙ্গীত পছন্দ অনুসন্ধান 🎧 | [ক্লাস্টারিং](5-Clustering/README.md) | K-Means ক্লাস্টারিং পদ্ধতি অন্বেষণ করুন | [Python](5-Clustering/2-K-Means/README.md) • [R](../../5-Clustering/2-K-Means/solution/R/lesson_15.html) | Jen • Eric Wanjau | +| 16 | প্রাকৃতিক ভাষা প্রক্রিয়াকরণে পরিচিতি ☕️ | [প্রাকৃতিক ভাষা প্রক্রিয়াকরণ](6-NLP/README.md) | একটি সহজ বট তৈরি করে NLP-এর মৌলিক বিষয়গুলো শিখুন | [Python](6-NLP/1-Introduction-to-NLP/README.md) | Stephen | +| 17 | সাধারণ NLP কাজসমূহ ☕️ | [প্রাকৃতিক ভাষা প্রক্রিয়াকরণ](6-NLP/README.md) | ভাষাগত কাঠামো নিয়ে কাজ করার সময় প্রয়োজনীয় সাধারণ কাজগুলো বুঝে আপনার NLP জ্ঞান গভীর করুন | [Python](6-NLP/2-Tasks/README.md) | Stephen | +| 18 | অনুবাদ ও অনুভূতি বিশ্লেষণ ♥️ | [প্রাকৃতিক ভাষা প্রক্রিয়াকরণ](6-NLP/README.md) | Jane Austen-এর সাথে অনুবাদ ও অনুভূতি বিশ্লেষণ | [Python](6-NLP/3-Translation-Sentiment/README.md) | Stephen | +| 19 | ইউরোপের রোমান্টিক হোটেলগুলো ♥️ | [প্রাকৃতিক ভাষা প্রক্রিয়াকরণ](6-NLP/README.md) | হোটেল রিভিউ দিয়ে অনুভূতি বিশ্লেষণ ১ | [Python](6-NLP/4-Hotel-Reviews-1/README.md) | Stephen | +| 20 | ইউরোপের রোমান্টিক হোটেলগুলো ♥️ | [প্রাকৃতিক ভাষা প্রক্রিয়াকরণ](6-NLP/README.md) | হোটেল রিভিউ দিয়ে অনুভূতি বিশ্লেষণ ২ | [Python](6-NLP/5-Hotel-Reviews-2/README.md) | Stephen | +| 21 | টাইম সিরিজ পূর্বাভাসে পরিচিতি | [টাইম সিরিজ](7-TimeSeries/README.md) | টাইম সিরিজ পূর্বাভাসে পরিচিতি | [Python](7-TimeSeries/1-Introduction/README.md) | Francesca | +| 22 | ⚡️ বিশ্ব বিদ্যুৎ ব্যবহার ⚡️ - ARIMA দিয়ে টাইম সিরিজ পূর্বাভাস | [টাইম সিরিজ](7-TimeSeries/README.md) | ARIMA দিয়ে টাইম সিরিজ পূর্বাভাস | [Python](7-TimeSeries/2-ARIMA/README.md) | Francesca | +| 23 | ⚡️ বিশ্ব বিদ্যুৎ ব্যবহার ⚡️ - SVR দিয়ে টাইম সিরিজ পূর্বাভাস | [টাইম সিরিজ](7-TimeSeries/README.md) | Support Vector Regressor দিয়ে টাইম সিরিজ পূর্বাভাস | [Python](7-TimeSeries/3-SVR/README.md) | Anirban | +| 24 | রিইনফোর্সমেন্ট লার্নিং-এর পরিচিতি | [রিইনফোর্সমেন্ট লার্নিং](8-Reinforcement/README.md) | Q-Learning দিয়ে রিইনফোর্সমেন্ট লার্নিং-এর পরিচিতি | [Python](8-Reinforcement/1-QLearning/README.md) | Dmitry | | 25 | পিটারকে নেকড়ে থেকে বাঁচাতে সাহায্য করুন! 🐺 | [রিইনফোর্সমেন্ট লার্নিং](8-Reinforcement/README.md) | রিইনফোর্সমেন্ট লার্নিং জিম | [Python](8-Reinforcement/2-Gym/README.md) | Dmitry | -| Postscript | বাস্তব জগতে এমএল পরিস্থিতি ও প্রয়োগ | [বাস্তব জগতে এমএল](9-Real-World/README.md) | ক্লাসিক্যাল মেশিন লার্নিং-এর কিছু আকর্ষণীয় ও প্রকাশ্য বাস্তব প্রয়োগ | [পাঠ](9-Real-World/1-Applications/README.md) | দল | -| Postscript | RAI ড্যাশবোর্ড ব্যবহার করে ML-এ মডেল ডিবাগিং | [বাস্তব জগতে এমএল](9-Real-World/README.md) | Responsible AI ড্যাশবোর্ড উপাদান ব্যবহার করে মেশিন লার্নিং-এ মডেল ডিবাগিং | [পাঠ](9-Real-World/2-Debugging-ML-Models/README.md) | Ruth Yakubu | +| পোস্টস্ক্রিপ্ট | বাস্তব জীবনের ML দৃশ্যপট ও অ্যাপ্লিকেশন | [ML in the Wild](9-Real-World/README.md) | শাস্ত্রীয় ML-এর কিছু আকর্ষণীয় ও উন্মোচনমূলক বাস্তব-জগতের অ্যাপ্লিকেশন | [পাঠ](9-Real-World/1-Applications/README.md) | Team | +| পোস্টস্ক্রিপ্ট | RAI ড্যাশবোর্ড ব্যবহার করে ML-এ মডেল ডিবাগিং | [ML in the Wild](9-Real-World/README.md) | Responsible AI ড্যাশবোর্ড উপাদান ব্যবহার করে মেশিন লার্নিং-এ মডেল ডিবাগিং | [পাঠ](9-Real-World/2-Debugging-ML-Models/README.md) | Ruth Yakubu | > [এই কোর্সের সব অতিরিক্ত সম্পদ আমাদের Microsoft Learn সংগ্রহে খুঁজে দেখুন](https://learn.microsoft.com/en-us/collections/qrqzamz1nn2wx3?WT.mc_id=academic-77952-bethanycheum) ## অফলাইন অ্যাক্সেস -আপনি [Docsify](https://docsify.js.org/#/) ব্যবহার করে এই ডকুমেন্টেশনটি অফলাইনে চালাতে পারেন। এই রিপোটি ফর্ক করুন, আপনার লোকাল মেশিনে [Docsify ইনস্টল করুন](https://docsify.js.org/#/quickstart), এবং তারপর এই রিপোর রুট ফোল্ডারে টাইপ করুন `docsify serve`. ওয়েবসাইটটি আপনার লোকালহোস্টের পোর্ট 3000-এ সার্ভ হবে: `localhost:3000`. +আপনি এই ডকুমেন্টেশনটি অফলাইনে চালাতে পারেন [Docsify](https://docsify.js.org/#/) ব্যবহার করে। এই রিপোটি fork করুন, আপনার লোকাল মেশিনে [Docsify ইনস্টল করুন](https://docsify.js.org/#/quickstart), এবং তারপর এই রিপোর রুট ফোল্ডারে টাইপ করুন `docsify serve`. ওয়েবসাইটটি আপনার লোকালহোস্টে পোর্ট 3000-এ সার্ভ হবে: `localhost:3000`. ## পিডিএফ কোরিকুলামের লিঙ্কসহ একটি পিডিএফ [এখানে](https://microsoft.github.io/ML-For-Beginners/pdf/readme.pdf) দেখুন。 -## 🎒 অন্যান্য কোর্সসমূহ +## 🎒 অন্যান্য কোর্স আমাদের দল অন্যান্য কোর্সও তৈরি করে! দেখুন: ### LangChain -[![LangChain4j - নবীনদের জন্য](https://img.shields.io/badge/LangChain4j%20for%20Beginners-22C55E?style=for-the-badge&&labelColor=E5E7EB&color=0553D6)](https://aka.ms/langchain4j-for-beginners) -[![LangChain.js - নবীনদের জন্য](https://img.shields.io/badge/LangChain.js%20for%20Beginners-22C55E?style=for-the-badge&labelColor=E5E7EB&color=0553D6)](https://aka.ms/langchainjs-for-beginners?WT.mc_id=m365-94501-dwahlin) +[![শুরুদের জন্য LangChain4j](https://img.shields.io/badge/LangChain4j%20for%20Beginners-22C55E?style=for-the-badge&&labelColor=E5E7EB&color=0553D6)](https://aka.ms/langchain4j-for-beginners) +[![শুরুদের জন্য LangChain.js](https://img.shields.io/badge/LangChain.js%20for%20Beginners-22C55E?style=for-the-badge&labelColor=E5E7EB&color=0553D6)](https://aka.ms/langchainjs-for-beginners?WT.mc_id=m365-94501-dwahlin) --- ### Azure / Edge / MCP / Agents -[![AZD - নবীনদের জন্য](https://img.shields.io/badge/AZD%20for%20Beginners-0078D4?style=for-the-badge&labelColor=E5E7EB&color=0078D4)](https://github.com/microsoft/AZD-for-beginners?WT.mc_id=academic-105485-koreyst) -[![Edge AI - নবীনদের জন্য](https://img.shields.io/badge/Edge%20AI%20for%20Beginners-00B8E4?style=for-the-badge&labelColor=E5E7EB&color=00B8E4)](https://github.com/microsoft/edgeai-for-beginners?WT.mc_id=academic-105485-koreyst) -[![MCP - নবীনদের জন্য](https://img.shields.io/badge/MCP%20for%20Beginners-009688?style=for-the-badge&labelColor=E5E7EB&color=009688)](https://github.com/microsoft/mcp-for-beginners?WT.mc_id=academic-105485-koreyst) -[![AI Agents - নবীনদের জন্য](https://img.shields.io/badge/AI%20Agents%20for%20Beginners-00C49A?style=for-the-badge&labelColor=E5E7EB&color=00C49A)](https://github.com/microsoft/ai-agents-for-beginners?WT.mc_id=academic-105485-koreyst) +[![শুরুদের জন্য AZD](https://img.shields.io/badge/AZD%20for%20Beginners-0078D4?style=for-the-badge&labelColor=E5E7EB&color=0078D4)](https://github.com/microsoft/AZD-for-beginners?WT.mc_id=academic-105485-koreyst) +[![শুরুদের জন্য Edge AI](https://img.shields.io/badge/Edge%20AI%20for%20Beginners-00B8E4?style=for-the-badge&labelColor=E5E7EB&color=00B8E4)](https://github.com/microsoft/edgeai-for-beginners?WT.mc_id=academic-105485-koreyst) +[![শুরুদের জন্য MCP](https://img.shields.io/badge/MCP%20for%20Beginners-009688?style=for-the-badge&labelColor=E5E7EB&color=009688)](https://github.com/microsoft/mcp-for-beginners?WT.mc_id=academic-105485-koreyst) +[![শুরুদের জন্য AI Agents](https://img.shields.io/badge/AI%20Agents%20for%20Beginners-00C49A?style=for-the-badge&labelColor=E5E7EB&color=00C49A)](https://github.com/microsoft/ai-agents-for-beginners?WT.mc_id=academic-105485-koreyst) --- -### Generative AI Series -[![Generative AI - নবীনদের জন্য](https://img.shields.io/badge/Generative%20AI%20for%20Beginners-8B5CF6?style=for-the-badge&labelColor=E5E7EB&color=8B5CF6)](https://github.com/microsoft/generative-ai-for-beginners?WT.mc_id=academic-105485-koreyst) -[![Generative AI (.NET)](https://img.shields.io/badge/Generative%20AI%20(.NET)-9333EA?style=for-the-badge&labelColor=E5E7EB&color=9333EA)](https://github.com/microsoft/Generative-AI-for-beginners-dotnet?WT.mc_id=academic-105485-koreyst) -[![জেনারেটিভ এআই (Java)](https://img.shields.io/badge/Generative%20AI%20(Java)-C084FC?style=for-the-badge&labelColor=E5E7EB&color=C084FC)](https://github.com/microsoft/generative-ai-for-beginners-java?WT.mc_id=academic-105485-koreyst) -[![জেনারেটিভ এআই (JavaScript)](https://img.shields.io/badge/Generative%20AI%20(JavaScript)-E879F9?style=for-the-badge&labelColor=E5E7EB&color=E879F9)](https://github.com/microsoft/generative-ai-with-javascript?WT.mc_id=academic-105485-koreyst) +### জেনারেটিভ AI সিরিজ +[![শুরুদের জন্য জেনারেটিভ AI](https://img.shields.io/badge/Generative%20AI%20for%20Beginners-8B5CF6?style=for-the-badge&labelColor=E5E7EB&color=8B5CF6)](https://github.com/microsoft/generative-ai-for-beginners?WT.mc_id=academic-105485-koreyst) +[![জেনারেটিভ AI (.NET)](https://img.shields.io/badge/Generative%20AI%20(.NET)-9333EA?style=for-the-badge&labelColor=E5E7EB&color=9333EA)](https://github.com/microsoft/Generative-AI-for-beginners-dotnet?WT.mc_id=academic-105485-koreyst) +[![জেনারেটিভ AI (Java)](https://img.shields.io/badge/Generative%20AI%20(Java)-C084FC?style=for-the-badge&labelColor=E5E7EB&color=C084FC)](https://github.com/microsoft/generative-ai-for-beginners-java?WT.mc_id=academic-105485-koreyst) +[![জেনারেটিভ AI (JavaScript)](https://img.shields.io/badge/Generative%20AI%20(JavaScript)-E879F9?style=for-the-badge&labelColor=E5E7EB&color=E879F9)](https://github.com/microsoft/generative-ai-with-javascript?WT.mc_id=academic-105485-koreyst) --- -### মূল পাঠ্য +### মূল শেখা [![শুরুদের জন্য ML](https://img.shields.io/badge/ML%20for%20Beginners-22C55E?style=for-the-badge&labelColor=E5E7EB&color=22C55E)](https://aka.ms/ml-beginners?WT.mc_id=academic-105485-koreyst) -[![শুরুদের জন্য ডেটা সায়েন্স](https://img.shields.io/badge/Data%20Science%20for%20Beginners-84CC16?style=for-the-badge&labelColor=E5E7EB&color=84CC16)](https://aka.ms/datascience-beginners?WT.mc_id=academic-105485-koreyst) -[![শুরুদের জন্য এআই](https://img.shields.io/badge/AI%20for%20Beginners-A3E635?style=for-the-badge&labelColor=E5E7EB&color=A3E635)](https://aka.ms/ai-beginners?WT.mc_id=academic-105485-koreyst) +[![শুরুদের জন্য ডাটা সায়েন্স](https://img.shields.io/badge/Data%20Science%20for%20Beginners-84CC16?style=for-the-badge&labelColor=E5E7EB&color=84CC16)](https://aka.ms/datascience-beginners?WT.mc_id=academic-105485-koreyst) +[![শুরুদের জন্য AI](https://img.shields.io/badge/AI%20for%20Beginners-A3E635?style=for-the-badge&labelColor=E5E7EB&color=A3E635)](https://aka.ms/ai-beginners?WT.mc_id=academic-105485-koreyst) [![শুরুদের জন্য সাইবারসিকিউরিটি](https://img.shields.io/badge/Cybersecurity%20for%20Beginners-F97316?style=for-the-badge&labelColor=E5E7EB&color=F97316)](https://github.com/microsoft/Security-101?WT.mc_id=academic-96948-sayoung) -[![শুরুদের জন্য ওয়েব ডেভেলপমেন্ট](https://img.shields.io/badge/Web%20Dev%20for%20Beginners-EC4899?style=for-the-badge&labelColor=E5E7EB&color=EC4899)](https://aka.ms/webdev-beginners?WT.mc_id=academic-105485-koreyst) +[![শুরুদের জন্য ওয়েব ডেভ](https://img.shields.io/badge/Web%20Dev%20for%20Beginners-EC4899?style=for-the-badge&labelColor=E5E7EB&color=EC4899)](https://aka.ms/webdev-beginners?WT.mc_id=academic-105485-koreyst) [![শুরুদের জন্য IoT](https://img.shields.io/badge/IoT%20for%20Beginners-14B8A6?style=for-the-badge&labelColor=E5E7EB&color=14B8A6)](https://aka.ms/iot-beginners?WT.mc_id=academic-105485-koreyst) [![শুরুদের জন্য XR ডেভেলপমেন্ট](https://img.shields.io/badge/XR%20Development%20for%20Beginners-38BDF8?style=for-the-badge&labelColor=E5E7EB&color=38BDF8)](https://github.com/microsoft/xr-development-for-beginners?WT.mc_id=academic-105485-koreyst) --- ### Copilot সিরিজ -[![AI-পেয়ারড প্রোগ্রামিংয়ের জন্য Copilot](https://img.shields.io/badge/Copilot%20for%20AI%20Paired%20Programming-FACC15?style=for-the-badge&labelColor=E5E7EB&color=FACC15)](https://aka.ms/GitHubCopilotAI?WT.mc_id=academic-105485-koreyst) -[![C#/.NET-এর জন্য Copilot](https://img.shields.io/badge/Copilot%20for%20C%23/.NET-FBBF24?style=for-the-badge&labelColor=E5E7EB&color=FBBF24)](https://github.com/microsoft/mastering-github-copilot-for-dotnet-csharp-developers?WT.mc_id=academic-105485-koreyst) +[![Copilot (AI-পেয়ারড প্রোগ্রামিং-এর জন্য)](https://img.shields.io/badge/Copilot%20for%20AI%20Paired%20Programming-FACC15?style=for-the-badge&labelColor=E5E7EB&color=FACC15)](https://aka.ms/GitHubCopilotAI?WT.mc_id=academic-105485-koreyst) +[![Copilot (C#/.NET-এর জন্য)](https://img.shields.io/badge/Copilot%20for%20C%23/.NET-FBBF24?style=for-the-badge&labelColor=E5E7EB&color=FBBF24)](https://github.com/microsoft/mastering-github-copilot-for-dotnet-csharp-developers?WT.mc_id=academic-105485-koreyst) [![Copilot অ্যাডভেঞ্চার](https://img.shields.io/badge/Copilot%20Adventure-FDE68A?style=for-the-badge&labelColor=E5E7EB&color=FDE68A)](https://github.com/microsoft/CopilotAdventures?WT.mc_id=academic-105485-koreyst) -## সহায়তা পেতে +## সহায়তা If you get stuck or have any questions about building AI apps. Join fellow learners and experienced developers in discussions about MCP. It's a supportive community where questions are welcome and knowledge is shared freely. [![Microsoft Foundry Discord](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) -আপনি যদি পণ্য সম্পর্কিত প্রতিক্রিয়া দিতে চান বা বিল্ড করার সময় কোনো ত্রুটি লক্ষ্য করেন, তবে দেখুন: +If you have product feedback or errors while building visit: [![Microsoft Foundry ডেভেলপার ফোরাম](https://img.shields.io/badge/GitHub-Microsoft_Foundry_Developer_Forum-blue?style=for-the-badge&logo=github&color=000000&logoColor=fff)](https://aka.ms/foundry/forum) --- -অস্বীকারোক্তি: -এই নথিটি AI অনুবাদ সেবা [Co-op Translator](https://github.com/Azure/co-op-translator) ব্যবহার করে অনুবাদ করা হয়েছে। আমরা যথার্থতার জন্য যত্নশীল হলেও, অনুগ্রহ করে মনে রাখবেন যে স্বয়ংক্রিয় অনুবাদে ত্রুটি বা অসঙ্গতি থাকতে পারে। মূল নথিটি তার মূল ভাষায়ই কর্তৃত্বপ্রাপ্ত উৎস হিসেবে বিবেচিত হওয়া উচিত। গুরুত্বপূর্ণ তথ্যের জন্য পেশাদার মানব অনুবাদ সুপারিশ করা হয়। এই অনুবাদের ব্যবহার থেকে সৃষ্ট কোনো ভুল বোঝাবুঝি বা ভুল ব্যাখ্যার জন্য আমরা দায়ী নই। +দায়-অস্বীকৃতি: +এই নথিটি AI অনুবাদ সেবা Co-op Translator (https://github.com/Azure/co-op-translator) ব্যবহার করে অনুবাদ করা হয়েছে। আমরা সঠিকতার প্রতি যত্নশীল হলেও, অনুগ্রহ করে মনে রাখবেন যে স্বয়ংক্রিয় অনুবাদে ভুল বা অসঙ্গতি থাকতে পারে। মূল নথিটিকে তার মূল ভাষায়ই কর্তৃত্বপ্রাপ্ত উৎস হিসেবে বিবেচনা করা উচিত। গুরুত্বপূর্ণ তথ্যের জন্য পেশাদার মানব অনুবাদ গ্রহণ করার পরামর্শ দেওয়া হচ্ছে। এই অনুবাদ ব্যবহারের ফলে সৃষ্ট কোনো ভুলবোঝা বা ভুল ব্যাখ্যার জন্য আমরা দায়ী নই। \ No newline at end of file diff --git a/translations/br/1-Introduction/README.md b/translations/br/1-Introduction/README.md index e7625b589..8b49ad0d2 100644 --- a/translations/br/1-Introduction/README.md +++ b/translations/br/1-Introduction/README.md @@ -11,7 +11,7 @@ CO_OP_TRANSLATOR_METADATA: Nesta seção do currículo, você será apresentado aos conceitos básicos que fundamentam o campo do aprendizado de máquina, o que ele é, e aprenderá sobre sua história e as técnicas que os pesquisadores utilizam para trabalhar com ele. Vamos explorar juntos este novo mundo do aprendizado de máquina! -![globo](../../../translated_images/globe.59f26379ceb40428672b4d9a568044618a2bf6292ecd53a5c481b90e3fa805eb.br.jpg) +![globo](../../../translated_images/globe.59f26379ceb40428.br.jpg) > Foto por Bill Oxford no Unsplash ### Aulas diff --git a/translations/br/2-Regression/1-Tools/solution/R/lesson_1-R.ipynb b/translations/br/2-Regression/1-Tools/solution/R/lesson_1-R.ipynb index f8dff255c..6e6d432cd 100644 --- a/translations/br/2-Regression/1-Tools/solution/R/lesson_1-R.ipynb +++ b/translations/br/2-Regression/1-Tools/solution/R/lesson_1-R.ipynb @@ -48,7 +48,7 @@ " width=\"630\"/>\n", "
Arte por @allison_horst
\n", "\n", - "\n" + "\n" ], "metadata": { "id": "LWNNzfqd6feZ" diff --git a/translations/br/2-Regression/2-Data/solution/R/lesson_2-R.ipynb b/translations/br/2-Regression/2-Data/solution/R/lesson_2-R.ipynb index b77281da9..9f83eac7e 100644 --- a/translations/br/2-Regression/2-Data/solution/R/lesson_2-R.ipynb +++ b/translations/br/2-Regression/2-Data/solution/R/lesson_2-R.ipynb @@ -227,7 +227,7 @@ "
Arte por @allison_horst
\n", "\n", "\n", - "\n" + "\n" ], "metadata": { "id": "o4jLY5-VZO2C" @@ -531,7 +531,7 @@ "
Infográfico por Dasani Madipalli
\n", "\n", "\n", - "\n", + "\n", "\n", "Existe um *sábio* ditado que diz o seguinte:\n", "\n", diff --git a/translations/br/2-Regression/3-Linear/solution/R/lesson_3-R.ipynb b/translations/br/2-Regression/3-Linear/solution/R/lesson_3-R.ipynb index 0d8ee31c2..5c0ea3c39 100644 --- a/translations/br/2-Regression/3-Linear/solution/R/lesson_3-R.ipynb +++ b/translations/br/2-Regression/3-Linear/solution/R/lesson_3-R.ipynb @@ -162,7 +162,7 @@ "
Arte por @allison_horst
\n", "\n", "\n", - "\n" + "\n" ], "metadata": { "id": "WdUKXk7Bs8-V" @@ -567,7 +567,7 @@ "
Infográfico por Dasani Madipalli
\n", "\n", "\n", - "\n" + "\n" ], "metadata": { "id": "YqXjLuWavNxW" @@ -808,7 +808,7 @@ "
Infográfico por Dasani Madipalli
\n", "\n", "\n", - "\n" + "\n" ], "metadata": { "id": "HOCqJXLTwtWI" diff --git a/translations/br/2-Regression/4-Logistic/solution/R/lesson_4-R.ipynb b/translations/br/2-Regression/4-Logistic/solution/R/lesson_4-R.ipynb index b438410e3..bea5f26f1 100644 --- a/translations/br/2-Regression/4-Logistic/solution/R/lesson_4-R.ipynb +++ b/translations/br/2-Regression/4-Logistic/solution/R/lesson_4-R.ipynb @@ -6,7 +6,7 @@ "source": [ "## Construir um modelo de regressão logística - Aula 4\n", "\n", - "![Infográfico de regressão logística vs. regressão linear](../../../../../../translated_images/linear-vs-logistic.ba180bf95e7ee66721ba10ebf2dac2666acbd64a88b003c83928712433a13c7d.br.png)\n", + "![Infográfico de regressão logística vs. regressão linear](../../../../../../translated_images/linear-vs-logistic.ba180bf95e7ee667.br.png)\n", "\n", "#### **[Questionário pré-aula](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/15/)**\n", "\n", @@ -78,7 +78,7 @@ "\n", "A regressão logística não oferece os mesmos recursos que a regressão linear. A primeira fornece uma previsão sobre uma `categoria binária` (\"laranja ou não laranja\"), enquanto a segunda é capaz de prever `valores contínuos`, por exemplo, dado a origem de uma abóbora e o momento da colheita, *quanto o preço dela vai aumentar*.\n", "\n", - "![Infográfico por Dasani Madipalli](../../../../../../translated_images/pumpkin-classifier.562771f104ad5436b87d1c67bca02a42a17841133556559325c0a0e348e5b774.br.png)\n", + "![Infográfico por Dasani Madipalli](../../../../../../translated_images/pumpkin-classifier.562771f104ad5436.br.png)\n", "\n", "### Outras classificações\n", "\n", @@ -88,7 +88,7 @@ "\n", "- **Ordinal**, que envolve categorias ordenadas, útil se quisermos organizar nossos resultados de forma lógica, como nossas abóboras ordenadas por um número finito de tamanhos (mini,pequeno,médio,grande,xl,xxl).\n", "\n", - "![Regressão multinomial vs ordinal](../../../../../../translated_images/multinomial-vs-ordinal.36701b4850e37d86c9dd49f7bef93a2f94dbdb8fe03443eb68f0542f97f28f29.br.png)\n", + "![Regressão multinomial vs ordinal](../../../../../../translated_images/multinomial-vs-ordinal.36701b4850e37d86.br.png)\n", "\n", "#### **As variáveis NÃO precisam ser correlacionadas**\n", "\n", diff --git a/translations/br/2-Regression/README.md b/translations/br/2-Regression/README.md index bb18e6a7c..e9f947627 100644 --- a/translations/br/2-Regression/README.md +++ b/translations/br/2-Regression/README.md @@ -12,7 +12,7 @@ CO_OP_TRANSLATOR_METADATA: Na América do Norte, as abóboras são frequentemente esculpidas em rostos assustadores para o Halloween. Vamos descobrir mais sobre esses vegetais fascinantes! -![jack-o-lanterns](../../../translated_images/jack-o-lanterns.181c661a9212457d7756f37219f660f1358af27554d856e5a991f16b4e15337c.br.jpg) +![jack-o-lanterns](../../../translated_images/jack-o-lanterns.181c661a9212457d.br.jpg) > Foto de Beth Teutschmann no Unsplash ## O que você vai aprender diff --git a/translations/br/3-Web-App/README.md b/translations/br/3-Web-App/README.md index 2e8e51b92..0ece173f3 100644 --- a/translations/br/3-Web-App/README.md +++ b/translations/br/3-Web-App/README.md @@ -11,7 +11,7 @@ CO_OP_TRANSLATOR_METADATA: Nesta seção do currículo, você será introduzido a um tópico aplicado de aprendizado de máquina: como salvar seu modelo Scikit-learn como um arquivo que pode ser usado para fazer previsões dentro de um aplicativo web. Depois que o modelo estiver salvo, você aprenderá como utilizá-lo em um aplicativo web construído com Flask. Primeiro, você criará um modelo usando alguns dados relacionados a avistamentos de OVNIs! Em seguida, você construirá um aplicativo web que permitirá inserir um número de segundos junto com valores de latitude e longitude para prever qual país relatou ter visto um OVNI. -![Estacionamento de OVNIs](../../../translated_images/ufo.9e787f5161da9d4d1dafc537e1da09be8210f2ee996cb638aa5cee1d92867a04.br.jpg) +![Estacionamento de OVNIs](../../../translated_images/ufo.9e787f5161da9d4d.br.jpg) Foto por Michael Herren no Unsplash diff --git a/translations/br/4-Classification/README.md b/translations/br/4-Classification/README.md index 3a114eeb4..00b50ee06 100644 --- a/translations/br/4-Classification/README.md +++ b/translations/br/4-Classification/README.md @@ -13,7 +13,7 @@ CO_OP_TRANSLATOR_METADATA: Na Ásia e na Índia, as tradições culinárias são extremamente diversas e muito deliciosas! Vamos analisar dados sobre culinárias regionais para tentar entender seus ingredientes. -![Vendedor de comida tailandesa](../../../translated_images/thai-food.c47a7a7f9f05c21892a1f9dc7bf30669e6d18dfda420c5c7ebb4153f6a304edd.br.jpg) +![Vendedor de comida tailandesa](../../../translated_images/thai-food.c47a7a7f9f05c218.br.jpg) > Foto por Lisheng Chang no Unsplash ## O que você vai aprender diff --git a/translations/br/5-Clustering/README.md b/translations/br/5-Clustering/README.md index 9b53b8e4e..5fa5cc5b3 100644 --- a/translations/br/5-Clustering/README.md +++ b/translations/br/5-Clustering/README.md @@ -15,7 +15,7 @@ Clustering é uma tarefa de aprendizado de máquina que busca encontrar objetos O público diversificado da Nigéria tem gostos musicais igualmente variados. Usando dados extraídos do Spotify (inspirado por [este artigo](https://towardsdatascience.com/country-wise-visual-analysis-of-music-taste-using-spotify-api-seaborn-in-python-77f5b749b421)), vamos analisar algumas músicas populares na Nigéria. Este conjunto de dados inclui informações sobre a pontuação de 'dançabilidade', 'acousticness', volume, 'speechiness', popularidade e energia de várias músicas. Será interessante descobrir padrões nesses dados! -![Um toca-discos](../../../translated_images/turntable.f2b86b13c53302dc106aa741de9dc96ac372864cf458dd6f879119857aab01da.br.jpg) +![Um toca-discos](../../../translated_images/turntable.f2b86b13c53302dc.br.jpg) > Foto por Marcela Laskoski no Unsplash diff --git a/translations/br/6-NLP/README.md b/translations/br/6-NLP/README.md index ae0736aa0..8dcb90bd3 100644 --- a/translations/br/6-NLP/README.md +++ b/translations/br/6-NLP/README.md @@ -17,7 +17,7 @@ Nesta seção do currículo, você será introduzido a um dos usos mais difundid Nestas lições, aprenderemos os fundamentos do PLN construindo pequenos bots conversacionais para entender como o aprendizado de máquina ajuda a tornar essas conversas cada vez mais 'inteligentes'. Você viajará no tempo, conversando com Elizabeth Bennett e Mr. Darcy do clássico romance de Jane Austen, **Orgulho e Preconceito**, publicado em 1813. Depois, você aprofundará seu conhecimento aprendendo sobre análise de sentimentos por meio de avaliações de hotéis na Europa. -![Livro Orgulho e Preconceito e chá](../../../translated_images/p&p.279f1c49ecd889419e4ce6206525e9aa30d32a976955cd24daa636c361c6391f.br.jpg) +![Livro Orgulho e Preconceito e chá](../../../translated_images/p&p.279f1c49ecd88941.br.jpg) > Foto por Elaine Howlin no Unsplash ## Lições diff --git a/translations/br/7-TimeSeries/README.md b/translations/br/7-TimeSeries/README.md index f83e2a254..7b366d255 100644 --- a/translations/br/7-TimeSeries/README.md +++ b/translations/br/7-TimeSeries/README.md @@ -17,7 +17,7 @@ Nestes dois módulos, você será introduzido à previsão de séries temporais, Nosso foco regional é o uso de eletricidade no mundo, um conjunto de dados interessante para aprender a prever o consumo futuro de energia com base em padrões de carga anteriores. Você verá como esse tipo de previsão pode ser extremamente útil em um ambiente empresarial. -![rede elétrica](../../../translated_images/electric-grid.0c21d5214db09ffae93c06a87ca2abbb9ba7475ef815129c5b423d7f9a7cf136.br.jpg) +![rede elétrica](../../../translated_images/electric-grid.0c21d5214db09ffa.br.jpg) Foto de [Peddi Sai hrithik](https://unsplash.com/@shutter_log?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText) de torres elétricas em uma estrada em Rajasthan no [Unsplash](https://unsplash.com/s/photos/electric-india?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText) diff --git a/translations/br/8-Reinforcement/README.md b/translations/br/8-Reinforcement/README.md index e7f3cb9d4..0acca880e 100644 --- a/translations/br/8-Reinforcement/README.md +++ b/translations/br/8-Reinforcement/README.md @@ -13,7 +13,7 @@ O aprendizado por reforço, RL, é considerado um dos paradigmas básicos de apr Imagine que você tem um ambiente simulado, como o mercado de ações. O que acontece se você impuser uma determinada regulamentação? Isso terá um efeito positivo ou negativo? Se algo negativo acontecer, você precisa aceitar esse _reforço negativo_, aprender com ele e mudar de direção. Se o resultado for positivo, você precisa construir sobre esse _reforço positivo_. -![Pedro e o lobo](../../../translated_images/peter.779730f9ba3a8a8d9290600dcf55f2e491c0640c785af7ac0d64f583c49b8864.br.png) +![Pedro e o lobo](../../../translated_images/peter.779730f9ba3a8a8d.br.png) > Pedro e seus amigos precisam escapar do lobo faminto! Imagem por [Jen Looper](https://twitter.com/jenlooper) diff --git a/translations/br/9-Real-World/README.md b/translations/br/9-Real-World/README.md index da0226b43..baae8f48c 100644 --- a/translations/br/9-Real-World/README.md +++ b/translations/br/9-Real-World/README.md @@ -11,7 +11,7 @@ CO_OP_TRANSLATOR_METADATA: Nesta seção do currículo, você será apresentado a algumas aplicações reais do aprendizado de máquina clássico. Pesquisamos na internet para encontrar artigos e publicações sobre aplicações que utilizam essas estratégias, evitando ao máximo redes neurais, aprendizado profundo e IA. Descubra como o aprendizado de máquina é usado em sistemas empresariais, aplicações ecológicas, finanças, artes e cultura, entre outros. -![chess](../../../translated_images/chess.e704a268781bdad85d1876b6c2295742fa0d856e7dcf3659147052df9d3db205.br.jpg) +![chess](../../../translated_images/chess.e704a268781bdad8.br.jpg) > Foto por Alexis Fauvet no Unsplash diff --git a/translations/br/README.md b/translations/br/README.md index 1951bca3b..78d37d211 100644 --- a/translations/br/README.md +++ b/translations/br/README.md @@ -1,19 +1,19 @@ [![Licença do GitHub](https://img.shields.io/github/license/microsoft/ML-For-Beginners.svg)](https://github.com/microsoft/ML-For-Beginners/blob/master/LICENSE) -[![Colaboradores do GitHub](https://img.shields.io/github/contributors/microsoft/ML-For-Beginners.svg)](https://GitHub.com/microsoft/ML-For-Beginners/graphs/contributors/) -[![Problemas do GitHub](https://img.shields.io/github/issues/microsoft/ML-For-Beginners.svg)](https://GitHub.com/microsoft/ML-For-Beginners/issues/) +[![Contribuidores do GitHub](https://img.shields.io/github/contributors/microsoft/ML-For-Beginners.svg)](https://GitHub.com/microsoft/ML-For-Beginners/graphs/contributors/) +[![Problemas no GitHub](https://img.shields.io/github/issues/microsoft/ML-For-Beginners.svg)](https://GitHub.com/microsoft/ML-For-Beginners/issues/) [![Pull requests do GitHub](https://img.shields.io/github/issues-pr/microsoft/ML-For-Beginners.svg)](https://GitHub.com/microsoft/ML-For-Beginners/pulls/) [![PRs bem-vindos](https://img.shields.io/badge/PRs-welcome-brightgreen.svg?style=flat-square)](http://makeapullrequest.com) -[![Discord do Microsoft Foundry](https://img.shields.io/github/watchers/microsoft/ML-For-Beginners.svg?style=social&label=Watch)](https://GitHub.com/microsoft/ML-For-Beginners/watchers/) +[![Observadores do GitHub](https://img.shields.io/github/watchers/microsoft/ML-For-Beginners.svg?style=social&label=Watch)](https://GitHub.com/microsoft/ML-For-Beginners/watchers/) [![Forks do GitHub](https://img.shields.io/github/forks/microsoft/ML-For-Beginners.svg?style=social&label=Fork)](https://GitHub.com/microsoft/ML-For-Beginners/network/) [![Estrelas do GitHub](https://img.shields.io/github/stars/microsoft/ML-For-Beginners.svg?style=social&label=Star)](https://GitHub.com/microsoft/ML-For-Beginners/stargazers/) @@ -22,65 +22,65 @@ CO_OP_TRANSLATOR_METADATA: #### Suportado via GitHub Action (Automatizado e Sempre Atualizado) -[Árabe](../ar/README.md) | [Bengalês](../bn/README.md) | [Búlgaro](../bg/README.md) | [Birmanês (Myanmar)](../my/README.md) | [Chinês (Simplificado)](../zh/README.md) | [Chinês (Tradicional, Hong Kong)](../hk/README.md) | [Chinês (Tradicional, Macau)](../mo/README.md) | [Chinês (Tradicional, Taiwan)](../tw/README.md) | [Croata](../hr/README.md) | [Tcheco](../cs/README.md) | [Dinamarquês](../da/README.md) | [Holandês](../nl/README.md) | [Estoniano](../et/README.md) | [Finlandês](../fi/README.md) | [Francês](../fr/README.md) | [Alemão](../de/README.md) | [Grego](../el/README.md) | [Hebraico](../he/README.md) | [Hindi](../hi/README.md) | [Húngaro](../hu/README.md) | [Indonésio](../id/README.md) | [Italiano](../it/README.md) | [Japonês](../ja/README.md) | [Kannada](../kn/README.md) | [Coreano](../ko/README.md) | [Lituano](../lt/README.md) | [Malaio](../ms/README.md) | [Malayalam](../ml/README.md) | [Marathi](../mr/README.md) | [Nepali](../ne/README.md) | [Pidgin Nigeriano](../pcm/README.md) | [Norueguês](../no/README.md) | [Persa (Farsi)](../fa/README.md) | [Polonês](../pl/README.md) | [Português (Brasil)](./README.md) | [Português (Portugal)](../pt/README.md) | [Punjabi (Gurmukhi)](../pa/README.md) | [Romeno](../ro/README.md) | [Russo](../ru/README.md) | [Sérvio (Cirílico)](../sr/README.md) | [Eslovaco](../sk/README.md) | [Esloveno](../sl/README.md) | [Espanhol](../es/README.md) | [Suaíli](../sw/README.md) | [Sueco](../sv/README.md) | [Tagalog (Filipino)](../tl/README.md) | [Tamil](../ta/README.md) | [Telugu](../te/README.md) | [Tailandês](../th/README.md) | [Turco](../tr/README.md) | [Ucraniano](../uk/README.md) | [Urdu](../ur/README.md) | [Vietnamita](../vi/README.md) +[Árabe](../ar/README.md) | [Bengalês](../bn/README.md) | [Búlgaro](../bg/README.md) | [Burmês (Myanmar)](../my/README.md) | [Chinês (Simplificado)](../zh/README.md) | [Chinês (Tradicional, Hong Kong)](../hk/README.md) | [Chinês (Tradicional, Macau)](../mo/README.md) | [Chinês (Tradicional, Taiwan)](../tw/README.md) | [Croata](../hr/README.md) | [Tcheco](../cs/README.md) | [Dinamarquês](../da/README.md) | [Holandês](../nl/README.md) | [Estoniano](../et/README.md) | [Finlandês](../fi/README.md) | [Francês](../fr/README.md) | [Alemão](../de/README.md) | [Grego](../el/README.md) | [Hebraico](../he/README.md) | [Hindi](../hi/README.md) | [Húngaro](../hu/README.md) | [Indonésio](../id/README.md) | [Italiano](../it/README.md) | [Japonês](../ja/README.md) | [Kannada](../kn/README.md) | [Coreano](../ko/README.md) | [Lituano](../lt/README.md) | [Malaio](../ms/README.md) | [Malayalam](../ml/README.md) | [Marata](../mr/README.md) | [Nepali](../ne/README.md) | [Pidgin Nigeriano](../pcm/README.md) | [Norueguês](../no/README.md) | [Persa (Farsi)](../fa/README.md) | [Polonês](../pl/README.md) | [Português (Brasil)](./README.md) | [Português (Portugal)](../pt/README.md) | [Punjabi (Gurmukhi)](../pa/README.md) | [Romeno](../ro/README.md) | [Russo](../ru/README.md) | [Sérvio (Cirílico)](../sr/README.md) | [Eslovaco](../sk/README.md) | [Esloveno](../sl/README.md) | [Espanhol](../es/README.md) | [Suaíli](../sw/README.md) | [Sueco](../sv/README.md) | [Tagalog (Filipino)](../tl/README.md) | [Tamil](../ta/README.md) | [Telugu](../te/README.md) | [Tailandês](../th/README.md) | [Turco](../tr/README.md) | [Ucraniano](../uk/README.md) | [Urdu](../ur/README.md) | [Vietnamita](../vi/README.md) #### Junte-se à Nossa Comunidade [![Microsoft Foundry Discord](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) -Temos uma série no Discord "Aprenda com IA" em andamento; saiba mais e junte-se a nós em [Série Aprenda com IA](https://aka.ms/learnwithai/discord) de 18 - 30 de setembro de 2025. Você receberá dicas e truques sobre como usar o GitHub Copilot para Data Science. +Temos uma série no Discord "Learn with AI" em andamento, saiba mais e junte-se a nós em [Série Aprenda com IA](https://aka.ms/learnwithai/discord) de 18 a 30 de setembro de 2025. Você receberá dicas e truques de como usar o GitHub Copilot para Data Science. -![Série Aprenda com IA](../../translated_images/3.9b58fd8d6c373c20c588c5070c4948a826ab074426c28ceb5889641294373dfc.br.png) +![Série Aprenda com IA](../../translated_images/3.9b58fd8d6c373c20.br.png) # Aprendizado de Máquina para Iniciantes - Um Currículo > 🌍 Viaje pelo mundo enquanto exploramos Aprendizado de Máquina por meio das culturas do mundo 🌍 -Os Cloud Advocates da Microsoft têm o prazer de oferecer um currículo de 12 semanas e 26 aulas totalmente dedicado a **Aprendizado de Máquina**. Neste currículo, você aprenderá sobre o que às vezes é chamado de **aprendizado de máquina clássico**, usando principalmente Scikit-learn como biblioteca e evitando deep learning, que é abordado em nosso [currículo 'AI for Beginners'](https://aka.ms/ai4beginners). Combine estas aulas com nosso [currículo 'Data Science for Beginners'](https://aka.ms/ds4beginners), também! +Os Cloud Advocates da Microsoft têm o prazer de oferecer um currículo de 12 semanas e 26 lições totalmente sobre **Aprendizado de Máquina**. Neste currículo, você aprenderá sobre o que às vezes é chamado de **aprendizado de máquina clássico**, usando principalmente a biblioteca Scikit-learn e evitando deep learning, que é abordado em nosso [currículo IA para Iniciantes](https://aka.ms/ai4beginners). Combine estas lições com nosso ['Data Science for Beginners' curriculum](https://aka.ms/ds4beginners) também! -Viaje conosco ao redor do mundo enquanto aplicamos essas técnicas clássicas a dados de muitas regiões do planeta. Cada lição inclui questionários pré e pós-aula, instruções escritas para concluir a lição, uma solução, uma tarefa e mais. Nossa pedagogia baseada em projetos permite que você aprenda enquanto constrói, uma maneira comprovada de novos conhecimentos "fixarem". +Viaje conosco ao redor do mundo enquanto aplicamos essas técnicas clássicas a dados de muitas regiões do planeta. Cada lição inclui quizzes pré e pós-aula, instruções escritas para completar a lição, uma solução, uma tarefa e mais. Nossa pedagogia baseada em projetos permite que você aprenda enquanto constrói, uma maneira comprovada de fixar novas habilidades. -**✍️ Agradecimentos sinceros aos nossos autores** Jen Looper, Stephen Howell, Francesca Lazzeri, Tomomi Imura, Cassie Breviu, Dmitry Soshnikov, Chris Noring, Anirban Mukherjee, Ornella Altunyan, Ruth Yakubu and Amy Boyd +**✍️ Agradecimentos calorosos aos nossos autores** Jen Looper, Stephen Howell, Francesca Lazzeri, Tomomi Imura, Cassie Breviu, Dmitry Soshnikov, Chris Noring, Anirban Mukherjee, Ornella Altunyan, Ruth Yakubu and Amy Boyd **🎨 Agradecimentos também aos nossos ilustradores** Tomomi Imura, Dasani Madipalli, e Jen Looper -**🙏 Agradecimentos especiais 🙏 aos nossos Microsoft Student Ambassador autores, revisores, e contribuidores de conteúdo**, notavelmente Rishit Dagli, Muhammad Sakib Khan Inan, Rohan Raj, Alexandru Petrescu, Abhishek Jaiswal, Nawrin Tabassum, Ioan Samuila, e Snigdha Agarwal +**🙏 Agradecimentos especiais 🙏 aos nossos Microsoft Student Ambassador autores, revisores e contribuidores de conteúdo**, notadamente Rishit Dagli, Muhammad Sakib Khan Inan, Rohan Raj, Alexandru Petrescu, Abhishek Jaiswal, Nawrin Tabassum, Ioan Samuila, and Snigdha Agarwal -**🤩 Gratidão extra aos Microsoft Student Ambassadors Eric Wanjau, Jasleen Sondhi, e Vidushi Gupta pelas nossas lições em R!** +**🤩 Agradecimento extra aos Microsoft Student Ambassadors Eric Wanjau, Jasleen Sondhi, e Vidushi Gupta pelas nossas lições em R!** -# Como Começar +# Começando Siga estes passos: -1. **Faça um fork do repositório**: Clique no botão "Fork" no canto superior direito desta página. +1. **Faça um fork do Repositório**: Clique no botão "Fork" no canto superior direito desta página. 2. **Clone o Repositório**: `git clone https://github.com/microsoft/ML-For-Beginners.git` -> [encontre todos os recursos adicionais deste curso em nossa coleção Microsoft Learn](https://learn.microsoft.com/en-us/collections/qrqzamz1nn2wx3?WT.mc_id=academic-77952-bethanycheum) +> [encontre todos os recursos adicionais para este curso em nossa coleção Microsoft Learn](https://learn.microsoft.com/en-us/collections/qrqzamz1nn2wx3?WT.mc_id=academic-77952-bethanycheum) -> 🔧 **Precisa de ajuda?** Consulte nosso [Guia de Solução de Problemas](TROUBLESHOOTING.md) para soluções para problemas comuns de instalação, configuração e execução das lições. +> 🔧 **Precisa de ajuda?** Consulte nosso [Guia de Solução de Problemas](TROUBLESHOOTING.md) para soluções de problemas comuns com instalação, configuração e execução das lições. -**[Estudantes](https://aka.ms/student-page)**, para usar este currículo, faça um fork do repositório inteiro para sua própria conta no GitHub e complete os exercícios sozinho ou em grupo: +**[Estudantes](https://aka.ms/student-page)**, para usar este currículo, faça um fork de todo o repositório para sua própria conta do GitHub e complete os exercícios sozinho ou em grupo: -- Comece com um questionário pré-aula. -- Leia a aula e complete as atividades, pausando e refletindo a cada verificação de conhecimento. -- Tente criar os projetos compreendendo as lições em vez de apenas executar o código da solução; no entanto, esse código está disponível nas pastas `/solution` em cada lição orientada a projeto. -- Faça o questionário pós-aula. +- Comece com um quiz pré-aula. +- Leia a aula e complete as atividades, fazendo pausas e refletindo em cada verificação de conhecimento. +- Tente criar os projetos compreendendo as lições em vez de executar o código da solução; no entanto, esse código está disponível nas pastas `/solution` em cada lição orientada por projeto. +- Faça o quiz pós-aula. - Complete o desafio. - Complete a tarefa. -- Após concluir um grupo de lições, visite o [Fórum de Discussão](https://github.com/microsoft/ML-For-Beginners/discussions) e "aprenda em voz alta" preenchendo a rubrica PAT apropriada. Uma 'PAT' é uma Progress Assessment Tool (Ferramenta de Avaliação de Progresso) que é uma rubrica que você preenche para aprofundar seu aprendizado. Você também pode reagir a outras PATs para que possamos aprender juntos. +- Depois de concluir um grupo de lições, visite o [Fórum de Discussão](https://github.com/microsoft/ML-For-Beginners/discussions) e "aprenda em voz alta" preenchendo a rubrica PAT apropriada. Um 'PAT' é uma Progress Assessment Tool (Ferramenta de Avaliação de Progresso) que é uma rubrica que você preenche para aprofundar seu aprendizado. Você também pode reagir a outros PATs para que possamos aprender juntos. -> Para estudo adicional, recomendamos seguir estes módulos e trilhas de aprendizado do [Microsoft Learn](https://docs.microsoft.com/en-us/users/jenlooper-2911/collections/k7o7tg1gp306q4?WT.mc_id=academic-77952-leestott). +> Para estudo adicional, recomendamos seguir estes módulos e trilhas de aprendizagem do [Microsoft Learn](https://docs.microsoft.com/en-us/users/jenlooper-2911/collections/k7o7tg1gp306q4?WT.mc_id=academic-77952-leestott). -**Professores**, incluímos [algumas sugestões](for-teachers.md) sobre como usar este currículo. +**Professores**, incluímos algumas sugestões sobre como usar este currículo: [for-teachers.md](for-teachers.md). --- -## Guias em vídeo +## Tutoriais em vídeo -Algumas das lições estão disponíveis em vídeo de formato curto. Você pode encontrá-los incorporados nas lições ou na [lista de reprodução ML for Beginners no canal Microsoft Developer no YouTube](https://aka.ms/ml-beginners-videos) clicando na imagem abaixo. +Algumas das lições estão disponíveis em vídeo de formato curto. Você pode encontrar todos eles incorporados nas lições, ou na [playlist ML for Beginners no canal Microsoft Developer no YouTube](https://aka.ms/ml-beginners-videos) clicando na imagem abaixo. -[![Banner ML para iniciantes](../../translated_images/ml-for-beginners-video-banner.63f694a100034bc6251134294459696e070a3a9a04632e9fe6a24aa0de4a7384.br.png)](https://aka.ms/ml-beginners-videos) +[![Banner ML para iniciantes](../../translated_images/ml-for-beginners-video-banner.63f694a100034bc6.br.png)](https://aka.ms/ml-beginners-videos) --- @@ -90,71 +90,71 @@ Algumas das lições estão disponíveis em vídeo de formato curto. Você pode **Gif por** [Mohit Jaisal](https://linkedin.com/in/mohitjaisal) -> 🎥 Clique na imagem acima para um vídeo sobre o projeto e as pessoas que o criaram! +> 🎥 Clique na imagem acima para ver um vídeo sobre o projeto e as pessoas que o criaram! --- ## Pedagogia -Escolhemos dois princípios pedagógicos ao construir este currículo: garantir que seja prático e **baseado em projetos** e que inclua **questionários frequentes**. Além disso, este currículo tem um **tema** comum para proporcionar coesão. +Escolhemos dois princípios pedagógicos ao construir este currículo: garantir que ele seja prático e **baseado em projetos** e que inclua **questionários frequentes**. Além disso, este currículo tem um **tema** comum para dar coesão. -Ao garantir que o conteúdo esteja alinhado com projetos, o processo torna-se mais envolvente para os alunos e a retenção de conceitos é aumentada. Além disso, um questionário de baixo risco antes da aula orienta a intenção do aluno para aprender um tópico, enquanto um segundo questionário após a aula assegura maior retenção. Este currículo foi projetado para ser flexível e divertido e pode ser feito como um todo ou em partes. Os projetos começam pequenos e tornam-se progressivamente mais complexos até o fim do ciclo de 12 semanas. Este currículo também inclui um posfácio sobre aplicações do mundo real de ML, que pode ser usado como crédito extra ou como base para discussão. +Ao garantir que o conteúdo esteja alinhado com projetos, o processo se torna mais envolvente para os estudantes e a retenção dos conceitos será aumentada. Além disso, um quiz de baixo risco antes da aula define a intenção do estudante em aprender um tópico, enquanto um segundo quiz após a aula garante maior retenção. Este currículo foi projetado para ser flexível e divertido e pode ser feito na íntegra ou em partes. Os projetos começam pequenos e se tornam progressivamente mais complexos até o final do ciclo de 12 semanas. Este currículo também inclui um posfácio sobre aplicações do mundo real de ML, que pode ser usado como crédito extra ou como base para discussão. -> Encontre nosso [Código de Conduta](CODE_OF_CONDUCT.md), [Contribuindo](CONTRIBUTING.md), [Tradução](TRANSLATIONS.md), e diretrizes de [Solução de Problemas](TROUBLESHOOTING.md). Agradecemos seu feedback construtivo! +> Encontre nosso [Código de Conduta](CODE_OF_CONDUCT.md), [Contribuindo](CONTRIBUTING.md), [Tradução](TRANSLATIONS.md), e diretrizes de [Solução de Problemas](TROUBLESHOOTING.md). Agradecemos seus comentários construtivos! ## Cada lição inclui - sketchnote opcional - vídeo suplementar opcional -- guia em vídeo (apenas algumas lições) -- [questionário pré-aula de aquecimento](https://ff-quizzes.netlify.app/en/ml/) +- tutorial em vídeo (apenas algumas lições) +- [quiz de aquecimento pré-aula](https://ff-quizzes.netlify.app/en/ml/) - lição escrita -- para lições baseadas em projetos, guias passo a passo sobre como construir o projeto +- para aulas baseadas em projetos, guias passo a passo sobre como construir o projeto - verificações de conhecimento - um desafio - leitura suplementar - tarefa -- [questionário pós-aula](https://ff-quizzes.netlify.app/en/ml/) +- [quiz pós-aula](https://ff-quizzes.netlify.app/en/ml/) -> **Uma nota sobre idiomas**: Estas lições são escritas principalmente em Python, mas muitas também estão disponíveis em R. Para completar uma lição em R, vá para a pasta `/solution` e procure as lições em R. Elas incluem uma extensão .rmd que representa um arquivo **R Markdown** que pode ser simplesmente definido como a incorporação de `code chunks` (de R ou outras linguagens) e um `YAML header` (que orienta como formatar saídas como PDF) em um `Markdown document`. Como tal, serve como um excelente framework de autoria para ciência de dados, pois permite combinar seu código, sua saída e seus pensamentos, permitindo escrevê-los em Markdown. Além disso, documentos R Markdown podem ser renderizados para formatos de saída como PDF, HTML ou Word. +> **Uma nota sobre linguagens**: Essas lições são escritas principalmente em Python, mas muitas também estão disponíveis em R. Para completar uma lição em R, vá até a pasta `/solution` e procure por lições em R. Elas incluem uma extensão .rmd que representa um arquivo **R Markdown** que pode ser simplesmente definido como uma incorporação de `trechos de código` (de R ou outras linguagens) e um `cabeçalho YAML` (que orienta como formatar saídas como PDF) em um `documento Markdown`. Como tal, serve como um framework exemplar de autoria para ciência de dados, pois permite combinar seu código, sua saída e seus pensamentos escrevendo-os em Markdown. Além disso, documentos R Markdown podem ser renderizados para formatos de saída como PDF, HTML ou Word. -> **Uma nota sobre questionários**: Todos os questionários estão contidos na [pasta Quiz App](../../quiz-app), totalizando 52 questionários de três perguntas cada. Eles estão vinculados nas lições, mas o aplicativo de questionário pode ser executado localmente; siga as instruções na pasta `quiz-app` para hospedar localmente ou implantar no Azure. +> **Uma nota sobre quizzes**: Todos os quizzes estão contidos na [pasta Quiz App](../../quiz-app), totalizando 52 quizzes de três perguntas cada. Eles estão vinculados a partir das lições, mas o app de quizzes pode ser executado localmente; siga as instruções na pasta `quiz-app` para hospedar localmente ou implantar no Azure. | Número da Lição | Tópico | Agrupamento da Lição | Objetivos de Aprendizagem | Lição Vinculada | Autor | | :-----------: | :------------------------------------------------------------: | :-------------------------------------------------: | ------------------------------------------------------------------------------------------------------------------------------- | :--------------------------------------------------------------------------------------------------------------------------------------: | :--------------------------------------------------: | -| 01 | Introdução ao aprendizado de máquina | [Introdução](1-Introduction/README.md) | Aprenda os conceitos básicos por trás do aprendizado de máquina | [Lição](1-Introduction/1-intro-to-ML/README.md) | Muhammad | -| 02 | A história do aprendizado de máquina | [Introdução](1-Introduction/README.md) | Aprenda a história subjacente a este campo | [Lição](1-Introduction/2-history-of-ML/README.md) | Jen and Amy | -| 03 | Equidade e aprendizado de máquina | [Introdução](1-Introduction/README.md) | Quais são as questões filosóficas importantes sobre equidade que os alunos devem considerar ao construir e aplicar modelos de ML? | [Lição](1-Introduction/3-fairness/README.md) | Tomomi | -| 04 | Técnicas para aprendizado de máquina | [Introdução](1-Introduction/README.md) | Quais técnicas os pesquisadores de ML usam para construir modelos de ML? | [Lição](1-Introduction/4-techniques-of-ML/README.md) | Chris and Jen | -| 05 | Introdução à regressão | [Regressão](2-Regression/README.md) | Comece com Python e Scikit-learn para modelos de regressão | [Python](2-Regression/1-Tools/README.md) • [R](../../2-Regression/1-Tools/solution/R/lesson_1.html) | Jen • Eric Wanjau | -| 06 | Preços de abóbora na América do Norte 🎃 | [Regressão](2-Regression/README.md) | Visualize e limpe os dados em preparação para ML | [Python](2-Regression/2-Data/README.md) • [R](../../2-Regression/2-Data/solution/R/lesson_2.html) | Jen • Eric Wanjau | -| 07 | Preços de abóbora na América do Norte 🎃 | [Regressão](2-Regression/README.md) | Construa modelos de regressão linear e polinomial | [Python](2-Regression/3-Linear/README.md) • [R](../../2-Regression/3-Linear/solution/R/lesson_3.html) | Jen and Dmitry • Eric Wanjau | -| 08 | Preços de abóbora na América do Norte 🎃 | [Regressão](2-Regression/README.md) | Construa um modelo de regressão logística | [Python](2-Regression/4-Logistic/README.md) • [R](../../2-Regression/4-Logistic/solution/R/lesson_4.html) | Jen • Eric Wanjau | -| 09 | Um Aplicativo Web 🔌 | [Aplicativo Web](3-Web-App/README.md) | Construa um aplicativo web para usar seu modelo treinado | [Python](3-Web-App/1-Web-App/README.md) | Jen | -| 10 | Introdução à classificação | [Classificação](4-Classification/README.md) | Limpe, prepare e visualize seus dados; introdução à classificação | [Python](4-Classification/1-Introduction/README.md) • [R](../../4-Classification/1-Introduction/solution/R/lesson_10.html) | Jen e Cassie • Eric Wanjau | -| 11 | Deliciosas culinárias asiática e indiana 🍜 | [Classificação](4-Classification/README.md) | Introdução aos classificadores | [Python](4-Classification/2-Classifiers-1/README.md) • [R](../../4-Classification/2-Classifiers-1/solution/R/lesson_11.html) | Jen e Cassie • Eric Wanjau | -| 12 | Deliciosas culinárias asiática e indiana 🍜 | [Classificação](4-Classification/README.md) | Mais classificadores | [Python](4-Classification/3-Classifiers-2/README.md) • [R](../../4-Classification/3-Classifiers-2/solution/R/lesson_12.html) | Jen e Cassie • Eric Wanjau | -| 13 | Deliciosas culinárias asiática e indiana 🍜 | [Classificação](4-Classification/README.md) | Construa um aplicativo web de recomendação usando seu modelo | [Python](4-Classification/4-Applied/README.md) | Jen | -| 14 | Introdução ao agrupamento | [Agrupamento](5-Clustering/README.md) | Limpe, prepare e visualize seus dados; introdução ao agrupamento | [Python](5-Clustering/1-Visualize/README.md) • [R](../../5-Clustering/1-Visualize/solution/R/lesson_14.html) | Jen • Eric Wanjau | -| 15 | Explorando gostos musicais nigerianos 🎧 | [Agrupamento](5-Clustering/README.md) | Explore o método de agrupamento K-Means | [Python](5-Clustering/2-K-Means/README.md) • [R](../../5-Clustering/2-K-Means/solution/R/lesson_15.html) | Jen • Eric Wanjau | -| 16 | Introdução ao processamento de linguagem natural ☕️ | [Processamento de linguagem natural](6-NLP/README.md) | Aprenda o básico de PLN construindo um bot simples | [Python](6-NLP/1-Introduction-to-NLP/README.md) | Stephen | -| 17 | Tarefas comuns de PLN ☕️ | [Processamento de linguagem natural](6-NLP/README.md) | Aprofunde seu conhecimento em PLN entendendo tarefas comuns necessárias ao lidar com estruturas de linguagem | [Python](6-NLP/2-Tasks/README.md) | Stephen | -| 18 | Tradução e análise de sentimento ♥️ | [Processamento de linguagem natural](6-NLP/README.md) | Tradução e análise de sentimento com Jane Austen | [Python](6-NLP/3-Translation-Sentiment/README.md) | Stephen | -| 19 | Hotéis românticos da Europa ♥️ | [Processamento de linguagem natural](6-NLP/README.md) | Análise de sentimento com avaliações de hotéis 1 | [Python](6-NLP/4-Hotel-Reviews-1/README.md) | Stephen | -| 20 | Hotéis românticos da Europa ♥️ | [Processamento de linguagem natural](6-NLP/README.md) | Análise de sentimento com avaliações de hotéis 2 | [Python](6-NLP/5-Hotel-Reviews-2/README.md) | Stephen | -| 21 | Introdução à previsão de séries temporais | [Séries temporais](7-TimeSeries/README.md) | Introdução à previsão de séries temporais | [Python](7-TimeSeries/1-Introduction/README.md) | Francesca | -| 22 | ⚡️ Consumo de energia mundial ⚡️ - previsão de séries temporais com ARIMA | [Séries temporais](7-TimeSeries/README.md) | Previsão de séries temporais com ARIMA | [Python](7-TimeSeries/2-ARIMA/README.md) | Francesca | -| 23 | ⚡️ Consumo de energia mundial ⚡️ - previsão de séries temporais com SVR | [Séries temporais](7-TimeSeries/README.md) | Previsão de séries temporais com Regressor de Vetores de Suporte | [Python](7-TimeSeries/3-SVR/README.md) | Anirban | -| 24 | Introdução ao aprendizado por reforço | [Aprendizado por reforço](8-Reinforcement/README.md) | Introdução ao aprendizado por reforço com Q-Learning | [Python](8-Reinforcement/1-QLearning/README.md) | Dmitry | -| 25 | Ajude Peter a evitar o lobo! 🐺 | [Aprendizado por reforço](8-Reinforcement/README.md) | Gym de aprendizado por reforço | [Python](8-Reinforcement/2-Gym/README.md) | Dmitry | -| Pós-escrito | Cenários e aplicações de ML no mundo real | [ML no Mundo](9-Real-World/README.md) | Aplicações do mundo real interessantes e reveladoras do ML clássico | [Lição](9-Real-World/1-Applications/README.md) | Equipe | -| Pós-escrito | Depuração de Modelos em ML usando o painel RAI | [ML no Mundo](9-Real-World/README.md) | Depuração de modelos em Machine Learning usando componentes do painel Responsible AI | [Lição](9-Real-World/2-Debugging-ML-Models/README.md) | Ruth Yakubu | - -> [encontre todos os recursos adicionais para este curso em nossa coleção do Microsoft Learn](https://learn.microsoft.com/en-us/collections/qrqzamz1nn2wx3?WT.mc_id=academic-77952-bethanycheum) +| 01 | Introdução ao aprendizado de máquina | [Introdução](1-Introduction/README.md) | Aprenda os conceitos básicos por trás do aprendizado de máquina | [Lição](1-Introduction/1-intro-to-ML/README.md) | Muhammad | +| 02 | A História do aprendizado de máquina | [Introdução](1-Introduction/README.md) | Aprenda a história que fundamenta este campo | [Lição](1-Introduction/2-history-of-ML/README.md) | Jen and Amy | +| 03 | Equidade e aprendizado de máquina | [Introdução](1-Introduction/README.md) | Quais são as questões filosóficas importantes em torno da equidade que os estudantes devem considerar ao construir e aplicar modelos de ML? | [Lição](1-Introduction/3-fairness/README.md) | Tomomi | +| 04 | Técnicas para aprendizado de máquina | [Introdução](1-Introduction/README.md) | Que técnicas os pesquisadores de ML usam para construir modelos de ML? | [Lição](1-Introduction/4-techniques-of-ML/README.md) | Chris and Jen | +| 05 | Introdução à regressão | [Regressão](2-Regression/README.md) | Comece com Python e Scikit-learn para modelos de regressão | [Python](2-Regression/1-Tools/README.md) • [R](../../2-Regression/1-Tools/solution/R/lesson_1.html) | Jen • Eric Wanjau | +| 06 | Preços de abóboras na América do Norte 🎃 | [Regressão](2-Regression/README.md) | Visualize e limpe os dados em preparação para ML | [Python](2-Regression/2-Data/README.md) • [R](../../2-Regression/2-Data/solution/R/lesson_2.html) | Jen • Eric Wanjau | +| 07 | Preços de abóboras na América do Norte 🎃 | [Regressão](2-Regression/README.md) | Construa modelos de regressão linear e polinomial | [Python](2-Regression/3-Linear/README.md) • [R](../../2-Regression/3-Linear/solution/R/lesson_3.html) | Jen and Dmitry • Eric Wanjau | +| 08 | Preços de abóboras na América do Norte 🎃 | [Regressão](2-Regression/README.md) | Construa um modelo de regressão logística | [Python](2-Regression/4-Logistic/README.md) • [R](../../2-Regression/4-Logistic/solution/R/lesson_4.html) | Jen • Eric Wanjau | +| 09 | Um Aplicativo Web 🔌 | [Aplicativo Web](3-Web-App/README.md) | Construa um aplicativo web para usar seu modelo treinado | [Python](3-Web-App/1-Web-App/README.md) | Jen | +| 10 | Introdução à classificação | [Classificação](4-Classification/README.md) | Limpe, prepare e visualize seus dados; introdução à classificação | [Python](4-Classification/1-Introduction/README.md) • [R](../../4-Classification/1-Introduction/solution/R/lesson_10.html) | Jen and Cassie • Eric Wanjau | +| 11 | Culinárias asiáticas e indianas deliciosas 🍜 | [Classificação](4-Classification/README.md) | Introdução a classificadores | [Python](4-Classification/2-Classifiers-1/README.md) • [R](../../4-Classification/2-Classifiers-1/solution/R/lesson_11.html) | Jen and Cassie • Eric Wanjau | +| 12 | Culinárias asiáticas e indianas deliciosas 🍜 | [Classificação](4-Classification/README.md) | Mais classificadores | [Python](4-Classification/3-Classifiers-2/README.md) • [R](../../4-Classification/3-Classifiers-2/solution/R/lesson_12.html) | Jen and Cassie • Eric Wanjau | +| 13 | Culinárias asiáticas e indianas deliciosas 🍜 | [Classificação](4-Classification/README.md) | Construa um aplicativo web de recomendação usando seu modelo | [Python](4-Classification/4-Applied/README.md) | Jen | +| 14 | Introdução ao agrupamento | [Agrupamento](5-Clustering/README.md) | Limpe, prepare e visualize seus dados; Introdução ao agrupamento | [Python](5-Clustering/1-Visualize/README.md) • [R](../../5-Clustering/1-Visualize/solution/R/lesson_14.html) | Jen • Eric Wanjau | +| 15 | Explorando gostos musicais nigerianos 🎧 | [Agrupamento](5-Clustering/README.md) | Explore o método de agrupamento K-Means | [Python](5-Clustering/2-K-Means/README.md) • [R](../../5-Clustering/2-K-Means/solution/R/lesson_15.html) | Jen • Eric Wanjau | +| 16 | Introdução ao processamento de linguagem natural ☕️ | [Processamento de linguagem natural](6-NLP/README.md) | Aprenda o básico sobre PLN construindo um bot simples | [Python](6-NLP/1-Introduction-to-NLP/README.md) | Stephen | +| 17 | Tarefas comuns de PLN ☕️ | [Processamento de linguagem natural](6-NLP/README.md) | Aprofunde seu conhecimento em PLN entendendo tarefas comuns necessárias ao lidar com estruturas de linguagem | [Python](6-NLP/2-Tasks/README.md) | Stephen | +| 18 | Tradução e análise de sentimento ♥️ | [Processamento de linguagem natural](6-NLP/README.md) | Tradução e análise de sentimento com Jane Austen | [Python](6-NLP/3-Translation-Sentiment/README.md) | Stephen | +| 19 | Hotéis românticos da Europa ♥️ | [Processamento de linguagem natural](6-NLP/README.md) | Análise de sentimento com avaliações de hotéis 1 | [Python](6-NLP/4-Hotel-Reviews-1/README.md) | Stephen | +| 20 | Hotéis românticos da Europa ♥️ | [Processamento de linguagem natural](6-NLP/README.md) | Análise de sentimento com avaliações de hotéis 2 | [Python](6-NLP/5-Hotel-Reviews-2/README.md) | Stephen | +| 21 | Introdução à previsão de séries temporais | [Séries temporais](7-TimeSeries/README.md) | Introdução à previsão de séries temporais | [Python](7-TimeSeries/1-Introduction/README.md) | Francesca | +| 22 | ⚡️ Consumo de energia mundial ⚡️ - previsão de séries temporais com ARIMA | [Séries temporais](7-TimeSeries/README.md) | Previsão de séries temporais com ARIMA | [Python](7-TimeSeries/2-ARIMA/README.md) | Francesca | +| 23 | ⚡️ Consumo de energia mundial ⚡️ - previsão de séries temporais com SVR | [Séries temporais](7-TimeSeries/README.md) | Previsão de séries temporais com Support Vector Regressor | [Python](7-TimeSeries/3-SVR/README.md) | Anirban | +| 24 | Introdução ao aprendizado por reforço | [Aprendizado por reforço](8-Reinforcement/README.md) | Introdução ao aprendizado por reforço com Q-Learning | [Python](8-Reinforcement/1-QLearning/README.md) | Dmitry | +| 25 | Ajude Peter a evitar o lobo! 🐺 | [Aprendizado por reforço](8-Reinforcement/README.md) | Aprendizado por reforço com Gym | [Python](8-Reinforcement/2-Gym/README.md) | Dmitry | +| Postscript | Cenários e aplicações de ML no mundo real | [ML in the Wild](9-Real-World/README.md) | Aplicações interessantes e reveladoras do mundo real de ML clássico | [Lição](9-Real-World/1-Applications/README.md) | Equipe | +| Postscript | Depuração de modelos em ML usando o painel RAI | [ML in the Wild](9-Real-World/README.md) | Depuração de modelos em Machine Learning usando componentes do painel Responsible AI | [Lição](9-Real-World/2-Debugging-ML-Models/README.md) | Ruth Yakubu | + +> [encontre todos os recursos adicionais para este curso em nossa coleção Microsoft Learn](https://learn.microsoft.com/en-us/collections/qrqzamz1nn2wx3?WT.mc_id=academic-77952-bethanycheum) ## Acesso offline -Você pode executar esta documentação offline usando [Docsify](https://docsify.js.org/#/). Faça um fork deste repo, [instale o Docsify](https://docsify.js.org/#/quickstart) em sua máquina local, e então, na pasta raiz deste repo, digite `docsify serve`. O site será servido na porta 3000 no seu localhost: `localhost:3000`. +Você pode executar esta documentação offline usando [Docsify](https://docsify.js.org/#/). Faça um fork deste repositório, [instale o Docsify](https://docsify.js.org/#/quickstart) em sua máquina local e, então, na pasta raiz deste repositório, digite `docsify serve`. O site será servido na porta 3000 no seu localhost: `localhost:3000`. ## PDFs @@ -202,22 +202,22 @@ Nossa equipe produz outros cursos! Confira: ### Série Copilot [![Copilot para Programação Emparelhada com IA](https://img.shields.io/badge/Copilot%20for%20AI%20Paired%20Programming-FACC15?style=for-the-badge&labelColor=E5E7EB&color=FACC15)](https://aka.ms/GitHubCopilotAI?WT.mc_id=academic-105485-koreyst) [![Copilot para C#/.NET](https://img.shields.io/badge/Copilot%20for%20C%23/.NET-FBBF24?style=for-the-badge&labelColor=E5E7EB&color=FBBF24)](https://github.com/microsoft/mastering-github-copilot-for-dotnet-csharp-developers?WT.mc_id=academic-105485-koreyst) -[![Aventura Copilot](https://img.shields.io/badge/Copilot%20Adventure-FDE68A?style=for-the-badge&labelColor=E5E7EB&color=FDE68A)](https://github.com/microsoft/CopilotAdventures?WT.mc_id=academic-105485-koreyst) +[![Aventura do Copilot](https://img.shields.io/badge/Copilot%20Adventure-FDE68A?style=for-the-badge&labelColor=E5E7EB&color=FDE68A)](https://github.com/microsoft/CopilotAdventures?WT.mc_id=academic-105485-koreyst) -## Obter Ajuda +## Obtendo Ajuda -Se você ficar preso ou tiver alguma dúvida sobre como criar aplicativos de IA. Junte-se a outros aprendizes e desenvolvedores experientes em discussões sobre o MCP. É uma comunidade acolhedora onde perguntas são bem-vindas e o conhecimento é compartilhado livremente. +Se você ficar preso ou tiver dúvidas sobre criar aplicativos de IA. Junte-se a outros aprendizes e desenvolvedores experientes em discussões sobre MCP. É uma comunidade de apoio onde perguntas são bem-vindas e o conhecimento é compartilhado livremente. -[![Discord da Microsoft Foundry](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) +[![Discord do Microsoft Foundry](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) Se você tiver feedback sobre o produto ou encontrar erros durante o desenvolvimento, visite: -[![Fórum de Desenvolvedores Microsoft Foundry](https://img.shields.io/badge/GitHub-Microsoft_Foundry_Developer_Forum-blue?style=for-the-badge&logo=github&color=000000&logoColor=fff)](https://aka.ms/foundry/forum) +[![Fórum de Desenvolvedores do Microsoft Foundry](https://img.shields.io/badge/GitHub-Microsoft_Foundry_Developer_Forum-blue?style=for-the-badge&logo=github&color=000000&logoColor=fff)](https://aka.ms/foundry/forum) --- Isenção de responsabilidade: -Este documento foi traduzido usando o serviço de tradução por IA [Co-op Translator](https://github.com/Azure/co-op-translator). Embora nos esforcemos pela precisão, esteja ciente de que traduções automáticas podem conter erros ou imprecisões. O documento original em seu idioma nativo deve ser considerado a fonte autoritativa. Para informações críticas, recomenda-se a tradução profissional realizada por um tradutor humano. Não nos responsabilizamos por quaisquer mal-entendidos ou interpretações incorretas decorrentes do uso desta tradução. +Este documento foi traduzido usando o serviço de tradução por IA Co-op Translator (https://github.com/Azure/co-op-translator). Embora nos esforcemos para garantir a precisão, esteja ciente de que traduções automatizadas podem conter erros ou imprecisões. O documento original em seu idioma nativo deve ser considerado a fonte oficial. Para informações críticas, recomenda-se tradução humana profissional. Não nos responsabilizamos por quaisquer mal-entendidos ou interpretações equivocadas decorrentes do uso desta tradução. \ No newline at end of file diff --git a/translations/cs/README.md b/translations/cs/README.md index 4cbff5588..d55f62559 100644 --- a/translations/cs/README.md +++ b/translations/cs/README.md @@ -1,49 +1,51 @@ -[![Licence GitHub](https://img.shields.io/github/license/microsoft/ML-For-Beginners.svg)](https://github.com/microsoft/ML-For-Beginners/blob/master/LICENSE) +[![Licence GitHubu](https://img.shields.io/github/license/microsoft/ML-For-Beginners.svg)](https://github.com/microsoft/ML-For-Beginners/blob/master/LICENSE) [![Přispěvatelé GitHubu](https://img.shields.io/github/contributors/microsoft/ML-For-Beginners.svg)](https://GitHub.com/microsoft/ML-For-Beginners/graphs/contributors/) -[![Problémy na GitHubu](https://img.shields.io/github/issues/microsoft/ML-For-Beginners.svg)](https://GitHub.com/microsoft/ML-For-Beginners/issues/) +[![Issues GitHubu](https://img.shields.io/github/issues/microsoft/ML-For-Beginners.svg)](https://GitHub.com/microsoft/ML-For-Beginners/issues/) [![Pull requesty GitHubu](https://img.shields.io/github/issues-pr/microsoft/ML-For-Beginners.svg)](https://GitHub.com/microsoft/ML-For-Beginners/pulls/) -[![PRy vítány](https://img.shields.io/badge/PRs-welcome-brightgreen.svg?style=flat-square)](http://makeapullrequest.com) +[![PRs vítány](https://img.shields.io/badge/PRs-welcome-brightgreen.svg?style=flat-square)](http://makeapullrequest.com) -[![Microsoft Foundry Discord](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) +[![Sledující GitHubu](https://img.shields.io/github/watchers/microsoft/ML-For-Beginners.svg?style=social&label=Watch)](https://GitHub.com/microsoft/ML-For-Beginners/watchers/) +[![Forky GitHubu](https://img.shields.io/github/forks/microsoft/ML-For-Beginners.svg?style=social&label=Fork)](https://GitHub.com/microsoft/ML-For-Beginners/network/) +[![Hvězdy GitHubu](https://img.shields.io/github/stars/microsoft/ML-For-Beginners.svg?style=social&label=Star)](https://GitHub.com/microsoft/ML-For-Beginners/stargazers/) -### 🌐 Podpora více jazyků +### 🌐 Vícejazyčná podpora -#### Podporováno přes GitHub Action (automatizováno a vždy aktuální) +#### Podporováno pomocí GitHub Action (automatizováno a vždy aktuální) -[Arabština](../ar/README.md) | [Bengálština](../bn/README.md) | [Bulharština](../bg/README.md) | [Barmský (Myanmar)](../my/README.md) | [Čínština (zjednodušená)](../zh/README.md) | [Čínština (tradiční, Hongkong)](../hk/README.md) | [Čínština (tradiční, Macau)](../mo/README.md) | [Čínština (tradiční, Tchaj-wan)](../tw/README.md) | [Chorvatština](../hr/README.md) | [Čeština](./README.md) | [Dánština](../da/README.md) | [Nizozemština](../nl/README.md) | [Estonština](../et/README.md) | [Finština](../fi/README.md) | [Francouzština](../fr/README.md) | [Němčina](../de/README.md) | [Řečtina](../el/README.md) | [Hebrejština](../he/README.md) | [Hindština](../hi/README.md) | [Maďarština](../hu/README.md) | [Indonéština](../id/README.md) | [Italština](../it/README.md) | [Japonština](../ja/README.md) | [Kannadština](../kn/README.md) | [Korejština](../ko/README.md) | [Litevština](../lt/README.md) | [Malajština](../ms/README.md) | [Malayalam](../ml/README.md) | [Maráthština](../mr/README.md) | [Nepálština](../ne/README.md) | [Nigérijský pidžin](../pcm/README.md) | [Norština](../no/README.md) | [Perština (Farsi)](../fa/README.md) | [Polština](../pl/README.md) | [Portugalština (Brazílie)](../br/README.md) | [Portugalština (Portugalsko)](../pt/README.md) | [Paňdžábština (Gurmukhí)](../pa/README.md) | [Rumunština](../ro/README.md) | [Ruština](../ru/README.md) | [Srbština (azbuka)](../sr/README.md) | [Slovenština](../sk/README.md) | [Slovinština](../sl/README.md) | [Španělština](../es/README.md) | [Svahilština](../sw/README.md) | [Švédština](../sv/README.md) | [Tagalog (Filipínština)](../tl/README.md) | [Tamilština](../ta/README.md) | [Telugština](../te/README.md) | [Thajština](../th/README.md) | [Turečtina](../tr/README.md) | [Ukrajinština](../uk/README.md) | [Urdština](../ur/README.md) | [Vietnamština](../vi/README.md) +[Arabština](../ar/README.md) | [Bengálština](../bn/README.md) | [Bulharština](../bg/README.md) | [Barmština (Myanmar)](../my/README.md) | [Čínština (zjednodušená)](../zh/README.md) | [Čínština (tradiční, Hong Kong)](../hk/README.md) | [Čínština (tradiční, Macau)](../mo/README.md) | [Čínština (tradiční, Taiwan)](../tw/README.md) | [Chorvatština](../hr/README.md) | [Čeština](./README.md) | [Dánština](../da/README.md) | [Nizozemština](../nl/README.md) | [Estonština](../et/README.md) | [Finština](../fi/README.md) | [Francouzština](../fr/README.md) | [Němčina](../de/README.md) | [Řečtina](../el/README.md) | [Hebrejština](../he/README.md) | [Hindština](../hi/README.md) | [Maďarština](../hu/README.md) | [Indonéština](../id/README.md) | [Italština](../it/README.md) | [Japonština](../ja/README.md) | [Kannadština](../kn/README.md) | [Korejština](../ko/README.md) | [Litevština](../lt/README.md) | [Malajština](../ms/README.md) | [Malajalámština](../ml/README.md) | [Maráthština](../mr/README.md) | [Nepálština](../ne/README.md) | [Nigérijský pidžin](../pcm/README.md) | [Norština](../no/README.md) | [Perština (Farsi)](../fa/README.md) | [Polština](../pl/README.md) | [Portugalština (Brazílie)](../br/README.md) | [Portugalština (Portugalsko)](../pt/README.md) | [Paňdžábština (Gurmukhi)](../pa/README.md) | [Rumunština](../ro/README.md) | [Ruština](../ru/README.md) | [Srbština (cyrilice)](../sr/README.md) | [Slovenština](../sk/README.md) | [Slovinština](../sl/README.md) | [Španělština](../es/README.md) | [Svahilština](../sw/README.md) | [Švédština](../sv/README.md) | [Tagalog (filipínština)](../tl/README.md) | [Tamilština](../ta/README.md) | [Telugština](../te/README.md) | [Thajština](../th/README.md) | [Turečtina](../tr/README.md) | [Ukrajinština](../uk/README.md) | [Urdština](../ur/README.md) | [Vietnamština](../vi/README.md) -#### Přidejte se k naší komunitě +#### Připojte se k naší komunitě [![Microsoft Foundry Discord](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) -Pořádáme na Discordu sérii "Learn with AI", dozvíte se více a připojte se k nám na [Série Learn with AI](https://aka.ms/learnwithai/discord) od 18. do 30. září 2025. Získáte tipy a triky pro používání GitHub Copilot pro datovou vědu. +Probíhá naše série „Learn with AI“ na Discordu — dozvíte se více a připojte se k nám na [Learn with AI Series](https://aka.ms/learnwithai/discord) od 18. do 30. září 2025. Získáte tipy a triky pro používání GitHub Copilot pro datovou vědu. -![Série Learn with AI](../../translated_images/3.9b58fd8d6c373c20c588c5070c4948a826ab074426c28ceb5889641294373dfc.cs.png) +![Série Learn with AI](../../translated_images/3.9b58fd8d6c373c20.cs.png) -# Strojové učení pro začátečníky - Učební plán +# Strojové učení pro začátečníky - osnovy kurzu -> 🌍 Cestujte po světě, zatímco prozkoumáváme strojové učení prostřednictvím světových kultur 🌍 +> 🌍 Cestujte po celém světě, když zkoumáme strojové učení prostřednictvím světových kultur 🌍 -Cloud Advocates v Microsoftu s potěšením nabízejí 12týdenní, 26-lekční učební plán zaměřený na **strojové učení**. V tomto kurzu se naučíte to, čemu se někdy říká **klasické strojové učení**, přičemž primárně používáme knihovnu Scikit-learn a vyhýbáme se hlubokému učení, které je pokryto v našem [kurikulu 'AI for Beginners'](https://aka.ms/ai4beginners). Tyto lekce spárujte také s naším ['Data Science for Beginners' kurikulem](https://aka.ms/ds4beginners). +Obhájci cloudu ve společnosti Microsoft s radostí nabízejí 12týdenní osnovu s 26 lekcemi věnovanou výhradně **strojovému učení**. V této osnově se seznámíte s tím, co se někdy nazývá **klasické strojové učení**, především s využitím knihovny Scikit-learn a bez hlubokého učení, které je pokryto v našem [kurzu 'AI for Beginners'](https://aka.ms/ai4beginners). Párujte tyto lekce také s naším [kurzem 'Data Science for Beginners'](https://aka.ms/ds4beginners). -Cestujte s námi po světě, když aplikujeme tyto klasické techniky na data z mnoha koutů světa. Každá lekce obsahuje před- a po-lekční kvízy, psané instrukce k dokončení lekce, řešení, úkol a další. Naše projektově založená pedagogika vám umožní učit se při tvorbě, což je osvědčený způsob, jak si nové dovednosti uchovat. +Cestujte s námi po světě, když aplikujeme tyto klasické techniky na data z mnoha oblastí světa. Každá lekce obsahuje vstupní a závěrečný kvíz, písemné pokyny k dokončení lekce, řešení, úkol a další. Naše projektově orientovaná pedagogika vám umožní učit se při tvorbě, což je osvědčený způsob, jak se nové dovednosti „uchytí“. -**✍️ Srdečné poděkování autorům** Jen Looper, Stephen Howell, Francesca Lazzeri, Tomomi Imura, Cassie Breviu, Dmitry Soshnikov, Chris Noring, Anirban Mukherjee, Ornella Altunyan, Ruth Yakubu a Amy Boyd +**✍️ Srdečné díky našim autorům** Jen Looper, Stephen Howell, Francesca Lazzeri, Tomomi Imura, Cassie Breviu, Dmitry Soshnikov, Chris Noring, Anirban Mukherjee, Ornella Altunyan, Ruth Yakubu a Amy Boyd -**🎨 Poděkování také ilustrátorům** Tomomi Imura, Dasani Madipalli a Jen Looper +**🎨 Díky také našim ilustrátorům** Tomomi Imura, Dasani Madipalli a Jen Looper -**🙏 Zvláštní poděkování 🙏 našim autorům, recenzentům a přispěvatelům obsahu z Microsoft Student Ambassador**, zejména Rishit Dagli, Muhammad Sakib Khan Inan, Rohan Raj, Alexandru Petrescu, Abhishek Jaiswal, Nawrin Tabassum, Ioan Samuila a Snigdha Agarwal +**🙏 Zvláštní poděkování 🙏 našim autorům, recenzentům a přispěvatelům obsahu z řad Microsoft Student Ambassador**, zejména Rishit Dagli, Muhammad Sakib Khan Inan, Rohan Raj, Alexandru Petrescu, Abhishek Jaiswal, Nawrin Tabassum, Ioan Samuila a Snigdha Agarwal **🤩 Extra poděkování Microsoft Student Ambassadors Eric Wanjau, Jasleen Sondhi a Vidushi Gupta za naše lekce v R!** @@ -51,34 +53,34 @@ Cestujte s námi po světě, když aplikujeme tyto klasické techniky na data z Postupujte podle těchto kroků: 1. **Vytvořte fork repozitáře**: Klikněte na tlačítko "Fork" v pravém horním rohu této stránky. -2. **Naklonujte repozitář**: `git clone https://github.com/microsoft/ML-For-Beginners.git` +2. **Klonujte repozitář**: `git clone https://github.com/microsoft/ML-For-Beginners.git` -> [najdete všechny doplňkové zdroje pro tento kurz v naší kolekci Microsoft Learn](https://learn.microsoft.com/en-us/collections/qrqzamz1nn2wx3?WT.mc_id=academic-77952-bethanycheum) +> [najděte všechny další zdroje pro tento kurz v naší kolekci Microsoft Learn](https://learn.microsoft.com/en-us/collections/qrqzamz1nn2wx3?WT.mc_id=academic-77952-bethanycheum) -> 🔧 **Potřebujete pomoc?** Pro řešení běžných problémů s instalací, nastavením a spuštěním lekcí zkontrolujte náš [Průvodce řešením problémů](TROUBLESHOOTING.md). +> 🔧 **Potřebujete pomoc?** Podívejte se na náš [průvodce řešením problémů](TROUBLESHOOTING.md) pro řešení běžných potíží s instalací, nastavením a spouštěním lekcí. -**[Studenti](https://aka.ms/student-page)**, abyste mohli tento učební plán využít, vytvořte fork celého repozitáře do svého GitHub účtu a dokončete cvičení sami nebo ve skupině: +**[Studenti](https://aka.ms/student-page)**, chcete-li využít tuto osnovu, vytvořte fork celého repozitáře na svůj GitHub účet a dokončujte cvičení sami nebo ve skupině: -- Začněte kvízem před přednáškou. -- Přečtěte si přednášku a dokončete aktivity, zastavujte se a přemýšlejte u každé kontroly znalostí. -- Snažte se vytvářet projekty tím, že pochopíte lekce místo prostého spuštění kódu řešení; tento kód je však dostupný ve složkách `/solution` v každé lekci zaměřené na projekt. -- Vyplňte kvíz po přednášce. +- Začněte úvodním kvízem před přednáškou. +- Přečtěte si přednášku a dokončete aktivity, zastavujte se a přemýšlejte při každé znalostní kontrole. +- Snažte se vytvářet projekty porozuměním lekcí místo pouhého spouštění řešení; přesto jsou tato řešení k dispozici ve složkách `/solution` v každé projektově orientované lekci. +- Udělejte závěrečný kvíz po přednášce. - Dokončete výzvu. -- Splňte úkol. -- Po dokončení skupiny lekcí navštivte [Diskusní fórum](https://github.com/microsoft/ML-For-Beginners/discussions) a "učte se nahlas" tím, že vyplníte příslušný PAT rubrik. 'PAT' je Nástroj pro hodnocení pokroku, což je rubrika, kterou vyplníte, abyste podpořili své učení. Můžete také reagovat na jiné PATy, abychom se učili společně. +- Dokončete zadání. +- Po dokončení skupiny lekcí navštivte [diskusní fórum](https://github.com/microsoft/ML-For-Beginners/discussions) a „učte se nahlas“ vyplněním příslušného hodnotícího rubriky PAT. 'PAT' je nástroj pro hodnocení pokroku (Progress Assessment Tool), což je rubrika, kterou vyplníte na podporu svého učení. Můžete také reagovat na jiné PATy, abychom se mohli učit společně. > Pro další studium doporučujeme sledovat tyto [moduly a učební cesty Microsoft Learn](https://docs.microsoft.com/en-us/users/jenlooper-2911/collections/k7o7tg1gp306q4?WT.mc_id=academic-77952-leestott). -**Učitelé**, zahrnuli jsme [některá doporučení](for-teachers.md), jak tento učební plán využít. +**Učitelé**, poskytli jsme [několik doporučení](for-teachers.md) o tom, jak tuto osnovu používat. --- ## Video průvodci -Některé lekce jsou dostupné jako krátká videa. Všechny je najdete přímo v lekcích nebo na [přehrávacím seznamu ML for Beginners na kanálu Microsoft Developer na YouTube](https://aka.ms/ml-beginners-videos) kliknutím na obrázek níže. +Některé lekce jsou dostupné jako krátká videa. Vše najdete vložené přímo v lekcích nebo v [playlistu ML for Beginners na kanálu Microsoft Developer YouTube](https://aka.ms/ml-beginners-videos) kliknutím na obrázek níže. -[![Banner ML pro začátečníky](../../translated_images/ml-for-beginners-video-banner.63f694a100034bc6251134294459696e070a3a9a04632e9fe6a24aa0de4a7384.cs.png)](https://aka.ms/ml-beginners-videos) +[![Banner ML for beginners](../../translated_images/ml-for-beginners-video-banner.63f694a100034bc6.cs.png)](https://aka.ms/ml-beginners-videos) --- @@ -94,74 +96,74 @@ Některé lekce jsou dostupné jako krátká videa. Všechny je najdete přímo ## Pedagogika -Při budování tohoto kurikula jsme se rozhodli pro dva pedagogické principy: zajistit, aby byl praktický a založený na projektech, a aby obsahoval časté kvízy. Kromě toho má tento kurz společné **téma**, které mu dává soudržnost. +Při vytváření této osnovy jsme zvolili dva pedagogické principy: zajistit, aby byla praktická a **projektově orientovaná**, a aby obsahovala **časté kvízy**. Kromě toho má tato osnova společné **téma**, které jí dává soudržnost. -Zajištěním souladu obsahu s projekty se proces pro studenty stává více poutavým a retence konceptů se zvýší. Nízkorizikový kvíz před hodinou navíc nastavuje záměr studenta pro učení se tématu, zatímco druhý kvíz po hodině zajišťuje další udržení znalostí. Tento učební plán byl navržen tak, aby byl flexibilní a zábavný a lze jej absolvovat celý nebo částečně. Projekty začínají malé a postupně se během 12týdenního cyklu zvyšují na složitější. Tento kurz také obsahuje doslov o reálných aplikacích ML, který lze využít jako dodatečnou odměnu nebo jako základ pro diskusi. +Zajistěním, že obsah je v souladu s projekty, je proces pro studenty poutavější a uchování konceptů bude posíleno. Navíc nízkorizikový kvíz před hodinou nastaví záměr studenta k učení tématu, zatímco druhý kvíz po hodině zajistí další uchování znalostí. Tato osnova byla navržena tak, aby byla flexibilní a zábavná a lze ji absolvovat celou nebo částečně. Projekty začínají malé a postupně se během 12týdenního cyklu stávají složitějšími. Tato osnova také obsahuje dodatek o reálných aplikacích ML, který lze použít jako bonusové body nebo jako podklad pro diskusi. -> Najděte náš [Kodex chování](CODE_OF_CONDUCT.md), [Příspěvky](CONTRIBUTING.md), [Překlady](TRANSLATIONS.md) a [Průvodce řešením problémů](TROUBLESHOOTING.md). Vítáme vaše konstruktivní připomínky! +> Najděte náš [Kodex chování](CODE_OF_CONDUCT.md), [Příspěvky](CONTRIBUTING.md), [Překlady](TRANSLATIONS.md) a [Průvodce řešením problémů](TROUBLESHOOTING.md). Vítáme vaši konstruktivní zpětnou vazbu! ## Každá lekce obsahuje -- volitelný sketchnote +- volitelnou sketchnotu - volitelné doplňkové video - video průvodce (pouze některé lekce) -- [rozcvičku před lekcí (kvíz)](https://ff-quizzes.netlify.app/en/ml/) -- psanou lekci -- pro lekce založené na projektech krok-za-krokem návody, jak projekt vytvořit -- kontroly znalostí +- [úvodní kvíz před přednáškou](https://ff-quizzes.netlify.app/en/ml/) +- písemnou lekci +- u projektově orientovaných lekcí krok za krokem průvodce, jak projekt postavit +- kontrolní znalostní otázky - výzvu - doplňující četbu - zadání -- [kvíz po přednášce](https://ff-quizzes.netlify.app/en/ml/) +- [závěrečný kvíz po přednášce](https://ff-quizzes.netlify.app/en/ml/) -> **Poznámka o jazycích**: Tyto lekce jsou primárně psány v Pythonu, ale mnoho z nich je také dostupných v R. Pro dokončení lekce v R přejděte do složky `/solution` a vyhledejte lekce v R. Obsahují příponu .rmd, která představuje **R Markdown** soubor, který lze jednoduše definovat jako vložení `code chunks` (v R nebo jiných jazycích) a `YAML header` (který určuje, jak formátovat výstupy jako PDF) v `Markdown document`. Jako takový slouží jako vzorové autorovací prostředí pro datovou vědu, protože vám umožní kombinovat váš kód, jeho výstup a vaše poznámky tím, že je můžete zapisovat v Markdownu. Navíc dokumenty R Markdown lze rendrovat do výstupních formátů, jako jsou PDF, HTML nebo Word. +> **Poznámka o jazycích**: Tyto lekce jsou primárně psány v Pythonu, ale mnohé jsou také dostupné v R. Chcete-li dokončit lekci v R, přejděte do složky `/solution` a vyhledejte lekce v R. Obsahují příponu .rmd, která představuje soubor **R Markdown**, což lze jednoduše definovat jako vložení `code chunks` (v R nebo jiných jazycích) a `YAML header` (který určuje, jak formátovat výstupy, například PDF) v `Markdown document`. Slouží tedy jako vzorový autorský rámec pro datovou vědu, protože vám umožňuje kombinovat váš kód, jeho výstup a vaše poznámky tak, že je zapíšete v Markdownu. Kromě toho lze dokumenty R Markdown vyrenderovat do výstupních formátů, jako jsou PDF, HTML nebo Word. -> **Poznámka o kvízech**: Všechny kvízy jsou obsaženy ve [složce Quiz App](../../quiz-app), celkem 52 kvízů po třech otázkách. Jsou propojeny z lekcí, ale aplikaci kvízu lze spustit lokálně; postupujte podle instrukcí ve složce `quiz-app` pro lokální hostování nebo nasazení na Azure. +> **Poznámka o kvízech**: Všechny kvízy jsou obsaženy ve [složce Quiz App](../../quiz-app), celkem 52 kvízů po třech otázkách. Jsou propojeny v lekcích, ale aplikaci s kvízy lze spustit lokálně; postupujte podle pokynů ve složce `quiz-app`, abyste aplikaci hostovali lokálně nebo nasadili do Azure. -| Číslo lekce | Téma | Skupina lekcí | Výukové cíle | Propojená lekce | Autor | +| Číslo lekce | Téma | Seskupení lekcí | Cíle učení | Propojená lekce | Autor | | :-----------: | :------------------------------------------------------------: | :-------------------------------------------------: | ------------------------------------------------------------------------------------------------------------------------------- | :--------------------------------------------------------------------------------------------------------------------------------------: | :--------------------------------------------------: | -| 01 | Úvod do strojového učení | [Úvod](1-Introduction/README.md) | Poznejte základní koncepty strojového učení | [Lekce](1-Introduction/1-intro-to-ML/README.md) | Muhammad | -| 02 | The History of machine learning | [Úvod](1-Introduction/README.md) | Learn the history underlying this field | [Lekce](1-Introduction/2-history-of-ML/README.md) | Jen a Amy | -| 03 | Fairness and machine learning | [Úvod](1-Introduction/README.md) | What are the important philosophical issues around fairness that students should consider when building and applying ML models? | [Lekce](1-Introduction/3-fairness/README.md) | Tomomi | -| 04 | Techniques for machine learning | [Úvod](1-Introduction/README.md) | What techniques do ML researchers use to build ML models? | [Lekce](1-Introduction/4-techniques-of-ML/README.md) | Chris a Jen | -| 05 | Úvod do regrese | [Regression](2-Regression/README.md) | Začněte s Pythonem a Scikit-learnem pro regresní modely | [Python](2-Regression/1-Tools/README.md) • [R](../../2-Regression/1-Tools/solution/R/lesson_1.html) | Jen • Eric Wanjau | -| 06 | North American pumpkin prices 🎃 | [Regression](2-Regression/README.md) | Visualizujte a vyčistěte data v přípravě na ML | [Python](2-Regression/2-Data/README.md) • [R](../../2-Regression/2-Data/solution/R/lesson_2.html) | Jen • Eric Wanjau | -| 07 | North American pumpkin prices 🎃 | [Regression](2-Regression/README.md) | Postavte lineární a polynomiální regresní modely | [Python](2-Regression/3-Linear/README.md) • [R](../../2-Regression/3-Linear/solution/R/lesson_3.html) | Jen a Dmitry • Eric Wanjau | -| 08 | North American pumpkin prices 🎃 | [Regression](2-Regression/README.md) | Postavte logistický regresní model | [Python](2-Regression/4-Logistic/README.md) • [R](../../2-Regression/4-Logistic/solution/R/lesson_4.html) | Jen • Eric Wanjau | +| 01 | Úvod do strojového učení | [Úvod](1-Introduction/README.md) | Naučte se základní koncepty strojového učení | [Lekce](1-Introduction/1-intro-to-ML/README.md) | Muhammad | +| 02 | Historie strojového učení | [Úvod](1-Introduction/README.md) | Poznejte historii, která stojí za tímto oborem | [Lekce](1-Introduction/2-history-of-ML/README.md) | Jen a Amy | +| 03 | Spravedlnost a strojové učení | [Úvod](1-Introduction/README.md) | Jaké jsou důležité filozofické otázky týkající se spravedlnosti, které by studenti měli zvážit při vytváření a aplikaci ML modelů? | [Lekce](1-Introduction/3-fairness/README.md) | Tomomi | +| 04 | Techniky pro strojové učení | [Úvod](1-Introduction/README.md) | Jaké techniky používají výzkumníci v ML k tvorbě modelů? | [Lekce](1-Introduction/4-techniques-of-ML/README.md) | Chris a Jen | +| 05 | Úvod do regrese | [Regrese](2-Regression/README.md) | Začněte s Pythonem a Scikit-learn pro regresní modely | [Python](2-Regression/1-Tools/README.md) • [R](../../2-Regression/1-Tools/solution/R/lesson_1.html) | Jen • Eric Wanjau | +| 06 | Ceny dýní v Severní Americe 🎃 | [Regrese](2-Regression/README.md) | Vizualizujte a čistěte data v přípravě na ML | [Python](2-Regression/2-Data/README.md) • [R](../../2-Regression/2-Data/solution/R/lesson_2.html) | Jen • Eric Wanjau | +| 07 | Ceny dýní v Severní Americe 🎃 | [Regrese](2-Regression/README.md) | Vytvořte lineární a polynomické regresní modely | [Python](2-Regression/3-Linear/README.md) • [R](../../2-Regression/3-Linear/solution/R/lesson_3.html) | Jen a Dmitry • Eric Wanjau | +| 08 | Ceny dýní v Severní Americe 🎃 | [Regrese](2-Regression/README.md) | Vytvořte logistický regresní model | [Python](2-Regression/4-Logistic/README.md) • [R](../../2-Regression/4-Logistic/solution/R/lesson_4.html) | Jen • Eric Wanjau | | 09 | Webová aplikace 🔌 | [Webová aplikace](3-Web-App/README.md) | Vytvořte webovou aplikaci pro použití vašeho natrénovaného modelu | [Python](3-Web-App/1-Web-App/README.md) | Jen | -| 10 | Úvod do klasifikace | [Classification](4-Classification/README.md) | Vyčistěte, připravte a vizualizujte svá data; úvod do klasifikace | [Python](4-Classification/1-Introduction/README.md) • [R](../../4-Classification/1-Introduction/solution/R/lesson_10.html) | Jen a Cassie • Eric Wanjau | -| 11 | Lahodné asijské a indické kuchyně 🍜 | [Classification](4-Classification/README.md) | Úvod do klasifikátorů | [Python](4-Classification/2-Classifiers-1/README.md) • [R](../../4-Classification/2-Classifiers-1/solution/R/lesson_11.html) | Jen a Cassie • Eric Wanjau | -| 12 | Lahodné asijské a indické kuchyně 🍜 | [Classification](4-Classification/README.md) | Více klasifikátorů | [Python](4-Classification/3-Classifiers-2/README.md) • [R](../../4-Classification/3-Classifiers-2/solution/R/lesson_12.html) | Jen a Cassie • Eric Wanjau | -| 13 | Lahodné asijské a indické kuchyně 🍜 | [Classification](4-Classification/README.md) | Vytvořte doporučovací webovou aplikaci pomocí vašeho modelu | [Python](4-Classification/4-Applied/README.md) | Jen | -| 14 | Úvod do shlukování | [Clustering](5-Clustering/README.md) | Vyčistěte, připravte a vizualizujte svá data; Úvod do shlukování | [Python](5-Clustering/1-Visualize/README.md) • [R](../../5-Clustering/1-Visualize/solution/R/lesson_14.html) | Jen • Eric Wanjau | -| 15 | Objevování nigerijských hudebních vkusů 🎧 | [Clustering](5-Clustering/README.md) | Prozkoumejte metodu K-Means shlukování | [Python](5-Clustering/2-K-Means/README.md) • [R](../../5-Clustering/2-K-Means/solution/R/lesson_15.html) | Jen • Eric Wanjau | +| 10 | Úvod do klasifikace | [Klasifikace](4-Classification/README.md) | Učistěte, připravte a vizualizujte data; úvod do klasifikace | [Python](4-Classification/1-Introduction/README.md) • [R](../../4-Classification/1-Introduction/solution/R/lesson_10.html) | Jen a Cassie • Eric Wanjau | +| 11 | Lahodné asijské a indické kuchyně 🍜 | [Klasifikace](4-Classification/README.md) | Úvod do klasifikátorů | [Python](4-Classification/2-Classifiers-1/README.md) • [R](../../4-Classification/2-Classifiers-1/solution/R/lesson_11.html) | Jen a Cassie • Eric Wanjau | +| 12 | Lahodné asijské a indické kuchyně 🍜 | [Klasifikace](4-Classification/README.md) | Další klasifikátory | [Python](4-Classification/3-Classifiers-2/README.md) • [R](../../4-Classification/3-Classifiers-2/solution/R/lesson_12.html) | Jen a Cassie • Eric Wanjau | +| 13 | Lahodné asijské a indické kuchyně 🍜 | [Klasifikace](4-Classification/README.md) | Vytvořte doporučující webovou aplikaci pomocí svého modelu | [Python](4-Classification/4-Applied/README.md) | Jen | +| 14 | Úvod do shlukování | [Shlukování](5-Clustering/README.md) | Učistěte, připravte a vizualizujte data; úvod do shlukování | [Python](5-Clustering/1-Visualize/README.md) • [R](../../5-Clustering/1-Visualize/solution/R/lesson_14.html) | Jen • Eric Wanjau | +| 15 | Průzkum nigerijských hudebních chutí 🎧 | [Shlukování](5-Clustering/README.md) | Prozkoumejte metodu shlukování K-Means | [Python](5-Clustering/2-K-Means/README.md) • [R](../../5-Clustering/2-K-Means/solution/R/lesson_15.html) | Jen • Eric Wanjau | | 16 | Úvod do zpracování přirozeného jazyka ☕️ | [Zpracování přirozeného jazyka](6-NLP/README.md) | Naučte se základy NLP vytvořením jednoduchého bota | [Python](6-NLP/1-Introduction-to-NLP/README.md) | Stephen | -| 17 | Běžné úlohy NLP ☕️ | [Zpracování přirozeného jazyka](6-NLP/README.md) | Prohlubte své znalosti NLP pochopením běžných úloh nutných při práci se strukturami jazyka | [Python](6-NLP/2-Tasks/README.md) | Stephen | -| 18 | Překlad a analýza sentimentu ♥️ | [Zpracování přirozeného jazyka](6-NLP/README.md) | Překlad a analýza sentimentu s Jane Austen | [Python](6-NLP/3-Translation-Sentiment/README.md) | Stephen | +| 17 | Běžné úlohy NLP ☕️ | [Zpracování přirozeného jazyka](6-NLP/README.md) | Prohlubte své znalosti NLP porozuměním běžným úlohám potřebným při práci s jazykovými strukturami | [Python](6-NLP/2-Tasks/README.md) | Stephen | +| 18 | Překlad a analýza sentimentu ♥️ | [Zpracování přirozeného jazyka](6-NLP/README.md) | Překlad a analýza sentimentu na textech Jane Austen | [Python](6-NLP/3-Translation-Sentiment/README.md) | Stephen | | 19 | Romantické hotely Evropy ♥️ | [Zpracování přirozeného jazyka](6-NLP/README.md) | Analýza sentimentu s recenzemi hotelů 1 | [Python](6-NLP/4-Hotel-Reviews-1/README.md) | Stephen | | 20 | Romantické hotely Evropy ♥️ | [Zpracování přirozeného jazyka](6-NLP/README.md) | Analýza sentimentu s recenzemi hotelů 2 | [Python](6-NLP/5-Hotel-Reviews-2/README.md) | Stephen | -| 21 | Úvod do předpovídání časových řad | [Časové řady](7-TimeSeries/README.md) | Úvod do předpovídání časových řad | [Python](7-TimeSeries/1-Introduction/README.md) | Francesca | -| 22 | ⚡️ World Power Usage ⚡️ - předpovídání časových řad pomocí ARIMA | [Časové řady](7-TimeSeries/README.md) | Předpovídání časových řad pomocí ARIMA | [Python](7-TimeSeries/2-ARIMA/README.md) | Francesca | -| 23 | ⚡️ World Power Usage ⚡️ - předpovídání časových řad pomocí SVR | [Časové řady](7-TimeSeries/README.md) | Předpovídání časových řad pomocí Support Vector Regressor | [Python](7-TimeSeries/3-SVR/README.md) | Anirban | -| 24 | Úvod do učení s posílením | [Reinforcement learning](8-Reinforcement/README.md) | Úvod do posilovaného učení pomocí Q-Learning | [Python](8-Reinforcement/1-QLearning/README.md) | Dmitry | -| 25 | Pomozte Petrovi vyhnout se vlkovi! 🐺 | [Reinforcement learning](8-Reinforcement/README.md) | Reinforcement learning Gym | [Python](8-Reinforcement/2-Gym/README.md) | Dmitry | -| Dodatek | Scénáře a aplikace ML v reálném světě | [ML v reálném světě](9-Real-World/README.md) | Zajímavé a poučné aplikace klasického ML v reálném světě | [Lekce](9-Real-World/1-Applications/README.md) | Tým | -| Dodatek | Ladění modelů v ML pomocí komponent dashboardu RAI | [ML v reálném světě](9-Real-World/README.md) | Ladění modelů v ML pomocí komponent dashboardu Responsible AI | [Lekce](9-Real-World/2-Debugging-ML-Models/README.md) | Ruth Yakubu | +| 21 | Úvod do předpovědí časových řad | [Časové řady](7-TimeSeries/README.md) | Úvod do předpovědí časových řad | [Python](7-TimeSeries/1-Introduction/README.md) | Francesca | +| 22 | ⚡️ Světová spotřeba energie ⚡️ - předpovědi časových řad pomocí ARIMA | [Časové řady](7-TimeSeries/README.md) | Předpovědi časových řad pomocí ARIMA | [Python](7-TimeSeries/2-ARIMA/README.md) | Francesca | +| 23 | ⚡️ Světová spotřeba energie ⚡️ - předpovědi časových řad pomocí SVR | [Časové řady](7-TimeSeries/README.md) | Předpovědi časových řad pomocí Support Vector Regressor | [Python](7-TimeSeries/3-SVR/README.md) | Anirban | +| 24 | Úvod do učení posilováním | [Učení posilováním](8-Reinforcement/README.md) | Úvod do učení posilováním s Q-learningem | [Python](8-Reinforcement/1-QLearning/README.md) | Dmitry | +| 25 | Pomozte Peterovi vyhnout se vlkovi! 🐺 | [Učení posilováním](8-Reinforcement/README.md) | Gym pro učení posilováním | [Python](8-Reinforcement/2-Gym/README.md) | Dmitry | +| Poznámka | Scénáře a aplikace ML v reálném světě | [ML v praxi](9-Real-World/README.md) | Zajímavé a poučné aplikace klasického ML v reálném světě | [Lekce](9-Real-World/1-Applications/README.md) | Tým | +| Poznámka | Ladění modelů v ML pomocí RAI dashboardu | [ML v praxi](9-Real-World/README.md) | Ladění modelů v strojovém učení pomocí komponentů Responsible AI dashboardu | [Lekce](9-Real-World/2-Debugging-ML-Models/README.md) | Ruth Yakubu | -> [najděte všechny další zdroje pro tento kurz v naší kolekci Microsoft Learn](https://learn.microsoft.com/en-us/collections/qrqzamz1nn2wx3?WT.mc_id=academic-77952-bethanycheum) +> [Najdete všechny další zdroje pro tento kurz v naší kolekci Microsoft Learn](https://learn.microsoft.com/en-us/collections/qrqzamz1nn2wx3?WT.mc_id=academic-77952-bethanycheum) ## Offline přístup -Můžete tuto dokumentaci spustit offline pomocí [Docsify](https://docsify.js.org/#/). Vytvořte fork tohoto repozitáře, [nainstalujte Docsify](https://docsify.js.org/#/quickstart) na svém místním počítači, a pak v kořenové složce tohoto repozitáře zadejte `docsify serve`. Web bude naservírován na portu 3000 na vašem localhostu: `localhost:3000`. +Tuto dokumentaci můžete spustit offline pomocí [Docsify](https://docsify.js.org/#/). Vytvořte fork tohoto repo, [nainstalujte Docsify](https://docsify.js.org/#/quickstart) na svém počítači, a poté v kořenové složce tohoto repozitáře zadejte `docsify serve`. Web bude dostupný na portu 3000 na vašem localhostu: `localhost:3000`. -## PDF +## PDFy -Najděte PDF osnovy s odkazy [zde](https://microsoft.github.io/ML-For-Beginners/pdf/readme.pdf). +Najdete pdf osnovy s odkazy [zde](https://microsoft.github.io/ML-For-Beginners/pdf/readme.pdf). ## 🎒 Další kurzy -Náš tým vytváří i další kurzy! Podívejte se na: +Náš tým vytváří i jiné kurzy! Podívejte se: ### LangChain @@ -170,7 +172,7 @@ Náš tým vytváří i další kurzy! Podívejte se na: --- -### Azure / Edge / MCP / Agents +### Azure / Edge / MCP / Agenti [![AZD pro začátečníky](https://img.shields.io/badge/AZD%20for%20Beginners-0078D4?style=for-the-badge&labelColor=E5E7EB&color=0078D4)](https://github.com/microsoft/AZD-for-beginners?WT.mc_id=academic-105485-koreyst) [![Edge AI pro začátečníky](https://img.shields.io/badge/Edge%20AI%20for%20Beginners-00B8E4?style=for-the-badge&labelColor=E5E7EB&color=00B8E4)](https://github.com/microsoft/edgeai-for-beginners?WT.mc_id=academic-105485-koreyst) [![MCP pro začátečníky](https://img.shields.io/badge/MCP%20for%20Beginners-009688?style=for-the-badge&labelColor=E5E7EB&color=009688)](https://github.com/microsoft/mcp-for-beginners?WT.mc_id=academic-105485-koreyst) @@ -178,7 +180,7 @@ Náš tým vytváří i další kurzy! Podívejte se na: --- -### Série generativního AI +### Série Generativní AI [![Generativní AI pro začátečníky](https://img.shields.io/badge/Generative%20AI%20for%20Beginners-8B5CF6?style=for-the-badge&labelColor=E5E7EB&color=8B5CF6)](https://github.com/microsoft/generative-ai-for-beginners?WT.mc_id=academic-105485-koreyst) [![Generativní AI (.NET)](https://img.shields.io/badge/Generative%20AI%20(.NET)-9333EA?style=for-the-badge&labelColor=E5E7EB&color=9333EA)](https://github.com/microsoft/Generative-AI-for-beginners-dotnet?WT.mc_id=academic-105485-koreyst) [![Generativní AI (Java)](https://img.shields.io/badge/Generative%20AI%20(Java)-C084FC?style=for-the-badge&labelColor=E5E7EB&color=C084FC)](https://github.com/microsoft/generative-ai-for-beginners-java?WT.mc_id=academic-105485-koreyst) @@ -189,10 +191,10 @@ Náš tým vytváří i další kurzy! Podívejte se na: ### Základní kurzy [![Strojové učení pro začátečníky](https://img.shields.io/badge/ML%20for%20Beginners-22C55E?style=for-the-badge&labelColor=E5E7EB&color=22C55E)](https://aka.ms/ml-beginners?WT.mc_id=academic-105485-koreyst) [![Datová věda pro začátečníky](https://img.shields.io/badge/Data%20Science%20for%20Beginners-84CC16?style=for-the-badge&labelColor=E5E7EB&color=84CC16)](https://aka.ms/datascience-beginners?WT.mc_id=academic-105485-koreyst) -[![AI pro začátečníky](https://img.shields.io/badge/AI%20for%20Beginners-A3E635?style=for-the-badge&labelColor=E5E7EB&color=A3E635)](https://aka.ms/ai-beginners?WT.mc_id=academic-105485-koreyst) +[![Umělá inteligence pro začátečníky](https://img.shields.io/badge/AI%20for%20Beginners-A3E635?style=for-the-badge&labelColor=E5E7EB&color=A3E635)](https://aka.ms/ai-beginners?WT.mc_id=academic-105485-koreyst) [![Kyberbezpečnost pro začátečníky](https://img.shields.io/badge/Cybersecurity%20for%20Beginners-F97316?style=for-the-badge&labelColor=E5E7EB&color=F97316)](https://github.com/microsoft/Security-101?WT.mc_id=academic-96948-sayoung) [![Webový vývoj pro začátečníky](https://img.shields.io/badge/Web%20Dev%20for%20Beginners-EC4899?style=for-the-badge&labelColor=E5E7EB&color=EC4899)](https://aka.ms/webdev-beginners?WT.mc_id=academic-105485-koreyst) -[![IoT pro začátečníky](https://img.shields.io/badge/IoT%20for%20Beginners-14B8A6?style=for-the-badge&labelColor=E5E7EB&color=14B8A6)](https://aka.ms/iot-beginners?WT.mc_id=academic-105485-koreyst) +[![Internet věcí pro začátečníky](https://img.shields.io/badge/IoT%20for%20Beginners-14B8A6?style=for-the-badge&labelColor=E5E7EB&color=14B8A6)](https://aka.ms/iot-beginners?WT.mc_id=academic-105485-koreyst) [![Vývoj XR pro začátečníky](https://img.shields.io/badge/XR%20Development%20for%20Beginners-38BDF8?style=for-the-badge&labelColor=E5E7EB&color=38BDF8)](https://github.com/microsoft/xr-development-for-beginners?WT.mc_id=academic-105485-koreyst) --- @@ -200,22 +202,22 @@ Náš tým vytváří i další kurzy! Podívejte se na: ### Série Copilot [![Copilot pro párové programování s AI](https://img.shields.io/badge/Copilot%20for%20AI%20Paired%20Programming-FACC15?style=for-the-badge&labelColor=E5E7EB&color=FACC15)](https://aka.ms/GitHubCopilotAI?WT.mc_id=academic-105485-koreyst) [![Copilot pro C#/.NET](https://img.shields.io/badge/Copilot%20for%20C%23/.NET-FBBF24?style=for-the-badge&labelColor=E5E7EB&color=FBBF24)](https://github.com/microsoft/mastering-github-copilot-for-dotnet-csharp-developers?WT.mc_id=academic-105485-koreyst) -[![Dobrodružství Copilota](https://img.shields.io/badge/Copilot%20Adventure-FDE68A?style=for-the-badge&labelColor=E5E7EB&color=FDE68A)](https://github.com/microsoft/CopilotAdventures?WT.mc_id=academic-105485-koreyst) +[![Dobrodružství Copilot](https://img.shields.io/badge/Copilot%20Adventure-FDE68A?style=for-the-badge&labelColor=E5E7EB&color=FDE68A)](https://github.com/microsoft/CopilotAdventures?WT.mc_id=academic-105485-koreyst) -## Získání pomoci +## Kde získat pomoc -Pokud se zaseknete nebo budete mít nějaké dotazy ohledně vytváření aplikací s AI, připojte se k ostatním studentům a zkušeným vývojářům v diskusích o MCP. Je to podpůrná komunita, kde jsou otázky vítány a znalosti se sdílejí volně. +Pokud se zaseknete nebo máte jakékoli otázky ohledně vytváření AI aplikací, připojte se k ostatním studentům a zkušeným vývojářům k diskusím o MCP. Je to podpůrná komunita, kde jsou otázky vítány a znalosti se otevřeně sdílejí. -[![Microsoft Foundry na Discordu](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) +[![Microsoft Foundry Discord](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) -Pokud máte zpětnou vazbu k produktu nebo narazíte na chyby při vývoji, navštivte: +Pokud máte připomínky k produktu nebo se při vývoji vyskytnou chyby, navštivte: -[![Vývojářské fórum Microsoft Foundry](https://img.shields.io/badge/GitHub-Microsoft_Foundry_Developer_Forum-blue?style=for-the-badge&logo=github&color=000000&logoColor=fff)](https://aka.ms/foundry/forum) +[![Fórum vývojářů Microsoft Foundry](https://img.shields.io/badge/GitHub-Microsoft_Foundry_Developer_Forum-blue?style=for-the-badge&logo=github&color=000000&logoColor=fff)](https://aka.ms/foundry/forum) --- -**Prohlášení o vyloučení odpovědnosti**: -Tento dokument byl přeložen pomocí služby pro automatický překlad založené na umělé inteligenci [Co-op Translator](https://github.com/Azure/co-op-translator). Přestože usilujeme o přesnost, mějte prosím na paměti, že automatické překlady mohou obsahovat chyby nebo nepřesnosti. Originální dokument v jeho původním jazyce by měl být považován za rozhodující zdroj. Pro zásadní informace doporučujeme využít profesionální lidský překlad. Nejsme odpovědní za jakékoli nedorozumění nebo chybné výklady vyplývající z použití tohoto překladu. +Prohlášení o vyloučení odpovědnosti: +Tento dokument byl přeložen pomocí služby pro automatický překlad založené na umělé inteligenci [Co-op Translator](https://github.com/Azure/co-op-translator). I když usilujeme o přesnost, mějte prosím na paměti, že automatické překlady mohou obsahovat chyby nebo nepřesnosti. Původní dokument v jeho zdrojovém jazyce by měl být považován za autoritativní zdroj. Pro důležité informace se doporučuje profesionální lidský překlad. Nejsme odpovědní za jakákoli nedorozumění nebo nesprávné výklady vyplývající z použití tohoto překladu. \ No newline at end of file diff --git a/translations/da/README.md b/translations/da/README.md index 099ff7067..0d89ca094 100644 --- a/translations/da/README.md +++ b/translations/da/README.md @@ -1,19 +1,19 @@ [![GitHub-licens](https://img.shields.io/github/license/microsoft/ML-For-Beginners.svg)](https://github.com/microsoft/ML-For-Beginners/blob/master/LICENSE) [![GitHub-bidragydere](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-forespørgsler](https://img.shields.io/github/issues-pr/microsoft/ML-For-Beginners.svg)](https://GitHub.com/microsoft/ML-For-Beginners/pulls/) -[![PR'er velkomne](https://img.shields.io/badge/PRs-welcome-brightgreen.svg?style=flat-square)](http://makeapullrequest.com) +[![GitHub-problemer](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 Velkommen](https://img.shields.io/badge/PRs-welcome-brightgreen.svg?style=flat-square)](http://makeapullrequest.com) -[![GitHub-observatører](https://img.shields.io/github/watchers/microsoft/ML-For-Beginners.svg?style=social&label=Watch)](https://GitHub.com/microsoft/ML-For-Beginners/watchers/) +[![GitHub-seere](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-stjerner](https://img.shields.io/github/stars/microsoft/ML-For-Beginners.svg?style=social&label=Star)](https://GitHub.com/microsoft/ML-For-Beginners/stargazers/) @@ -22,65 +22,65 @@ CO_OP_TRANSLATOR_METADATA: #### Understøttet via GitHub Action (Automatiseret og altid opdateret) -[Arabisk](../ar/README.md) | [Bengali](../bn/README.md) | [Bulgarsk](../bg/README.md) | [Burmesisk (Myanmar)](../my/README.md) | [Kinesisk (forenklet)](../zh/README.md) | [Kinesisk (traditionelt, Hongkong)](../hk/README.md) | [Kinesisk (traditionelt, Macau)](../mo/README.md) | [Kinesisk (traditionelt, Taiwan)](../tw/README.md) | [Kroatisk](../hr/README.md) | [Tjekkisk](../cs/README.md) | [Dansk](./README.md) | [Hollandsk](../nl/README.md) | [Estisk](../et/README.md) | [Finsk](../fi/README.md) | [Fransk](../fr/README.md) | [Tysk](../de/README.md) | [Græsk](../el/README.md) | [Hebraisk](../he/README.md) | [Hindi](../hi/README.md) | [Ungarsk](../hu/README.md) | [Indonesisk](../id/README.md) | [Italiensk](../it/README.md) | [Japansk](../ja/README.md) | [Kannada](../kn/README.md) | [Koreansk](../ko/README.md) | [Litauisk](../lt/README.md) | [Malayisk](../ms/README.md) | [Malayalam](../ml/README.md) | [Marathi](../mr/README.md) | [Nepali](../ne/README.md) | [Nigeriansk pidgin](../pcm/README.md) | [Norsk](../no/README.md) | [Persisk (Farsi)](../fa/README.md) | [Polsk](../pl/README.md) | [Portugisisk (Brasilien)](../br/README.md) | [Portugisisk (Portugal)](../pt/README.md) | [Punjabi (Gurmukhi)](../pa/README.md) | [Rumænsk](../ro/README.md) | [Russisk](../ru/README.md) | [Serbisk (kyrillisk)](../sr/README.md) | [Slovakisk](../sk/README.md) | [Slovensk](../sl/README.md) | [Spansk](../es/README.md) | [Swahili](../sw/README.md) | [Svensk](../sv/README.md) | [Tagalog (Filippinsk)](../tl/README.md) | [Tamil](../ta/README.md) | [Telugu](../te/README.md) | [Thai](../th/README.md) | [Tyrkisk](../tr/README.md) | [Ukrainsk](../uk/README.md) | [Urdu](../ur/README.md) | [Vietnamesisk](../vi/README.md) +[Arabic](../ar/README.md) | [Bengali](../bn/README.md) | [Bulgarian](../bg/README.md) | [Burmese (Myanmar)](../my/README.md) | [Chinese (Simplified)](../zh/README.md) | [Chinese (Traditional, Hong Kong)](../hk/README.md) | [Chinese (Traditional, Macau)](../mo/README.md) | [Chinese (Traditional, Taiwan)](../tw/README.md) | [Croatian](../hr/README.md) | [Czech](../cs/README.md) | [Danish](./README.md) | [Dutch](../nl/README.md) | [Estonian](../et/README.md) | [Finnish](../fi/README.md) | [French](../fr/README.md) | [German](../de/README.md) | [Greek](../el/README.md) | [Hebrew](../he/README.md) | [Hindi](../hi/README.md) | [Hungarian](../hu/README.md) | [Indonesian](../id/README.md) | [Italian](../it/README.md) | [Japanese](../ja/README.md) | [Kannada](../kn/README.md) | [Korean](../ko/README.md) | [Lithuanian](../lt/README.md) | [Malay](../ms/README.md) | [Malayalam](../ml/README.md) | [Marathi](../mr/README.md) | [Nepali](../ne/README.md) | [Nigerian Pidgin](../pcm/README.md) | [Norwegian](../no/README.md) | [Persian (Farsi)](../fa/README.md) | [Polish](../pl/README.md) | [Portuguese (Brazil)](../br/README.md) | [Portuguese (Portugal)](../pt/README.md) | [Punjabi (Gurmukhi)](../pa/README.md) | [Romanian](../ro/README.md) | [Russian](../ru/README.md) | [Serbian (Cyrillic)](../sr/README.md) | [Slovak](../sk/README.md) | [Slovenian](../sl/README.md) | [Spanish](../es/README.md) | [Swahili](../sw/README.md) | [Swedish](../sv/README.md) | [Tagalog (Filipino)](../tl/README.md) | [Tamil](../ta/README.md) | [Telugu](../te/README.md) | [Thai](../th/README.md) | [Turkish](../tr/README.md) | [Ukrainian](../uk/README.md) | [Urdu](../ur/README.md) | [Vietnamese](../vi/README.md) #### Deltag i vores fællesskab [![Microsoft Foundry Discord](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) -Vi har en igangværende Discord "Learn with AI"-serie; læs mere og tilmeld dig på [Lær med AI-serien](https://aka.ms/learnwithai/discord) fra 18. - 30. september 2025. Du får tips og tricks til at bruge GitHub Copilot til Data Science. +Vi har en løbende Discord "Learn with AI"-serie; læs mere og deltag hos [Learn with AI Series](https://aka.ms/learnwithai/discord) fra 18. - 30. september 2025. Du vil få tips og tricks til at bruge GitHub Copilot til Data Science. -![Lær med AI-serien](../../translated_images/3.9b58fd8d6c373c20c588c5070c4948a826ab074426c28ceb5889641294373dfc.da.png) +![Lær med AI-serien](../../translated_images/3.9b58fd8d6c373c20.da.png) # Maskinlæring for begyndere - En læseplan > 🌍 Rejs rundt i verden, mens vi udforsker maskinlæring gennem verdens kulturer 🌍 -Cloud Advocates hos Microsoft er glade for at tilbyde et 12-ugers, 26-lektioners pensum om **Maskinlæring**. I dette pensum vil du lære om det, der nogle gange kaldes **klassisk maskinlæring**, primært ved brug af Scikit-learn som bibliotek og uden dyb læring, som er dækket i vores [AI for Beginners' curriculum](https://aka.ms/ai4beginners). Kombinér disse lektioner med vores ['Data Science for Beginners' curriculum](https://aka.ms/ds4beginners) også! +Cloud Advocates hos Microsoft tilbyder en 12-ugers, 26-lektions læseplan, der handler om **Maskinlæring**. I denne læseplan lærer du om det, som nogle gange kaldes **klassisk maskinlæring**, hvor vi primært bruger Scikit-learn som bibliotek og undgår deep learning, som dækkes i vores [AI for Beginners' curriculum](https://aka.ms/ai4beginners). Kombiner disse lektioner med vores ['Data Science for Beginners' curriculum](https://aka.ms/ds4beginners) også! -Rejs med os rundt i verden, mens vi anvender disse klassiske teknikker på data fra mange regioner. Hver lektion inkluderer før- og efter-forelæsningsquizzer, skriftlige instruktioner til at fuldføre lektionen, en løsning, en opgave og mere. Vores projektbaserede pædagogik gør det muligt at lære ved at bygge, en bevist måde for nye færdigheder at 'sidde fast'. +Rejs med os rundt i verden, mens vi anvender disse klassiske teknikker på data fra mange regioner. Hver lektion indeholder quizzer før og efter lektionen, skriftlige instruktioner til at gennemføre lektionen, en løsning, en opgave og mere. Vores projektbaserede pædagogik giver dig mulighed for at lære ved at bygge, en bevist måde at få nye færdigheder til at "sætte sig". -**✍️ Hjertelig tak til vores forfattere** Jen Looper, Stephen Howell, Francesca Lazzeri, Tomomi Imura, Cassie Breviu, Dmitry Soshnikov, Chris Noring, Anirban Mukherjee, Ornella Altunyan, Ruth Yakubu and Amy Boyd +**✍️ Stor tak til vores forfattere** Jen Looper, Stephen Howell, Francesca Lazzeri, Tomomi Imura, Cassie Breviu, Dmitry Soshnikov, Chris Noring, Anirban Mukherjee, Ornella Altunyan, Ruth Yakubu og Amy Boyd -**🎨 Tak også til vores illustratorer** Tomomi Imura, Dasani Madipalli, og Jen Looper +**🎨 Tak også til vores illustratorer** Tomomi Imura, Dasani Madipalli og Jen Looper -**🙏 Særlig tak 🙏 til vores Microsoft Student Ambassador-forfattere, -anmeldere og -indholdsleverandører**, navnlig Rishit Dagli, Muhammad Sakib Khan Inan, Rohan Raj, Alexandru Petrescu, Abhishek Jaiswal, Nawrin Tabassum, Ioan Samuila, og Snigdha Agarwal +**🙏 Særlige tak 🙏 til vores Microsoft Student Ambassador-forfattere, anmeldere og indholds-bidragsydere**, særligt Rishit Dagli, Muhammad Sakib Khan Inan, Rohan Raj, Alexandru Petrescu, Abhishek Jaiswal, Nawrin Tabassum, Ioan Samuila og Snigdha Agarwal -**🤩 Ekstra tak til Microsoft Student Ambassadors Eric Wanjau, Jasleen Sondhi, og Vidushi Gupta for vores R-lektioner!** +**🤩 Ekstra tak til Microsoft Student Ambassadors Eric Wanjau, Jasleen Sondhi og Vidushi Gupta for vores R-lektioner!** # Kom godt i gang Følg disse trin: -1. **Fork repository'et**: Klik på "Fork"-knappen øverst til højre på denne side. -2. **Klon repository'et**: `git clone https://github.com/microsoft/ML-For-Beginners.git` +1. **Fork repositoryet**: Klik på knappen "Fork" øverst til højre på denne side. +2. **Klon repositoryet**: `git clone https://github.com/microsoft/ML-For-Beginners.git` > [find alle yderligere ressourcer til dette kursus i vores Microsoft Learn-samling](https://learn.microsoft.com/en-us/collections/qrqzamz1nn2wx3?WT.mc_id=academic-77952-bethanycheum) -> 🔧 **Brug for hjælp?** Tjek vores [Fejlfinding](TROUBLESHOOTING.md) for løsninger på almindelige problemer med installation, opsætning og kørsel af lektioner. +> 🔧 **Brug for hjælp?** Se vores [Troubleshooting Guide](TROUBLESHOOTING.md) for løsninger på almindelige problemer med installation, opsætning og kørsel af lektioner. -**[Studerende](https://aka.ms/student-page)**, for at bruge dette pensum, fork hele repo'et til din egen GitHub-konto og fuldfør øvelserne på egen hånd eller i en gruppe: +**[Studerende](https://aka.ms/student-page)**, for at bruge denne læseplan: fork hele repoet til din egen GitHub-konto og gennemfør øvelserne på egen hånd eller i en gruppe: -- Start med en opvarmningsquiz før forelæsningen. -- Læs forelæsningen og fuldfør aktiviteterne, stop op og reflekter ved hvert videnscheck. -- Forsøg at lave projekterne ved at forstå lektionerne i stedet for blot at køre løsningskoden; den kode er dog tilgængelig i `/solution` mapperne i hver projektorienteret lektion. -- Tag quizzen efter forelæsningen. -- Fuldfør udfordringen. -- Fuldfør opgaven. -- Efter du har gennemført en lektionsgruppe, besøg [Diskussionsforumet](https://github.com/microsoft/ML-For-Beginners/discussions) og "lær højt" ved at udfylde den passende PAT-rubrik. En 'PAT' er et Progress Assessment Tool, som er en rubrik du udfylder for at fremme din læring. Du kan også reagere på andre PAT'er, så vi kan lære sammen. +- Start med en quiz før lektionen. +- Læs lektionen og gennemfør aktiviteterne, stop op og reflekter ved hver videnscheck. +- Prøv at skabe projekterne ved at forstå lektionerne i stedet for bare at køre løsningskoden; dog er den kode tilgængelig i `/solution`-mapperne i hver projektorienteret lektion. +- Tag quizzen efter lektionen. +- Gennemfør udfordringen. +- Gennemfør opgaven. +- Efter at have gennemført en lektion, besøg [Discussion Board](https://github.com/microsoft/ML-For-Beginners/discussions) og "learn out loud" ved at udfylde den passende PAT-rubric. En 'PAT' er et Progress Assessment Tool, en rubric du udfylder for at fremme din læring. Du kan også reagere på andre PATs, så vi kan lære sammen. -> Til videre studie anbefaler vi at følge disse [Microsoft Learn](https://docs.microsoft.com/en-us/users/jenlooper-2911/collections/k7o7tg1gp306q4?WT.mc_id=academic-77952-leestott) moduler og læringsforløb. +> Til videre studier anbefaler vi at følge disse [Microsoft Learn](https://docs.microsoft.com/en-us/users/jenlooper-2911/collections/k7o7tg1gp306q4?WT.mc_id=academic-77952-leestott) moduler og læringsforløb. -**Lærere**, vi har [inkluderet nogle forslag](for-teachers.md) til, hvordan du bruger dette pensum. +**Lærere**, vi har [inkluderet nogle forslag](for-teachers.md) til, hvordan man bruger denne læseplan. --- ## Video-gennemgange -Nogle af lektionerne er tilgængelige som korte videoer. Du kan finde dem inde i lektionerne eller på [ML for Beginners-playlisten på Microsoft Developer YouTube-kanalen](https://aka.ms/ml-beginners-videos) ved at klikke på billedet nedenfor. +Nogle af lektionerne er tilgængelige som kortformede videoer. Du kan finde dem indlejret i lektionerne, eller på [ML for Beginners-playlisten på Microsoft Developer YouTube-kanalen](https://aka.ms/ml-beginners-videos) ved at klikke på billedet nedenfor. -[![ML for begyndere-banner](../../translated_images/ml-for-beginners-video-banner.63f694a100034bc6251134294459696e070a3a9a04632e9fe6a24aa0de4a7384.da.png)](https://aka.ms/ml-beginners-videos) +[![ML for beginners-banner](../../translated_images/ml-for-beginners-video-banner.63f694a100034bc6.da.png)](https://aka.ms/ml-beginners-videos) --- @@ -90,71 +90,71 @@ Nogle af lektionerne er tilgængelige som korte videoer. Du kan finde dem inde i **Gif af** [Mohit Jaisal](https://linkedin.com/in/mohitjaisal) -> 🎥 Klik på billedet ovenfor for en video om projektet og folkene, der skabte det! +> 🎥 Klik på billedet ovenfor for en video om projektet og de personer, der skabte det! --- ## Pædagogik -Vi har valgt to pædagogiske principper, mens vi byggede dette pensum: sikring af, at det er håndgribeligt og **projektbaseret**, og at det inkluderer **hyppige quizzer**. Derudover har dette pensum et fælles **tema** for at give det sammenhæng. +Vi har valgt to pædagogiske principper i udviklingen af denne læseplan: at sikre, at den er praktisk og **projektbaseret**, og at den inkluderer **hyppige quizzer**. Derudover har denne læseplan et fælles **tema** for at skabe sammenhæng. -Ved at sikre, at indholdet stemmer overens med projekter, gøres processen mere engagerende for studerende, og fastholdelsen af koncepter vil blive øget. Derudover sætter en lavrisiko-quiz før en klasse den studerendes intention mod at lære et emne, mens en anden quiz efter klassen sikrer yderligere fastholdelse. Dette pensum er designet til at være fleksibelt og sjovt og kan tages i helhed eller delvist. Projekterne starter småt og bliver gradvist mere komplekse mod slutningen af den 12-ugers cyklus. Dette pensum inkluderer også et efterskrift om virkelige anvendelser af ML, som kan bruges som ekstra kredit eller som grundlag for diskussion. +Ved at sikre, at indholdet er tilpasset projekter, bliver processen mere engagerende for eleverne, og fastholdelsen af begreber vil blive forbedret. Desuden sætter en lavrisiko-quiz før en lektion intentionen hos eleven mod at lære et emne, mens en anden quiz efter lektionen sikrer yderligere fastholdelse. Denne læseplan er designet til at være fleksibel og sjov og kan tages i sin helhed eller delvist. Projekterne starter småt og bliver gradvist mere komplekse ved slutningen af den 12-ugers cyklus. Denne læseplan inkluderer også et efterord om virkelige anvendelser af ML, som kan bruges som ekstra kredit eller som basis for diskussion. -> Find vores [Adfærdskodeks](CODE_OF_CONDUCT.md), [Bidrag](CONTRIBUTING.md), [Oversættelse](TRANSLATIONS.md), og [Fejlfinding](TROUBLESHOOTING.md) retningslinjer. Vi byder dine konstruktive tilbagemeldinger velkommen! +> Find vores [Code of Conduct](CODE_OF_CONDUCT.md), [Contributing](CONTRIBUTING.md), [Translation](TRANSLATIONS.md) og [Troubleshooting](TROUBLESHOOTING.md) retningslinjer. Vi byder din konstruktive feedback velkommen! ## Hver lektion indeholder - valgfri sketchnote - valgfri supplerende video -- video-gennemgang (kun nogle lektioner) -- [opvarmningsquiz før forelæsning](https://ff-quizzes.netlify.app/en/ml/) +- videogenomgang (kun nogle lektioner) +- [pre-lecture warmup quiz](https://ff-quizzes.netlify.app/en/ml/) - skriftlig lektion - for projektbaserede lektioner, trin-for-trin vejledninger til, hvordan man bygger projektet - videnschecks - en udfordring - supplerende læsning - opgave -- [quiz efter forelæsning](https://ff-quizzes.netlify.app/en/ml/) +- [post-lecture quiz](https://ff-quizzes.netlify.app/en/ml/) -> **En note om sprog**: Disse lektioner er primært skrevet i Python, men mange fås også i R. For at fuldføre en R-lektion, gå til `/solution` mappen og kig efter R-lektioner. De inkluderer en .rmd-udvidelse, som repræsenterer en **R Markdown**-fil, som enkelt kan defineres som en indlejring af `code chunks` (af R eller andre sprog) og en `YAML header` (der styrer, hvordan man formaterer output som PDF) i et `Markdown-dokument`. Som sådan fungerer det som en eksemplarisk forfatter-ramme for data science, da det tillader dig at kombinere din kode, dens output, og dine tanker ved at skrive dem ned i Markdown. Desuden kan R Markdown-dokumenter gengives til outputformater som PDF, HTML eller Word. +> **En note om sprog**: Disse lektioner er primært skrevet i Python, men mange er også tilgængelige i R. For at gennemføre en R-lektion, gå til `/solution`-mappen og kig efter R-lektioner. De indeholder en .rmd-udvidelse, som repræsenterer en **R Markdown**-fil, der enkelt kan defineres som en indlejring af `code chunks` (af R eller andre sprog) og en `YAML header` (der styrer, hvordan outputs som PDF formateres) i et `Markdown document`. Som sådan tjener det som en fremragende forfatterramme for data science, da det giver dig mulighed for at kombinere din kode, dens output og dine tanker ved at lade dig skrive dem ned i Markdown. Desuden kan R Markdown-dokumenter gengives til outputformater såsom PDF, HTML eller Word. -> **En note om quizzer**: Alle quizzer er indeholdt i [Quiz-app-mappen](../../quiz-app), i alt 52 quizzer med tre spørgsmål hver. De er linket fra lektionerne, men quiz-appen kan køres lokalt; følg instruktionen i `quiz-app` mappen for at hoste lokalt eller deploye til Azure. +> **En note om quizzer**: Alle quizzer findes i [Quiz App folder](../../quiz-app), i alt 52 quizzer med tre spørgsmål hver. De er linket fra lektionerne, men quiz-appen kan køres lokalt; følg instruktionerne i `quiz-app`-mappen for at hoste lokalt eller deploye til Azure. -| Lektionsnummer | Emne | Lektionsgruppering | Læringsmål | Linket lektion | Forfatter | +| Lektion Nummer | Emne | Lektionsgruppering | Læringsmål | Knyttet lektion | Forfatter | | :-----------: | :------------------------------------------------------------: | :-------------------------------------------------: | ------------------------------------------------------------------------------------------------------------------------------- | :--------------------------------------------------------------------------------------------------------------------------------------: | :--------------------------------------------------: | -| 01 | Introduktion til maskinlæring | [Introduktion](1-Introduction/README.md) | Lær de grundlæggende begreber bag maskinlæring | [Lektion](1-Introduction/1-intro-to-ML/README.md) | Muhammad | -| 02 | Maskinlæringens historie | [Introduktion](1-Introduction/README.md) | Lær historien bag dette felt | [Lektion](1-Introduction/2-history-of-ML/README.md) | Jen and Amy | +| 01 | Introduktion til maskinlæring | [Introduktion](1-Introduction/README.md) | Lær de grundlæggende koncepter bag maskinlæring | [Lektion](1-Introduction/1-intro-to-ML/README.md) | Muhammad | +| 02 | Maskinlæringens historie | [Introduktion](1-Introduction/README.md) | Lær historien bag dette felt | [Lektion](1-Introduction/2-history-of-ML/README.md) | Jen and Amy | | 03 | Retfærdighed og maskinlæring | [Introduktion](1-Introduction/README.md) | Hvad er de vigtige filosofiske spørgsmål omkring retfærdighed, som studerende bør overveje, når de bygger og anvender ML-modeller? | [Lektion](1-Introduction/3-fairness/README.md) | Tomomi | -| 04 | Teknikker til maskinlæring | [Introduktion](1-Introduction/README.md) | Hvilke teknikker bruger ML-forskere til at bygge ML-modeller? | [Lektion](1-Introduction/4-techniques-of-ML/README.md) | Chris and Jen | -| 05 | Introduktion til regression | [Regression](2-Regression/README.md) | Kom i gang med Python og Scikit-learn til regressionsmodeller | [Python](2-Regression/1-Tools/README.md) • [R](../../2-Regression/1-Tools/solution/R/lesson_1.html) | Jen • Eric Wanjau | -| 06 | Priser på græskar i Nordamerika 🎃 | [Regression](2-Regression/README.md) | Visualisér og rens data som forberedelse til ML | [Python](2-Regression/2-Data/README.md) • [R](../../2-Regression/2-Data/solution/R/lesson_2.html) | Jen • Eric Wanjau | -| 07 | Priser på græskar i Nordamerika 🎃 | [Regression](2-Regression/README.md) | Byg lineære og polynomiske regressionsmodeller | [Python](2-Regression/3-Linear/README.md) • [R](../../2-Regression/3-Linear/solution/R/lesson_3.html) | Jen and Dmitry • Eric Wanjau | -| 08 | Priser på græskar i Nordamerika 🎃 | [Regression](2-Regression/README.md) | Byg en logistisk regressionsmodel | [Python](2-Regression/4-Logistic/README.md) • [R](../../2-Regression/4-Logistic/solution/R/lesson_4.html) | Jen • Eric Wanjau | -| 09 | En webapp 🔌 | [Web App](3-Web-App/README.md) | Byg en webapp til at bruge din trænede model | [Python](3-Web-App/1-Web-App/README.md) | Jen | -| 10 | Introduktion til klassifikation | [Classification](4-Classification/README.md) | Rens, forbered og visualisér dine data; introduktion til klassifikation | [Python](4-Classification/1-Introduction/README.md) • [R](../../4-Classification/1-Introduction/solution/R/lesson_10.html) | Jen and Cassie • Eric Wanjau | -| 11 | Lækre asiatiske og indiske køkkener 🍜 | [Classification](4-Classification/README.md) | Introduktion til klassifikatorer | [Python](4-Classification/2-Classifiers-1/README.md) • [R](../../4-Classification/2-Classifiers-1/solution/R/lesson_11.html) | Jen and Cassie • Eric Wanjau | -| 12 | Lækre asiatiske og indiske køkkener 🍜 | [Classification](4-Classification/README.md) | Flere klassifikatorer | [Python](4-Classification/3-Classifiers-2/README.md) • [R](../../4-Classification/3-Classifiers-2/solution/R/lesson_12.html) | Jen and Cassie • Eric Wanjau | -| 13 | Lækre asiatiske og indiske køkkener 🍜 | [Classification](4-Classification/README.md) | Byg en anbefalings-webapp ved hjælp af din model | [Python](4-Classification/4-Applied/README.md) | Jen | -| 14 | Introduktion til klyngedannelse | [Clustering](5-Clustering/README.md) | Rens, forbered og visualisér dine data; introduktion til klyngedannelse | [Python](5-Clustering/1-Visualize/README.md) • [R](../../5-Clustering/1-Visualize/solution/R/lesson_14.html) | Jen • Eric Wanjau | -| 15 | Udforskning af nigerianske musiksmag 🎧 | [Clustering](5-Clustering/README.md) | Udforsk K-Means klyngemetoden | [Python](5-Clustering/2-K-Means/README.md) • [R](../../5-Clustering/2-K-Means/solution/R/lesson_15.html) | Jen • Eric Wanjau | -| 16 | Introduktion til naturlig sprogbehandling ☕️ | [Natural language processing](6-NLP/README.md) | Lær det grundlæggende om NLP ved at bygge en simpel bot | [Python](6-NLP/1-Introduction-to-NLP/README.md) | Stephen | -| 17 | Almindelige NLP-opgaver ☕️ | [Natural language processing](6-NLP/README.md) | Uddyb din NLP-viden ved at forstå almindelige opgaver, der kræves ved håndtering af sproglige strukturer | [Python](6-NLP/2-Tasks/README.md) | Stephen | -| 18 | Oversættelse og sentimentanalyse ♥️ | [Natural language processing](6-NLP/README.md) | Oversættelse og sentimentanalyse med Jane Austen | [Python](6-NLP/3-Translation-Sentiment/README.md) | Stephen | -| 19 | Romantiske hoteller i Europa ♥️ | [Natural language processing](6-NLP/README.md) | Sentimentanalyse med hotelanmeldelser 1 | [Python](6-NLP/4-Hotel-Reviews-1/README.md) | Stephen | -| 20 | Romantiske hoteller i Europa ♥️ | [Natural language processing](6-NLP/README.md) | Sentimentanalyse med hotelanmeldelser 2 | [Python](6-NLP/5-Hotel-Reviews-2/README.md) | Stephen | -| 21 | Introduktion til tidsserieprognoser | [Time series](7-TimeSeries/README.md) | Introduktion til tidsserieprognoser | [Python](7-TimeSeries/1-Introduction/README.md) | Francesca | -| 22 | ⚡️ World Power Usage ⚡️ - time series forecasting with ARIMA | [Time series](7-TimeSeries/README.md) | Tidsserieprognoser med ARIMA | [Python](7-TimeSeries/2-ARIMA/README.md) | Francesca | -| 23 | ⚡️ World Power Usage ⚡️ - time series forecasting with SVR | [Time series](7-TimeSeries/README.md) | Tidsserieprognoser med Support Vector Regressor | [Python](7-TimeSeries/3-SVR/README.md) | Anirban | -| 24 | Introduktion til forstærkningslæring | [Reinforcement learning](8-Reinforcement/README.md) | Introduktion til forstærkningslæring med Q-Learning | [Python](8-Reinforcement/1-QLearning/README.md) | Dmitry | -| 25 | Hjælp Peter med at undgå ulven! 🐺 | [Reinforcement learning](8-Reinforcement/README.md) | Reinforcement learning Gym | [Python](8-Reinforcement/2-Gym/README.md) | Dmitry | -| Efterskrift | Virkelige ML-scenarier og anvendelser | [ML in the Wild](9-Real-World/README.md) | Interessante og afslørende virkelige anvendelser af klassisk ML | [Lektion](9-Real-World/1-Applications/README.md) | Team | -| Efterskrift | Modelfejlfinding i ML ved hjælp af RAI-dashboard | [ML in the Wild](9-Real-World/README.md) | Modelfejlfinding i maskinlæring ved hjælp af Responsible AI-dashboardkomponenter | [Lektion](9-Real-World/2-Debugging-ML-Models/README.md) | Ruth Yakubu | +| 04 | Teknikker til maskinlæring | [Introduktion](1-Introduction/README.md) | Hvilke teknikker bruger ML-forskere til at opbygge ML-modeller? | [Lektion](1-Introduction/4-techniques-of-ML/README.md) | Chris and Jen | +| 05 | Introduktion til regression | [Regression](2-Regression/README.md) | Kom i gang med Python og Scikit-learn til regressionsmodeller | [Python](2-Regression/1-Tools/README.md) • [R](../../2-Regression/1-Tools/solution/R/lesson_1.html) | Jen • Eric Wanjau | +| 06 | Græskarpriser i Nordamerika 🎃 | [Regression](2-Regression/README.md) | Visualisér og rens data som forberedelse til ML | [Python](2-Regression/2-Data/README.md) • [R](../../2-Regression/2-Data/solution/R/lesson_2.html) | Jen • Eric Wanjau | +| 07 | Græskarpriser i Nordamerika 🎃 | [Regression](2-Regression/README.md) | Byg lineære og polynomielle regressionsmodeller | [Python](2-Regression/3-Linear/README.md) • [R](../../2-Regression/3-Linear/solution/R/lesson_3.html) | Jen and Dmitry • Eric Wanjau | +| 08 | Græskarpriser i Nordamerika 🎃 | [Regression](2-Regression/README.md) | Byg en logistisk regressionsmodel | [Python](2-Regression/4-Logistic/README.md) • [R](../../2-Regression/4-Logistic/solution/R/lesson_4.html) | Jen • Eric Wanjau | +| 09 | En webapp 🔌 | [Webapp](3-Web-App/README.md) | Byg en webapp til at bruge din trænede model | [Python](3-Web-App/1-Web-App/README.md) | Jen | +| 10 | Introduktion til klassifikation | [Klassifikation](4-Classification/README.md) | Rens, forbered og visualisér dine data; introduktion til klassifikation | [Python](4-Classification/1-Introduction/README.md) • [R](../../4-Classification/1-Introduction/solution/R/lesson_10.html) | Jen and Cassie • Eric Wanjau | +| 11 | Lækre asiatiske og indiske køkkener 🍜 | [Klassifikation](4-Classification/README.md) | Introduktion til klassifikatorer | [Python](4-Classification/2-Classifiers-1/README.md) • [R](../../4-Classification/2-Classifiers-1/solution/R/lesson_11.html) | Jen and Cassie • Eric Wanjau | +| 12 | Lækre asiatiske og indiske køkkener 🍜 | [Klassifikation](4-Classification/README.md) | Flere klassifikatorer | [Python](4-Classification/3-Classifiers-2/README.md) • [R](../../4-Classification/3-Classifiers-2/solution/R/lesson_12.html) | Jen and Cassie • Eric Wanjau | +| 13 | Lækre asiatiske og indiske køkkener 🍜 | [Klassifikation](4-Classification/README.md) | Byg en anbefalingswebapp ved hjælp af din model | [Python](4-Classification/4-Applied/README.md) | Jen | +| 14 | Introduktion til klyngedannelse | [Klyngedannelse](5-Clustering/README.md) | Rens, forbered og visualisér dine data; introduktion til klyngedannelse | [Python](5-Clustering/1-Visualize/README.md) • [R](../../5-Clustering/1-Visualize/solution/R/lesson_14.html) | Jen • Eric Wanjau | +| 15 | Udforskning af nigerianske musikpræferencer 🎧 | [Klyngedannelse](5-Clustering/README.md) | Udforsk K-Means-klyngemetoden | [Python](5-Clustering/2-K-Means/README.md) • [R](../../5-Clustering/2-K-Means/solution/R/lesson_15.html) | Jen • Eric Wanjau | +| 16 | Introduktion til naturlig sprogbehandling ☕️ | [Naturlig sprogbehandling](6-NLP/README.md) | Lær det grundlæggende om NLP ved at bygge en simpel bot | [Python](6-NLP/1-Introduction-to-NLP/README.md) | Stephen | +| 17 | Almindelige NLP-opgaver ☕️ | [Naturlig sprogbehandling](6-NLP/README.md) | Uddyb din NLP-viden ved at forstå almindelige opgaver, som er nødvendige, når man arbejder med sprogstrukturer | [Python](6-NLP/2-Tasks/README.md) | Stephen | +| 18 | Oversættelse og sentimentanalyse ♥️ | [Naturlig sprogbehandling](6-NLP/README.md) | Oversættelse og sentimentanalyse med Jane Austen | [Python](6-NLP/3-Translation-Sentiment/README.md) | Stephen | +| 19 | Romantiske hoteller i Europa ♥️ | [Naturlig sprogbehandling](6-NLP/README.md) | Sentimentanalyse med hotelanmeldelser 1 | [Python](6-NLP/4-Hotel-Reviews-1/README.md) | Stephen | +| 20 | Romantiske hoteller i Europa ♥️ | [Naturlig sprogbehandling](6-NLP/README.md) | Sentimentanalyse med hotelanmeldelser 2 | [Python](6-NLP/5-Hotel-Reviews-2/README.md) | Stephen | +| 21 | Introduktion til tidsserieprognoser | [Tidsserier](7-TimeSeries/README.md) | Introduktion til tidsserieprognoser | [Python](7-TimeSeries/1-Introduction/README.md) | Francesca | +| 22 | ⚡️ Verdens elforbrug ⚡️ - tidsserieprognoser med ARIMA | [Tidsserier](7-TimeSeries/README.md) | Tidsserieprognoser med ARIMA | [Python](7-TimeSeries/2-ARIMA/README.md) | Francesca | +| 23 | ⚡️ Verdens elforbrug ⚡️ - tidsserieprognoser med SVR | [Tidsserier](7-TimeSeries/README.md) | Tidsserieprognoser med Support Vector Regressor | [Python](7-TimeSeries/3-SVR/README.md) | Anirban | +| 24 | Introduktion til forstærkningslæring | [Forstærkningslæring](8-Reinforcement/README.md) | Introduktion til forstærkningslæring med Q-Learning | [Python](8-Reinforcement/1-QLearning/README.md) | Dmitry | +| 25 | Hjælp Peter med at undgå ulven! 🐺 | [Forstærkningslæring](8-Reinforcement/README.md) | Gym for forstærkningslæring | [Python](8-Reinforcement/2-Gym/README.md) | Dmitry | +| Efterskrift | Virkelige ML-scenarier og anvendelser | [ML i virkeligheden](9-Real-World/README.md) | Interessante og afslørende virkelige anvendelser af klassisk ML | [Lektion](9-Real-World/1-Applications/README.md) | Team | +| Efterskrift | Modeldebugging i ML ved brug af RAI-dashboardet | [ML i virkeligheden](9-Real-World/README.md) | Modeldebugging i maskinlæring ved hjælp af Responsible AI dashboard-komponenter | [Lektion](9-Real-World/2-Debugging-ML-Models/README.md) | Ruth Yakubu | > [find alle yderligere ressourcer til dette kursus i vores Microsoft Learn-samling](https://learn.microsoft.com/en-us/collections/qrqzamz1nn2wx3?WT.mc_id=academic-77952-bethanycheum) ## Offline adgang -Du kan køre denne dokumentation offline ved at bruge [Docsify](https://docsify.js.org/#/). Fork dette repo, [installer Docsify](https://docsify.js.org/#/quickstart) på din lokale maskine, og skriv derefter i rodmappen af dette repo `docsify serve`. Webstedet vil blive serveret på port 3000 på din localhost: `localhost:3000`. +Du kan køre denne dokumentation offline ved at bruge [Docsify](https://docsify.js.org/#/). Fork dette repo, [installer Docsify](https://docsify.js.org/#/quickstart) på din lokale maskine, og derefter i rodmappen af dette repo, skriv `docsify serve`. Hjemmesiden vil blive serveret på port 3000 på din localhost: `localhost:3000`. ## PDF'er @@ -163,7 +163,7 @@ Find en pdf af pensum med links [her](https://microsoft.github.io/ML-For-Beginne ## 🎒 Andre kurser -Vores team producerer andre kurser! Tjek disse: +Vores team producerer andre kurser! Tjek dem: ### LangChain @@ -172,7 +172,7 @@ Vores team producerer andre kurser! Tjek disse: --- -### Azure / Edge / MCP / Agenter +### Azure / Edge / MCP / Agents [![AZD for begyndere](https://img.shields.io/badge/AZD%20for%20Beginners-0078D4?style=for-the-badge&labelColor=E5E7EB&color=0078D4)](https://github.com/microsoft/AZD-for-beginners?WT.mc_id=academic-105485-koreyst) [![Edge AI for begyndere](https://img.shields.io/badge/Edge%20AI%20for%20Beginners-00B8E4?style=for-the-badge&labelColor=E5E7EB&color=00B8E4)](https://github.com/microsoft/edgeai-for-beginners?WT.mc_id=academic-105485-koreyst) [![MCP for begyndere](https://img.shields.io/badge/MCP%20for%20Beginners-009688?style=for-the-badge&labelColor=E5E7EB&color=009688)](https://github.com/microsoft/mcp-for-beginners?WT.mc_id=academic-105485-koreyst) @@ -188,10 +188,10 @@ Vores team producerer andre kurser! Tjek disse: --- -### Grundlæggende læring -[![Maskinlæring for begyndere](https://img.shields.io/badge/ML%20for%20Beginners-22C55E?style=for-the-badge&labelColor=E5E7EB&color=22C55E)](https://aka.ms/ml-beginners?WT.mc_id=academic-105485-koreyst) -[![Datavidenskab for begyndere](https://img.shields.io/badge/Data%20Science%20for%20Beginners-84CC16?style=for-the-badge&labelColor=E5E7EB&color=84CC16)](https://aka.ms/datascience-beginners?WT.mc_id=academic-105485-koreyst) -[![Kunstig intelligens for begyndere](https://img.shields.io/badge/AI%20for%20Beginners-A3E635?style=for-the-badge&labelColor=E5E7EB&color=A3E635)](https://aka.ms/ai-beginners?WT.mc_id=academic-105485-koreyst) +### Kernekurser +[![ML for begyndere](https://img.shields.io/badge/ML%20for%20Beginners-22C55E?style=for-the-badge&labelColor=E5E7EB&color=22C55E)](https://aka.ms/ml-beginners?WT.mc_id=academic-105485-koreyst) +[![Data Science for begyndere](https://img.shields.io/badge/Data%20Science%20for%20Beginners-84CC16?style=for-the-badge&labelColor=E5E7EB&color=84CC16)](https://aka.ms/datascience-beginners?WT.mc_id=academic-105485-koreyst) +[![AI for begyndere](https://img.shields.io/badge/AI%20for%20Beginners-A3E635?style=for-the-badge&labelColor=E5E7EB&color=A3E635)](https://aka.ms/ai-beginners?WT.mc_id=academic-105485-koreyst) [![Cybersikkerhed for begyndere](https://img.shields.io/badge/Cybersecurity%20for%20Beginners-F97316?style=for-the-badge&labelColor=E5E7EB&color=F97316)](https://github.com/microsoft/Security-101?WT.mc_id=academic-96948-sayoung) [![Webudvikling for begyndere](https://img.shields.io/badge/Web%20Dev%20for%20Beginners-EC4899?style=for-the-badge&labelColor=E5E7EB&color=EC4899)](https://aka.ms/webdev-beginners?WT.mc_id=academic-105485-koreyst) [![IoT for begyndere](https://img.shields.io/badge/IoT%20for%20Beginners-14B8A6?style=for-the-badge&labelColor=E5E7EB&color=14B8A6)](https://aka.ms/iot-beginners?WT.mc_id=academic-105485-koreyst) @@ -202,22 +202,22 @@ Vores team producerer andre kurser! Tjek disse: ### Copilot-serien [![Copilot til AI-parprogrammering](https://img.shields.io/badge/Copilot%20for%20AI%20Paired%20Programming-FACC15?style=for-the-badge&labelColor=E5E7EB&color=FACC15)](https://aka.ms/GitHubCopilotAI?WT.mc_id=academic-105485-koreyst) [![Copilot til C#/.NET](https://img.shields.io/badge/Copilot%20for%20C%23/.NET-FBBF24?style=for-the-badge&labelColor=E5E7EB&color=FBBF24)](https://github.com/microsoft/mastering-github-copilot-for-dotnet-csharp-developers?WT.mc_id=academic-105485-koreyst) -[![Copilot Adventure](https://img.shields.io/badge/Copilot%20Adventure-FDE68A?style=for-the-badge&labelColor=E5E7EB&color=FDE68A)](https://github.com/microsoft/CopilotAdventures?WT.mc_id=academic-105485-koreyst) +[![Copilot-eventyr](https://img.shields.io/badge/Copilot%20Adventure-FDE68A?style=for-the-badge&labelColor=E5E7EB&color=FDE68A)](https://github.com/microsoft/CopilotAdventures?WT.mc_id=academic-105485-koreyst) ## Få hjælp -Hvis du sidder fast eller har spørgsmål om at udvikle AI-apps, så slut dig til andre lærende og erfarne udviklere i diskussioner om MCP. Det er et støttende fællesskab, hvor spørgsmål er velkomne, og viden deles frit. +Hvis du sidder fast eller har spørgsmål om at bygge AI-apps, så deltag i diskussioner om MCP sammen med andre lærende og erfarne udviklere. Det er et støttende fællesskab, hvor spørgsmål er velkomne, og viden deles frit. [![Microsoft Foundry Discord](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) Hvis du har produktfeedback eller oplever fejl under udviklingen, besøg: -[![Microsoft Foundry Developer Forum](https://img.shields.io/badge/GitHub-Microsoft_Foundry_Developer_Forum-blue?style=for-the-badge&logo=github&color=000000&logoColor=fff)](https://aka.ms/foundry/forum) +[![Microsoft Foundry udviklerforum](https://img.shields.io/badge/GitHub-Microsoft_Foundry_Developer_Forum-blue?style=for-the-badge&logo=github&color=000000&logoColor=fff)](https://aka.ms/foundry/forum) --- Ansvarsfraskrivelse: -Dette dokument er blevet oversat ved hjælp af AI-oversættelsestjenesten [Co-op Translator](https://github.com/Azure/co-op-translator). Selvom vi stræber efter nøjagtighed, skal du være opmærksom på, at automatiske oversættelser kan indeholde fejl eller unøjagtigheder. Det oprindelige dokument på dets modersmål bør betragtes som den autoritative kilde. For kritiske oplysninger anbefales en professionel menneskelig oversættelse. Vi påtager os intet ansvar for misforståelser eller fejltolkninger, der opstår som følge af brugen af denne oversættelse. +Dette dokument er blevet oversat ved hjælp af AI-oversættelsestjenesten [Co-op Translator](https://github.com/Azure/co-op-translator). Selvom vi bestræber os på nøjagtighed, skal du være opmærksom på, at automatiske oversættelser kan indeholde fejl eller unøjagtigheder. Det oprindelige dokument i dets oprindelige sprog bør betragtes som den autoritative kilde. For kritiske oplysninger anbefales professionel, menneskelig oversættelse. Vi er ikke ansvarlige for eventuelle misforståelser eller fejltolkninger, der opstår som følge af brugen af denne oversættelse. \ No newline at end of file diff --git a/translations/de/1-Introduction/README.md b/translations/de/1-Introduction/README.md index 06abe04d8..f6c3d3fd8 100644 --- a/translations/de/1-Introduction/README.md +++ b/translations/de/1-Introduction/README.md @@ -11,7 +11,7 @@ CO_OP_TRANSLATOR_METADATA: In diesem Abschnitt des Lehrplans werden Sie mit den grundlegenden Konzepten des maschinellen Lernens vertraut gemacht, erfahren, was es ist, und etwas über seine Geschichte sowie die Techniken lernen, die Forscher verwenden, um damit zu arbeiten. Lassen Sie uns diese neue Welt des maschinellen Lernens gemeinsam erkunden! -![globe](../../../translated_images/globe.59f26379ceb40428672b4d9a568044618a2bf6292ecd53a5c481b90e3fa805eb.de.jpg) +![globe](../../../translated_images/globe.59f26379ceb40428.de.jpg) > Foto von Bill Oxford auf Unsplash ### Lektionen diff --git a/translations/de/2-Regression/1-Tools/solution/R/lesson_1-R.ipynb b/translations/de/2-Regression/1-Tools/solution/R/lesson_1-R.ipynb index a5004d712..2a60acaa1 100644 --- a/translations/de/2-Regression/1-Tools/solution/R/lesson_1-R.ipynb +++ b/translations/de/2-Regression/1-Tools/solution/R/lesson_1-R.ipynb @@ -48,7 +48,7 @@ " width=\"630\"/>\n", "
Kunstwerk von @allison_horst
\n", "\n", - "\n" + "\n" ], "metadata": { "id": "LWNNzfqd6feZ" diff --git a/translations/de/2-Regression/2-Data/solution/R/lesson_2-R.ipynb b/translations/de/2-Regression/2-Data/solution/R/lesson_2-R.ipynb index b4f64b3cc..9a8bb6d6d 100644 --- a/translations/de/2-Regression/2-Data/solution/R/lesson_2-R.ipynb +++ b/translations/de/2-Regression/2-Data/solution/R/lesson_2-R.ipynb @@ -49,7 +49,7 @@ "
Kunstwerk von @allison_horst
\n", "\n", "\n", - "\n" + "\n" ], "metadata": { "id": "Pg5aexcOPqAZ" @@ -230,7 +230,7 @@ "
Illustration von @allison_horst
\n", "\n", "\n", - "\n" + "\n" ], "metadata": { "id": "o4jLY5-VZO2C" @@ -536,7 +536,7 @@ "
Infografik von Dasani Madipalli
\n", "\n", "\n", - "\n", + "\n", "\n", "Es gibt ein *weises* Sprichwort, das so lautet:\n", "\n", diff --git a/translations/de/2-Regression/3-Linear/solution/R/lesson_3-R.ipynb b/translations/de/2-Regression/3-Linear/solution/R/lesson_3-R.ipynb index f4caacab7..c803ab8e7 100644 --- a/translations/de/2-Regression/3-Linear/solution/R/lesson_3-R.ipynb +++ b/translations/de/2-Regression/3-Linear/solution/R/lesson_3-R.ipynb @@ -162,7 +162,7 @@ "
Kunstwerk von @allison_horst
\n", "\n", "\n", - "\n" + "\n" ], "metadata": { "id": "WdUKXk7Bs8-V" @@ -567,7 +567,7 @@ "
Infografik von Dasani Madipalli
\n", "\n", "\n", - "\n" + "\n" ], "metadata": { "id": "YqXjLuWavNxW" @@ -808,7 +808,7 @@ "
Infografik von Dasani Madipalli
\n", "\n", "\n", - "\n" + "\n" ], "metadata": { "id": "HOCqJXLTwtWI" diff --git a/translations/de/2-Regression/4-Logistic/solution/R/lesson_4-R.ipynb b/translations/de/2-Regression/4-Logistic/solution/R/lesson_4-R.ipynb index 27a5fb19c..419cffa22 100644 --- a/translations/de/2-Regression/4-Logistic/solution/R/lesson_4-R.ipynb +++ b/translations/de/2-Regression/4-Logistic/solution/R/lesson_4-R.ipynb @@ -6,7 +6,7 @@ "source": [ "## Erstellen Sie ein logistisches Regressionsmodell - Lektion 4\n", "\n", - "![Infografik: Logistische vs. lineare Regression](../../../../../../translated_images/linear-vs-logistic.ba180bf95e7ee66721ba10ebf2dac2666acbd64a88b003c83928712433a13c7d.de.png)\n", + "![Infografik: Logistische vs. lineare Regression](../../../../../../translated_images/linear-vs-logistic.ba180bf95e7ee667.de.png)\n", "\n", "#### **[Quiz vor der Vorlesung](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/15/)**\n", "\n", @@ -78,7 +78,7 @@ "\n", "Die logistische Regression bietet nicht die gleichen Funktionen wie die lineare Regression. Erstere liefert eine Vorhersage über eine `binäre Kategorie` (\"orange oder nicht orange\"), während letztere in der Lage ist, `kontinuierliche Werte` vorherzusagen, zum Beispiel basierend auf der Herkunft eines Kürbisses und der Erntezeit, *wie stark sein Preis steigen wird*.\n", "\n", - "![Infografik von Dasani Madipalli](../../../../../../translated_images/pumpkin-classifier.562771f104ad5436b87d1c67bca02a42a17841133556559325c0a0e348e5b774.de.png)\n", + "![Infografik von Dasani Madipalli](../../../../../../translated_images/pumpkin-classifier.562771f104ad5436.de.png)\n", "\n", "### Andere Klassifikationen\n", "\n", @@ -88,7 +88,7 @@ "\n", "- **Ordinal**, bei der geordnete Kategorien verwendet werden, nützlich, wenn wir unsere Ergebnisse logisch ordnen möchten, wie unsere Kürbisse, die nach einer begrenzten Anzahl von Größen geordnet sind (mini, sm, med, lg, xl, xxl).\n", "\n", - "![Multinomiale vs ordinale Regression](../../../../../../translated_images/multinomial-vs-ordinal.36701b4850e37d86c9dd49f7bef93a2f94dbdb8fe03443eb68f0542f97f28f29.de.png)\n", + "![Multinomiale vs ordinale Regression](../../../../../../translated_images/multinomial-vs-ordinal.36701b4850e37d86.de.png)\n", "\n", "#### **Variablen MÜSSEN NICHT korrelieren**\n", "\n", diff --git a/translations/de/2-Regression/README.md b/translations/de/2-Regression/README.md index 65ffa8c5f..74d776508 100644 --- a/translations/de/2-Regression/README.md +++ b/translations/de/2-Regression/README.md @@ -12,7 +12,7 @@ CO_OP_TRANSLATOR_METADATA: In Nordamerika werden Kürbisse oft zu Halloween in gruselige Gesichter geschnitzt. Lassen Sie uns mehr über dieses faszinierende Gemüse herausfinden! -![jack-o-lanterns](../../../translated_images/jack-o-lanterns.181c661a9212457d7756f37219f660f1358af27554d856e5a991f16b4e15337c.de.jpg) +![jack-o-lanterns](../../../translated_images/jack-o-lanterns.181c661a9212457d.de.jpg) > Foto von Beth Teutschmann auf Unsplash ## Was Sie lernen werden diff --git a/translations/de/3-Web-App/README.md b/translations/de/3-Web-App/README.md index 7aa06731b..b78c0eb58 100644 --- a/translations/de/3-Web-App/README.md +++ b/translations/de/3-Web-App/README.md @@ -11,7 +11,7 @@ CO_OP_TRANSLATOR_METADATA: In diesem Abschnitt des Lehrplans werden Sie mit einem angewandten ML-Thema vertraut gemacht: wie Sie Ihr Scikit-learn-Modell als Datei speichern können, die innerhalb einer Webanwendung für Vorhersagen verwendet werden kann. Sobald das Modell gespeichert ist, lernen Sie, wie Sie es in einer Web-App verwenden, die mit Flask erstellt wurde. Zunächst erstellen Sie ein Modell mit Daten, die sich mit UFO-Sichtungen befassen! Anschließend entwickeln Sie eine Web-App, die es ermöglicht, eine Anzahl von Sekunden zusammen mit einem Breitengrad- und Längengradwert einzugeben, um vorherzusagen, welches Land eine UFO-Sichtung gemeldet hat. -![UFO-Parkplatz](../../../translated_images/ufo.9e787f5161da9d4d1dafc537e1da09be8210f2ee996cb638aa5cee1d92867a04.de.jpg) +![UFO-Parkplatz](../../../translated_images/ufo.9e787f5161da9d4d.de.jpg) Foto von Michael Herren auf Unsplash diff --git a/translations/de/4-Classification/README.md b/translations/de/4-Classification/README.md index 176f6a337..5e249b326 100644 --- a/translations/de/4-Classification/README.md +++ b/translations/de/4-Classification/README.md @@ -13,7 +13,7 @@ CO_OP_TRANSLATOR_METADATA: In Asien und Indien sind die Essensgewohnheiten äußerst vielfältig und sehr lecker! Schauen wir uns Daten über regionale Küchen an, um ihre Zutaten besser zu verstehen. -![Thai-Essen-Verkäufer](../../../translated_images/thai-food.c47a7a7f9f05c21892a1f9dc7bf30669e6d18dfda420c5c7ebb4153f6a304edd.de.jpg) +![Thai-Essen-Verkäufer](../../../translated_images/thai-food.c47a7a7f9f05c218.de.jpg) > Foto von Lisheng Chang auf Unsplash ## Was Sie lernen werden diff --git a/translations/de/5-Clustering/README.md b/translations/de/5-Clustering/README.md index f0b183fb0..d0c04c065 100644 --- a/translations/de/5-Clustering/README.md +++ b/translations/de/5-Clustering/README.md @@ -15,7 +15,7 @@ Clustering ist eine Aufgabe des maschinellen Lernens, bei der versucht wird, Obj Das vielfältige Publikum in Nigeria hat ebenso vielfältige musikalische Vorlieben. Mithilfe von Daten, die von Spotify gesammelt wurden (inspiriert von [diesem Artikel](https://towardsdatascience.com/country-wise-visual-analysis-of-music-taste-using-spotify-api-seaborn-in-python-77f5b749b421)), werfen wir einen Blick auf einige beliebte Musikstücke in Nigeria. Dieses Datenset enthält Informationen über verschiedene Songs, wie deren 'Danceability'-Score, 'Acousticness', Lautstärke, 'Speechiness', Popularität und Energie. Es wird spannend sein, Muster in diesen Daten zu entdecken! -![Ein Plattenspieler](../../../translated_images/turntable.f2b86b13c53302dc106aa741de9dc96ac372864cf458dd6f879119857aab01da.de.jpg) +![Ein Plattenspieler](../../../translated_images/turntable.f2b86b13c53302dc.de.jpg) > Foto von Marcela Laskoski auf Unsplash diff --git a/translations/de/6-NLP/README.md b/translations/de/6-NLP/README.md index 26191d1d7..8df6f91a9 100644 --- a/translations/de/6-NLP/README.md +++ b/translations/de/6-NLP/README.md @@ -17,7 +17,7 @@ In diesem Abschnitt des Lehrplans wirst du in eine der am weitesten verbreiteten In diesen Lektionen lernen wir die Grundlagen von NLP, indem wir kleine Konversationsbots erstellen, um zu verstehen, wie maschinelles Lernen dazu beiträgt, diese Gespräche immer „intelligenter“ zu machen. Du wirst in der Zeit zurückreisen und mit Elizabeth Bennett und Mr. Darcy aus Jane Austens klassischem Roman **Stolz und Vorurteil**, veröffentlicht im Jahr 1813, chatten. Anschließend vertiefst du dein Wissen, indem du mehr über Sentiment-Analyse anhand von Hotelbewertungen in Europa lernst. -![Stolz und Vorurteil Buch und Tee](../../../translated_images/p&p.279f1c49ecd889419e4ce6206525e9aa30d32a976955cd24daa636c361c6391f.de.jpg) +![Stolz und Vorurteil Buch und Tee](../../../translated_images/p&p.279f1c49ecd88941.de.jpg) > Foto von Elaine Howlin auf Unsplash ## Lektionen diff --git a/translations/de/7-TimeSeries/README.md b/translations/de/7-TimeSeries/README.md index 238247aaa..02ae68ea9 100644 --- a/translations/de/7-TimeSeries/README.md +++ b/translations/de/7-TimeSeries/README.md @@ -17,7 +17,7 @@ In diesen zwei Lektionen wirst du in die Zeitreihenprognose eingeführt, ein etw Unser regionaler Fokus liegt auf dem weltweiten Stromverbrauch, einem interessanten Datensatz, um zu lernen, wie man den zukünftigen Energieverbrauch basierend auf Mustern der vergangenen Last vorhersagen kann. Du wirst sehen, wie diese Art der Prognose in einem geschäftlichen Umfeld äußerst hilfreich sein kann. -![Stromnetz](../../../translated_images/electric-grid.0c21d5214db09ffae93c06a87ca2abbb9ba7475ef815129c5b423d7f9a7cf136.de.jpg) +![Stromnetz](../../../translated_images/electric-grid.0c21d5214db09ffa.de.jpg) Foto von [Peddi Sai hrithik](https://unsplash.com/@shutter_log?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText) von Strommasten auf einer Straße in Rajasthan auf [Unsplash](https://unsplash.com/s/photos/electric-india?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText) diff --git a/translations/de/8-Reinforcement/README.md b/translations/de/8-Reinforcement/README.md index 61a5fb20e..883edc776 100644 --- a/translations/de/8-Reinforcement/README.md +++ b/translations/de/8-Reinforcement/README.md @@ -13,7 +13,7 @@ Reinforcement Learning, RL, wird als eines der grundlegenden Paradigmen des masc Stellen Sie sich vor, Sie haben eine simulierte Umgebung wie den Aktienmarkt. Was passiert, wenn Sie eine bestimmte Regulierung einführen? Hat dies eine positive oder negative Wirkung? Wenn etwas Negatives passiert, müssen Sie diese _negative Verstärkung_ nutzen, daraus lernen und den Kurs ändern. Wenn es ein positives Ergebnis ist, müssen Sie darauf aufbauen und die _positive Verstärkung_ nutzen. -![Peter und der Wolf](../../../translated_images/peter.779730f9ba3a8a8d9290600dcf55f2e491c0640c785af7ac0d64f583c49b8864.de.png) +![Peter und der Wolf](../../../translated_images/peter.779730f9ba3a8a8d.de.png) > Peter und seine Freunde müssen dem hungrigen Wolf entkommen! Bild von [Jen Looper](https://twitter.com/jenlooper) diff --git a/translations/de/9-Real-World/README.md b/translations/de/9-Real-World/README.md index bedd52b89..cac0010da 100644 --- a/translations/de/9-Real-World/README.md +++ b/translations/de/9-Real-World/README.md @@ -11,7 +11,7 @@ CO_OP_TRANSLATOR_METADATA: In diesem Abschnitt des Lehrplans werden Sie mit einigen realen Anwendungen des klassischen maschinellen Lernens vertraut gemacht. Wir haben das Internet durchforstet, um Whitepapers und Artikel über Anwendungen zu finden, die diese Strategien genutzt haben, und dabei neuralen Netzwerken, Deep Learning und KI so weit wie möglich vermieden. Erfahren Sie, wie maschinelles Lernen in Geschäftssystemen, ökologischen Anwendungen, Finanzen, Kunst und Kultur und mehr eingesetzt wird. -![chess](../../../translated_images/chess.e704a268781bdad85d1876b6c2295742fa0d856e7dcf3659147052df9d3db205.de.jpg) +![chess](../../../translated_images/chess.e704a268781bdad8.de.jpg) > Foto von Alexis Fauvet auf Unsplash diff --git a/translations/de/README.md b/translations/de/README.md index 67ceb2bee..cbcab30f2 100644 --- a/translations/de/README.md +++ b/translations/de/README.md @@ -1,8 +1,8 @@ -[Arabisch](../ar/README.md) | [Bengalisch](../bn/README.md) | [Bulgarisch](../bg/README.md) | [Birmanisch (Myanmar)](../my/README.md) | [Chinesisch (vereinfacht)](../zh/README.md) | [Chinesisch (traditionell, Hongkong)](../hk/README.md) | [Chinesisch (traditionell, Macau)](../mo/README.md) | [Chinesisch (traditionell, Taiwan)](../tw/README.md) | [Kroatisch](../hr/README.md) | [Tschechisch](../cs/README.md) | [Dänisch](../da/README.md) | [Niederländisch](../nl/README.md) | [Estnisch](../et/README.md) | [Finnisch](../fi/README.md) | [Französisch](../fr/README.md) | [Deutsch](./README.md) | [Griechisch](../el/README.md) | [Hebräisch](../he/README.md) | [Hindi](../hi/README.md) | [Ungarisch](../hu/README.md) | [Indonesisch](../id/README.md) | [Italienisch](../it/README.md) | [Japanisch](../ja/README.md) | [Kannada](../kn/README.md) | [Koreanisch](../ko/README.md) | [Litauisch](../lt/README.md) | [Malaiisch](../ms/README.md) | [Malayalam](../ml/README.md) | [Marathi](../mr/README.md) | [Nepalesisch](../ne/README.md) | [Nigerianisches Pidgin](../pcm/README.md) | [Norwegisch](../no/README.md) | [Persisch (Farsi)](../fa/README.md) | [Polnisch](../pl/README.md) | [Portugiesisch (Brasilien)](../br/README.md) | [Portugiesisch (Portugal)](../pt/README.md) | [Punjabi (Gurmukhi)](../pa/README.md) | [Rumänisch](../ro/README.md) | [Russisch](../ru/README.md) | [Serbisch (Kyrillisch)](../sr/README.md) | [Slowakisch](../sk/README.md) | [Slowenisch](../sl/README.md) | [Spanisch](../es/README.md) | [Swahili](../sw/README.md) | [Schwedisch](../sv/README.md) | [Tagalog (Filipino)](../tl/README.md) | [Tamil](../ta/README.md) | [Telugu](../te/README.md) | [Thai](../th/README.md) | [Türkisch](../tr/README.md) | [Ukrainisch](../uk/README.md) | [Urdu](../ur/README.md) | [Vietnamesisch](../vi/README.md) +[Arabic](../ar/README.md) | [Bengali](../bn/README.md) | [Bulgarian](../bg/README.md) | [Burmese (Myanmar)](../my/README.md) | [Chinese (Simplified)](../zh/README.md) | [Chinese (Traditional, Hong Kong)](../hk/README.md) | [Chinese (Traditional, Macau)](../mo/README.md) | [Chinese (Traditional, Taiwan)](../tw/README.md) | [Croatian](../hr/README.md) | [Czech](../cs/README.md) | [Danish](../da/README.md) | [Dutch](../nl/README.md) | [Estonian](../et/README.md) | [Finnish](../fi/README.md) | [French](../fr/README.md) | [German](./README.md) | [Greek](../el/README.md) | [Hebrew](../he/README.md) | [Hindi](../hi/README.md) | [Hungarian](../hu/README.md) | [Indonesian](../id/README.md) | [Italian](../it/README.md) | [Japanese](../ja/README.md) | [Kannada](../kn/README.md) | [Korean](../ko/README.md) | [Lithuanian](../lt/README.md) | [Malay](../ms/README.md) | [Malayalam](../ml/README.md) | [Marathi](../mr/README.md) | [Nepali](../ne/README.md) | [Nigerian Pidgin](../pcm/README.md) | [Norwegian](../no/README.md) | [Persian (Farsi)](../fa/README.md) | [Polish](../pl/README.md) | [Portuguese (Brazil)](../br/README.md) | [Portuguese (Portugal)](../pt/README.md) | [Punjabi (Gurmukhi)](../pa/README.md) | [Romanian](../ro/README.md) | [Russian](../ru/README.md) | [Serbian (Cyrillic)](../sr/README.md) | [Slovak](../sk/README.md) | [Slovenian](../sl/README.md) | [Spanish](../es/README.md) | [Swahili](../sw/README.md) | [Swedish](../sv/README.md) | [Tagalog (Filipino)](../tl/README.md) | [Tamil](../ta/README.md) | [Telugu](../te/README.md) | [Thai](../th/README.md) | [Turkish](../tr/README.md) | [Ukrainian](../uk/README.md) | [Urdu](../ur/README.md) | [Vietnamese](../vi/README.md) -#### Tritt unserer Community bei +#### Treten Sie unserer Community bei [![Microsoft Foundry Discord](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) -Wir haben eine laufende Discord-Lernreihe "Learn with AI" — erfahre mehr und schließe dich uns an unter [Learn-with-AI-Reihe](https://aka.ms/learnwithai/discord) vom 18. bis 30. September 2025. Du erhältst Tipps und Tricks zur Verwendung von GitHub Copilot für Data Science. +Wir veranstalten eine Discord-Reihe "Learn with AI", erfahren Sie mehr und machen Sie mit unter [Learn with AI Series](https://aka.ms/learnwithai/discord) vom 18. bis 30. September 2025. Sie erhalten Tipps und Tricks zur Verwendung von GitHub Copilot für Data Science. -![Learn-with-AI-Reihe](../../translated_images/3.9b58fd8d6c373c20c588c5070c4948a826ab074426c28ceb5889641294373dfc.de.png) +![Learn with AI-Serie](../../translated_images/3.9b58fd8d6c373c20.de.png) -# Maschinelles Lernen für Anfänger - Ein Lehrplan +# Maschinelles Lernen für Einsteiger - Ein Lehrplan -> 🌍 Reise um die Welt, während wir Maschinelles Lernen anhand weltweiter Kulturen erkunden 🌍 +> 🌍 Reisen Sie um die Welt, während wir Maschinelles Lernen anhand von Weltkulturen erkunden 🌍 -Cloud Advocates bei Microsoft freuen sich, ein 12-wöchiges Curriculum mit 26 Lektionen rund um das Thema **Maschinelles Lernen** anzubieten. In diesem Curriculum lernst du, was manchmal als **klassisches Machine Learning** bezeichnet wird, wobei hauptsächlich Scikit-learn als Bibliothek verwendet wird und Deep Learning vermieden wird (Deep Learning wird in unserem [AI for Beginners'-Curriculum](https://aka.ms/ai4beginners) behandelt). Kombiniere diese Lektionen auch mit unserem ['Data Science for Beginners'-Curriculum](https://aka.ms/ds4beginners)! +Die Cloud Advocates bei Microsoft freuen sich, einen 12-wöchigen, 26-teiligen Lehrplan rund um das Thema **Maschinelles Lernen** anzubieten. In diesem Lehrplan lernen Sie das, was man manchmal als **klassisches Machine Learning** bezeichnet, hauptsächlich unter Verwendung von Scikit-learn als Bibliothek; Deep Learning wird in unserem [AI for Beginners' curriculum](https://aka.ms/ai4beginners) behandelt. Kombinieren Sie diese Lektionen auch mit unserem ['Data Science for Beginners' curriculum](https://aka.ms/ds4beginners)! -Reise mit uns um die Welt, während wir diese klassischen Techniken auf Daten aus vielen Regionen anwenden. Jede Lektion enthält Vor- und Nach-Lektions-Quiz, schriftliche Anleitungen zur Durchführung der Lektion, eine Lösung, eine Aufgabe und mehr. Unsere projektbasierte Pädagogik ermöglicht es dir, beim Bauen zu lernen — eine bewährte Methode, damit neue Fähigkeiten 'haften bleiben'. +Reisen Sie mit uns um die Welt, während wir diese klassischen Techniken auf Daten aus vielen Regionen anwenden. Jede Lektion enthält Vor- und Nach-Quizze, schriftliche Anleitungen zur Durchführung der Lektion, eine Lösung, eine Aufgabe und mehr. Unsere projektbasierte Didaktik ermöglicht Lernen durch Bauen — eine bewährte Methode, damit neue Fähigkeiten "haften bleiben". **✍️ Herzlichen Dank an unsere Autorinnen und Autoren** Jen Looper, Stephen Howell, Francesca Lazzeri, Tomomi Imura, Cassie Breviu, Dmitry Soshnikov, Chris Noring, Anirban Mukherjee, Ornella Altunyan, Ruth Yakubu und Amy Boyd -**🎨 Vielen Dank auch an unsere Illustratoren** Tomomi Imura, Dasani Madipalli und Jen Looper +**🎨 Ebenfalls Dank an unsere Illustratoren** Tomomi Imura, Dasani Madipalli und Jen Looper -**🙏 Besonderer Dank 🙏 an unsere Microsoft Student Ambassador-Autorinnen, -Reviewer und Inhaltsbeitragenden**, insbesondere Rishit Dagli, Muhammad Sakib Khan Inan, Rohan Raj, Alexandru Petrescu, Abhishek Jaiswal, Nawrin Tabassum, Ioan Samuila und Snigdha Agarwal +**🙏 Besonderer Dank 🙏 an unsere Microsoft Student Ambassador-Autorinnen und -Autoren, Reviewer und Inhaltsbeiträger**, namentlich Rishit Dagli, Muhammad Sakib Khan Inan, Rohan Raj, Alexandru Petrescu, Abhishek Jaiswal, Nawrin Tabassum, Ioan Samuila und Snigdha Agarwal **🤩 Extra-Dank an die Microsoft Student Ambassadors Eric Wanjau, Jasleen Sondhi und Vidushi Gupta für unsere R-Lektionen!** # Erste Schritte -Befolge diese Schritte: -1. **Forke das Repository**: Klicke auf die "Fork"-Schaltfläche oben rechts auf dieser Seite. -2. **Repository klonen**: `git clone https://github.com/microsoft/ML-For-Beginners.git` +Befolgen Sie diese Schritte: +1. **Forken Sie das Repository**: Klicken Sie auf die Schaltfläche "Fork" oben rechts auf dieser Seite. +2. **Klonen Sie das Repository**: `git clone https://github.com/microsoft/ML-For-Beginners.git` -> [Finde alle zusätzlichen Ressourcen für diesen Kurs in unserer Microsoft Learn-Sammlung](https://learn.microsoft.com/en-us/collections/qrqzamz1nn2wx3?WT.mc_id=academic-77952-bethanycheum) +> [finden Sie alle zusätzlichen Ressourcen für diesen Kurs in unserer Microsoft Learn-Sammlung](https://learn.microsoft.com/en-us/collections/qrqzamz1nn2wx3?WT.mc_id=academic-77952-bethanycheum) -> 🔧 **Brauchst du Hilfe?** Sieh dir unseren [Troubleshooting Guide](TROUBLESHOOTING.md) an für Lösungen zu häufigen Problemen bei Installation, Einrichtung und Ausführung der Lektionen. +> 🔧 **Brauchen Sie Hilfe?** Sehen Sie in unserer [Fehlerbehebungsanleitung](TROUBLESHOOTING.md) nach Lösungen für häufige Probleme bei Installation, Einrichtung und dem Ausführen von Lektionen. -**[Studierende](https://aka.ms/student-page)**, um dieses Curriculum zu nutzen, forke das gesamte Repo in dein eigenes GitHub-Konto und bearbeite die Übungen alleine oder in einer Gruppe: +**[Studierende](https://aka.ms/student-page)**, um dieses Curriculum zu nutzen, forken Sie das gesamte Repo in Ihr eigenes GitHub-Konto und bearbeiten Sie die Übungen allein oder in einer Gruppe: -- Beginne mit einem Pre-Lecture-Aufwärmquiz. -- Lies die Lektion und führe die Aktivitäten aus; halte bei jedem Wissenscheck inne und reflektiere. -- Versuche, die Projekte durch Verständnis der Lektionen zu erstellen, anstatt direkt den Lösungscode auszuführen; dieser Code ist jedoch in den `/solution`-Ordnern jeder projektorientierten Lektion verfügbar. -- Mache das Post-Lecture-Quiz. -- Schließe die Challenge ab. -- Erledige die Aufgabe. -- Nachdem du eine Lektion abgeschlossen hast, besuche das [Discussion Board](https://github.com/microsoft/ML-For-Beginners/discussions) und "learn out loud", indem du das entsprechende PAT-Rubric ausfüllst. Ein 'PAT' ist ein Progress Assessment Tool — ein Rubric, das du ausfüllst, um dein Lernen weiterzuführen. Du kannst auch auf andere PATs reagieren, damit wir gemeinsam lernen. +- Beginnen Sie mit einem Quiz vor der Vorlesung. +- Lesen Sie die Vorlesung und führen Sie die Aktivitäten durch, halten Sie bei jeder Wissensüberprüfung inne und reflektieren Sie. +- Versuchen Sie, die Projekte durch das Verständnis der Lektionen zu erstellen, anstatt den Lösungscode auszuführen; dieser Code ist jedoch in den `/solution`-Ordnern jeder projektorientierten Lektion verfügbar. +- Machen Sie das Quiz nach der Vorlesung. +- Schließen Sie die Challenge ab. +- Bearbeiten Sie die Aufgabe. +- Nach Abschluss einer Lektionsgruppe besuchen Sie das [Diskussionsforum](https://github.com/microsoft/ML-For-Beginners/discussions) und "lernen Sie laut", indem Sie die entsprechende PAT-Rubrik ausfüllen. Ein 'PAT' ist ein Progress Assessment Tool, eine Bewertungsrubrik, die Sie ausfüllen, um Ihr Lernen zu fördern. Sie können auch auf andere PATs reagieren, damit wir gemeinsam lernen. -> Für weiterführende Studien empfehlen wir, diesen [Microsoft Learn](https://docs.microsoft.com/en-us/users/jenlooper-2911/collections/k7o7tg1gp306q4?WT.mc_id=academic-77952-leestott) Modulen und Lernpfaden zu folgen. +> Für weiterführendes Studium empfehlen wir das Durcharbeiten dieser [Microsoft Learn](https://docs.microsoft.com/en-us/users/jenlooper-2911/collections/k7o7tg1gp306q4?WT.mc_id=academic-77952-leestott) Module und Lernpfade. -**Lehrkräfte**, wir haben [einige Vorschläge aufgenommen](for-teachers.md), wie dieses Curriculum eingesetzt werden kann. +**Lehrkräfte**, wir haben [einige Vorschläge](for-teachers.md) zur Nutzung dieses Curriculums beigefügt. --- ## Video-Anleitungen -Einige der Lektionen sind als Kurzvideos verfügbar. Du findest alle diese Videos in den Lektionen eingebettet oder in der [ML for Beginners-Playlist auf dem Microsoft Developer YouTube-Kanal](https://aka.ms/ml-beginners-videos), indem du auf das Bild unten klickst. +Einige Lektionen sind als Kurzvideos verfügbar. Sie können alle diese inline in den Lektionen finden oder auf der [ML for Beginners-Playlist auf dem Microsoft Developer YouTube-Kanal](https://aka.ms/ml-beginners-videos), indem Sie auf das Bild unten klicken. -[![ML für Anfänger-Banner](../../translated_images/ml-for-beginners-video-banner.63f694a100034bc6251134294459696e070a3a9a04632e9fe6a24aa0de4a7384.de.png)](https://aka.ms/ml-beginners-videos) +[![ML for beginners Banner](../../translated_images/ml-for-beginners-video-banner.63f694a100034bc6.de.png)](https://aka.ms/ml-beginners-videos) --- -## Das Team kennenlernen +## Treffen Sie das Team [![Promo-Video](../../images/ml.gif)](https://youtu.be/Tj1XWrDSYJU) **Gif von** [Mohit Jaisal](https://linkedin.com/in/mohitjaisal) -> 🎥 Klicke auf das Bild oben für ein Video über das Projekt und die Personen, die es erstellt haben! +> 🎥 Klicken Sie auf das obige Bild für ein Video über das Projekt und die Personen, die es erstellt haben! --- ## Pädagogik -Wir haben beim Aufbau dieses Curriculums zwei pädagogische Grundsätze gewählt: sicherstellen, dass es praxisorientiert und projektbasiert ist, und dass es **häufige Quizze** beinhaltet. Zusätzlich hat dieses Curriculum ein gemeinsames **Thema**, um ihm Kohärenz zu verleihen. +Wir haben beim Aufbau dieses Lehrplans zwei pädagogische Grundsätze gewählt: sicherstellen, dass er praxisnah **projektbasiert** ist und dass er **häufige Quizze** enthält. Darüber hinaus hat dieser Lehrplan ein gemeinsames **Thema**, das ihm Kohärenz verleiht. -Indem der Inhalt auf Projekte ausgerichtet ist, wird der Prozess für Lernende ansprechender und das Behalten der Konzepte wird gefördert. Ein niedrigschwelliges Quiz vor der Unterrichtseinheit setzt die Intention der Lernenden auf ein Thema, während ein zweites Quiz nach dem Unterricht die weitere Beibehaltung des Wissens unterstützt. Dieses Curriculum wurde flexibel und unterhaltsam gestaltet und kann ganz oder teilweise absolviert werden. Die Projekte beginnen klein und werden bis zum Ende des 12-Wochen-Zyklus zunehmend komplexer. Dieses Curriculum enthält außerdem ein Nachwort zu realen Anwendungen von ML, das als Bonuspunkte oder als Grundlage für Diskussionen verwendet werden kann. +Indem die Inhalte an Projekte angelehnt sind, wird der Prozess für Lernende engagierender und das Behalten von Konzepten wird gesteigert. Ein niedrigschwelliges Quiz vor einer Unterrichtseinheit setzt zudem die Lernintention der Teilnehmenden, während ein zweites Quiz nach der Einheit die weitere Behaltensleistung sichert. Dieser Lehrplan wurde so gestaltet, dass er flexibel und unterhaltsam ist und vollständig oder teilweise durchlaufen werden kann. Die Projekte beginnen klein und werden bis zum Ende des 12-wöchigen Zyklus zunehmend komplexer. Dieser Lehrplan enthält außerdem ein Nachwort zu realen Anwendungen von ML, das als Bonuspunkte oder als Grundlage für Diskussionen genutzt werden kann. -> Finde unseren [Code of Conduct](CODE_OF_CONDUCT.md), [Contributing](CONTRIBUTING.md), [Translation](TRANSLATIONS.md) und [Troubleshooting](TROUBLESHOOTING.md) Richtlinien. Wir freuen uns über dein konstruktives Feedback! +> Finden Sie unseren [Verhaltenskodex](CODE_OF_CONDUCT.md), [Beitragen](CONTRIBUTING.md), [Übersetzung](TRANSLATIONS.md) und [Fehlerbehebung](TROUBLESHOOTING.md) Leitfäden. Wir freuen uns über Ihr konstruktives Feedback! ## Jede Lektion enthält - optionale Sketchnote - optionales ergänzendes Video -- Video-Anleitung (nur einige Lektionen) -- [Pre-Lecture-Aufwärmquiz](https://ff-quizzes.netlify.app/en/ml/) +- Videoanleitung (nur einige Lektionen) +- [Aufwärmquiz vor der Vorlesung](https://ff-quizzes.netlify.app/en/ml/) - schriftliche Lektion -- für projektbasierte Lektionen: Schritt-für-Schritt-Anleitungen zum Erstellen des Projekts +- für projektbasierte Lektionen schrittweise Anleitungen zum Aufbau des Projekts - Wissenschecks -- eine Challenge +- eine Herausforderung - ergänzende Lektüre - Aufgabe -- [Post-Lecture-Quiz](https://ff-quizzes.netlify.app/en/ml/) +- [Quiz nach der Vorlesung](https://ff-quizzes.netlify.app/en/ml/) -> **Ein Hinweis zu Sprachen**: Diese Lektionen sind hauptsächlich in Python verfasst, viele sind jedoch auch in R verfügbar. Um eine R-Lektion zu bearbeiten, gehe in den `/solution`-Ordner und suche nach R-Lektionen. Sie enthalten eine .rmd-Erweiterung, die eine **R Markdown**-Datei darstellt, die einfach als Einbettung von `code chunks` (in R oder anderen Sprachen) und einem `YAML header` (der steuert, wie Ausgaben wie PDF formatiert werden) in einem `Markdown document` definiert werden kann. Als solche dient sie als beispielhaftes Autoren-Framework für Data Science, da sie es erlaubt, deinen Code, dessen Ausgabe und deine Gedanken zu kombinieren, indem du sie in Markdown niederschreibst. Darüber hinaus können R Markdown-Dokumente in Ausgabeformate wie PDF, HTML oder Word gerendert werden. +> **Eine Anmerkung zu Programmiersprachen**: Diese Lektionen sind hauptsächlich in Python geschrieben, aber viele sind auch in R verfügbar. Um eine R-Lektion abzuschließen, gehen Sie in den `/solution`-Ordner und suchen Sie nach R-Lektionen. Diese enthalten eine .rmd-Erweiterung, die eine **R Markdown**-Datei darstellt, die einfach als Einbettung von `code chunks` (von R oder anderen Sprachen) und einem `YAML header` (der steuert, wie Ausgaben wie PDF formatiert werden) in einem `Markdown document` definiert werden kann. Als solches dient sie als beispielhaftes Erstellungsframework für Data Science, da sie es Ihnen ermöglicht, Ihren Code, dessen Ausgabe und Ihre Gedanken zu kombinieren, indem Sie diese in Markdown niederschreiben. Darüber hinaus können R Markdown-Dokumente in Ausgabedateiformate wie PDF, HTML oder Word gerendert werden. -> **Ein Hinweis zu Quizzen**: Alle Quizze befinden sich im [Quiz App-Ordner](../../quiz-app), insgesamt 52 Quizze mit jeweils drei Fragen. Sie sind in den Lektionen verlinkt, aber die Quiz-App kann lokal ausgeführt werden; folge den Anweisungen im `quiz-app`-Ordner, um lokal zu hosten oder nach Azure zu deployen. +> **Eine Anmerkung zu Quizzen**: Alle Quizze sind im [Quiz-App-Ordner](../../quiz-app) enthalten, insgesamt 52 Quizze mit jeweils drei Fragen. Sie sind innerhalb der Lektionen verlinkt, aber die Quiz-App kann lokal ausgeführt werden; befolgen Sie die Anweisungen im `quiz-app`-Ordner, um lokal zu hosten oder auf Azure bereitzustellen. -| Lektionsnummer | Thema | Lektionsgruppierung | Lernziele | Verlinkte Lektion | Autor | +| Lektionsnummer | Thema | Lektionsgruppe | Lernziele | Verknüpfte Lektion | Autor | | :-----------: | :------------------------------------------------------------: | :-------------------------------------------------: | ------------------------------------------------------------------------------------------------------------------------------- | :--------------------------------------------------------------------------------------------------------------------------------------: | :--------------------------------------------------: | -| 01 | Einführung in das maschinelle Lernen | [Einführung](1-Introduction/README.md) | Lernen Sie die grundlegenden Konzepte des maschinellen Lernens | [Lektion](1-Introduction/1-intro-to-ML/README.md) | Muhammad | +| 01 | Einführung in maschinelles Lernen | [Einführung](1-Introduction/README.md) | Lernen Sie die grundlegenden Konzepte des maschinellen Lernens | [Lektion](1-Introduction/1-intro-to-ML/README.md) | Muhammad | | 02 | Die Geschichte des maschinellen Lernens | [Einführung](1-Introduction/README.md) | Erfahren Sie die Geschichte dieses Fachgebiets | [Lektion](1-Introduction/2-history-of-ML/README.md) | Jen and Amy | -| 03 | Fairness und maschinelles Lernen | [Einführung](1-Introduction/README.md) | Welche wichtigen philosophischen Fragen zur Fairness sollten Studierende berücksichtigen, wenn sie ML-Modelle entwickeln und anwenden? | [Lektion](1-Introduction/3-fairness/README.md) | Tomomi | -| 04 | Techniken des maschinellen Lernens | [Einführung](1-Introduction/README.md) | Welche Techniken verwenden ML-Forscher, um ML-Modelle zu erstellen? | [Lektion](1-Introduction/4-techniques-of-ML/README.md) | Chris and Jen | -| 05 | Einführung in die Regression | [Regression](2-Regression/README.md) | Erste Schritte mit Python und Scikit-learn für Regressionsmodelle | [Python](2-Regression/1-Tools/README.md) • [R](../../2-Regression/1-Tools/solution/R/lesson_1.html) | Jen • Eric Wanjau | +| 03 | Fairness und maschinelles Lernen | [Einführung](1-Introduction/README.md) | Welche wichtigen philosophischen Fragen zur Fairness sollten Lernende beachten, wenn sie ML-Modelle erstellen und anwenden? | [Lektion](1-Introduction/3-fairness/README.md) | Tomomi | +| 04 | Techniken des maschinellen Lernens | [Einführung](1-Introduction/README.md) | Welche Techniken verwenden ML-Forschende, um ML-Modelle zu erstellen? | [Lektion](1-Introduction/4-techniques-of-ML/README.md) | Chris and Jen | +| 05 | Einführung in die Regression | [Regression](2-Regression/README.md) | Einstieg in Python und Scikit-learn für Regressionsmodelle | [Python](2-Regression/1-Tools/README.md) • [R](../../2-Regression/1-Tools/solution/R/lesson_1.html) | Jen • Eric Wanjau | | 06 | Nordamerikanische Kürbisspreise 🎃 | [Regression](2-Regression/README.md) | Daten visualisieren und bereinigen zur Vorbereitung auf ML | [Python](2-Regression/2-Data/README.md) • [R](../../2-Regression/2-Data/solution/R/lesson_2.html) | Jen • Eric Wanjau | | 07 | Nordamerikanische Kürbisspreise 🎃 | [Regression](2-Regression/README.md) | Lineare und polynomiale Regressionsmodelle erstellen | [Python](2-Regression/3-Linear/README.md) • [R](../../2-Regression/3-Linear/solution/R/lesson_3.html) | Jen and Dmitry • Eric Wanjau | | 08 | Nordamerikanische Kürbisspreise 🎃 | [Regression](2-Regression/README.md) | Ein logistisches Regressionsmodell erstellen | [Python](2-Regression/4-Logistic/README.md) • [R](../../2-Regression/4-Logistic/solution/R/lesson_4.html) | Jen • Eric Wanjau | | 09 | Eine Web-App 🔌 | [Web-App](3-Web-App/README.md) | Erstellen Sie eine Web-App, um Ihr trainiertes Modell zu verwenden | [Python](3-Web-App/1-Web-App/README.md) | Jen | -| 10 | Einführung in die Klassifikation | [Klassifikation](4-Classification/README.md) | Daten bereinigen, vorbereiten und visualisieren; Einführung in die Klassifikation | [Python](4-Classification/1-Introduction/README.md) • [R](../../4-Classification/1-Introduction/solution/R/lesson_10.html) | Jen and Cassie • Eric Wanjau | +| 10 | Einführung in die Klassifikation | [Klassifikation](4-Classification/README.md) | Bereinigen, vorbereiten und visualisieren Sie Ihre Daten; Einführung in die Klassifikation | [Python](4-Classification/1-Introduction/README.md) • [R](../../4-Classification/1-Introduction/solution/R/lesson_10.html) | Jen and Cassie • Eric Wanjau | | 11 | Leckere asiatische und indische Küche 🍜 | [Klassifikation](4-Classification/README.md) | Einführung in Klassifikatoren | [Python](4-Classification/2-Classifiers-1/README.md) • [R](../../4-Classification/2-Classifiers-1/solution/R/lesson_11.html) | Jen and Cassie • Eric Wanjau | | 12 | Leckere asiatische und indische Küche 🍜 | [Klassifikation](4-Classification/README.md) | Weitere Klassifikatoren | [Python](4-Classification/3-Classifiers-2/README.md) • [R](../../4-Classification/3-Classifiers-2/solution/R/lesson_12.html) | Jen and Cassie • Eric Wanjau | | 13 | Leckere asiatische und indische Küche 🍜 | [Klassifikation](4-Classification/README.md) | Erstellen Sie eine Empfehlungs-Web-App mit Ihrem Modell | [Python](4-Classification/4-Applied/README.md) | Jen | -| 14 | Einführung in die Clusteranalyse | [Clusteranalyse](5-Clustering/README.md) | Daten bereinigen, vorbereiten und visualisieren; Einführung in die Clusteranalyse | [Python](5-Clustering/1-Visualize/README.md) • [R](../../5-Clustering/1-Visualize/solution/R/lesson_14.html) | Jen • Eric Wanjau | -| 15 | Erkundung nigerianischer Musikgeschmäcker 🎧 | [Clusteranalyse](5-Clustering/README.md) | Erkunden Sie die K-Means-Clustering-Methode | [Python](5-Clustering/2-K-Means/README.md) • [R](../../5-Clustering/2-K-Means/solution/R/lesson_15.html) | Jen • Eric Wanjau | -| 16 | Einführung in die Verarbeitung natürlicher Sprache ☕️ | [Natürliche Sprachverarbeitung](6-NLP/README.md) | Erlernen Sie die Grundlagen der NLP, indem Sie einen einfachen Bot bauen | [Python](6-NLP/1-Introduction-to-NLP/README.md) | Stephen | -| 17 | Gängige NLP-Aufgaben ☕️ | [Natürliche Sprachverarbeitung](6-NLP/README.md) | Vertiefen Sie Ihr NLP-Wissen, indem Sie gängige Aufgaben verstehen, die beim Umgang mit Sprachstrukturen erforderlich sind | [Python](6-NLP/2-Tasks/README.md) | Stephen | -| 18 | Übersetzung und Sentiment-Analyse ♥️ | [Natürliche Sprachverarbeitung](6-NLP/README.md) | Übersetzung und Sentiment-Analyse mit Jane Austen | [Python](6-NLP/3-Translation-Sentiment/README.md) | Stephen | -| 19 | Romantische Hotels in Europa ♥️ | [Natürliche Sprachverarbeitung](6-NLP/README.md) | Sentiment-Analyse mit Hotelbewertungen 1 | [Python](6-NLP/4-Hotel-Reviews-1/README.md) | Stephen | -| 20 | Romantische Hotels in Europa ♥️ | [Natürliche Sprachverarbeitung](6-NLP/README.md) | Sentiment-Analyse mit Hotelbewertungen 2 | [Python](6-NLP/5-Hotel-Reviews-2/README.md) | Stephen | -| 21 | Einführung in die Zeitreihenprognose | [Zeitreihen](7-TimeSeries/README.md) | Einführung in die Zeitreihenprognose | [Python](7-TimeSeries/1-Introduction/README.md) | Francesca | -| 22 | ⚡️ World Power Usage ⚡️ - Zeitreihenprognose mit ARIMA | [Zeitreihen](7-TimeSeries/README.md) | Zeitreihenprognose mit ARIMA | [Python](7-TimeSeries/2-ARIMA/README.md) | Francesca | -| 23 | ⚡️ World Power Usage ⚡️ - Zeitreihenprognose mit SVR | [Zeitreihen](7-TimeSeries/README.md) | Zeitreihenprognose mit Support Vector Regressor | [Python](7-TimeSeries/3-SVR/README.md) | Anirban | -| 24 | Einführung in Reinforcement Learning | [Verstärkungslernen](8-Reinforcement/README.md) | Einführung in das Verstärkungslernen mit Q-Learning | [Python](8-Reinforcement/1-QLearning/README.md) | Dmitry | -| 25 | Hilf Peter, dem Wolf zu entkommen! 🐺 | [Verstärkungslernen](8-Reinforcement/README.md) | Reinforcement-Learning Gym | [Python](8-Reinforcement/2-Gym/README.md) | Dmitry | -| Postscript | Echte ML-Szenarien und Anwendungen | [ML in the Wild](9-Real-World/README.md) | Interessante und aufschlussreiche reale Anwendungen klassischer ML | [Lektion](9-Real-World/1-Applications/README.md) | Team | -| Postscript | Modell-Debugging in ML mit RAI-Dashboard | [ML in the Wild](9-Real-World/README.md) | Modell-Debugging im Machine Learning mithilfe von Responsible AI-Dashboard-Komponenten | [Lektion](9-Real-World/2-Debugging-ML-Models/README.md) | Ruth Yakubu | - -> [finden Sie alle weiteren Ressourcen für diesen Kurs in unserer Microsoft Learn-Sammlung](https://learn.microsoft.com/en-us/collections/qrqzamz1nn2wx3?WT.mc_id=academic-77952-bethanycheum) +| 14 | Einführung in Clustering | [Clustering](5-Clustering/README.md) | Bereinigen, vorbereiten und visualisieren Sie Ihre Daten; Einführung in Clustering | [Python](5-Clustering/1-Visualize/README.md) • [R](../../5-Clustering/1-Visualize/solution/R/lesson_14.html) | Jen • Eric Wanjau | +| 15 | Nigerianische Musikgeschmäcker erkunden 🎧 | [Clustering](5-Clustering/README.md) | Erkunden Sie die K-Means-Clustering-Methode | [Python](5-Clustering/2-K-Means/README.md) • [R](../../5-Clustering/2-K-Means/solution/R/lesson_15.html) | Jen • Eric Wanjau | +| 16 | Einführung in die natürliche Sprachverarbeitung ☕️ | [Natürliche Sprachverarbeitung](6-NLP/README.md) | Lernen Sie die Grundlagen der NLP, indem Sie einen einfachen Bot erstellen | [Python](6-NLP/1-Introduction-to-NLP/README.md) | Stephen | +| 17 | Häufige NLP-Aufgaben ☕️ | [Natürliche Sprachverarbeitung](6-NLP/README.md) | Vertiefen Sie Ihr NLP-Wissen, indem Sie häufige Aufgaben verstehen, die beim Umgang mit Sprachstrukturen erforderlich sind | [Python](6-NLP/2-Tasks/README.md) | Stephen | +| 18 | Übersetzung und Sentimentanalyse ♥️ | [Natürliche Sprachverarbeitung](6-NLP/README.md) | Übersetzung und Sentimentanalyse mit Jane Austen | [Python](6-NLP/3-Translation-Sentiment/README.md) | Stephen | +| 19 | Romantische Hotels Europas ♥️ | [Natürliche Sprachverarbeitung](6-NLP/README.md) | Sentimentanalyse mit Hotelbewertungen 1 | [Python](6-NLP/4-Hotel-Reviews-1/README.md) | Stephen | +| 20 | Romantische Hotels Europas ♥️ | [Natürliche Sprachverarbeitung](6-NLP/README.md) | Sentimentanalyse mit Hotelbewertungen 2 | [Python](6-NLP/5-Hotel-Reviews-2/README.md) | Stephen | +| 21 | Einführung in Zeitreihenprognosen | [Zeitreihen](7-TimeSeries/README.md) | Einführung in Zeitreihenprognosen | [Python](7-TimeSeries/1-Introduction/README.md) | Francesca | +| 22 | ⚡️ Weltweiter Stromverbrauch ⚡️ - Zeitreihenprognosen mit ARIMA | [Zeitreihen](7-TimeSeries/README.md) | Zeitreihenprognosen mit ARIMA | [Python](7-TimeSeries/2-ARIMA/README.md) | Francesca | +| 23 | ⚡️ Weltweiter Stromverbrauch ⚡️ - Zeitreihenprognosen mit SVR | [Zeitreihen](7-TimeSeries/README.md) | Zeitreihenprognosen mit Support Vector Regressor | [Python](7-TimeSeries/3-SVR/README.md) | Anirban | +| 24 | Einführung in Reinforcement Learning | [Reinforcement learning](8-Reinforcement/README.md) | Einführung in Reinforcement Learning mit Q-Learning | [Python](8-Reinforcement/1-QLearning/README.md) | Dmitry | +| 25 | Hilf Peter, dem Wolf zu entkommen! 🐺 | [Reinforcement learning](8-Reinforcement/README.md) | Reinforcement-Learning-Gym | [Python](8-Reinforcement/2-Gym/README.md) | Dmitry | +| Postscript | Echtwelt-ML-Szenarien und Anwendungen | [ML in the Wild](9-Real-World/README.md) | Interessante und aufschlussreiche Anwendungsfälle klassischer ML | [Lektion](9-Real-World/1-Applications/README.md) | Team | +| Postscript | Modell-Debugging im ML mit dem RAI-Dashboard | [ML in the Wild](9-Real-World/README.md) | Modell-Debugging im Machine Learning mit Komponenten des Responsible AI-Dashboards | [Lektion](9-Real-World/2-Debugging-ML-Models/README.md) | Ruth Yakubu | + +> [finden Sie alle zusätzlichen Ressourcen für diesen Kurs in unserer Microsoft Learn-Sammlung](https://learn.microsoft.com/en-us/collections/qrqzamz1nn2wx3?WT.mc_id=academic-77952-bethanycheum) ## Offline-Zugriff -Sie können diese Dokumentation offline ausführen, indem Sie [Docsify](https://docsify.js.org/#/) verwenden. Forken Sie dieses Repo, [installieren Sie Docsify](https://docsify.js.org/#/quickstart) auf Ihrem lokalen Rechner, und geben Sie dann im Stammordner dieses Repos `docsify serve` ein. Die Website wird auf Port 3000 auf Ihrem localhost bereitgestellt: `localhost:3000`. +Sie können diese Dokumentation offline mit [Docsify](https://docsify.js.org/#/) ausführen. Erstellen Sie einen Fork dieses Repositories, [Docsify installieren](https://docsify.js.org/#/quickstart) auf Ihrer lokalen Maschine, und dann im Stammordner dieses Repositories geben Sie `docsify serve` ein. Die Website wird auf Port 3000 auf Ihrem lokalen Host bereitgestellt: `localhost:3000`. ## PDFs -Eine PDF-Version des Lehrplans mit Links finden Sie [hier](https://microsoft.github.io/ML-For-Beginners/pdf/readme.pdf). +Ein PDF des Lehrplans mit Links finden Sie [hier](https://microsoft.github.io/ML-For-Beginners/pdf/readme.pdf). ## 🎒 Weitere Kurse @@ -176,11 +176,11 @@ Unser Team bietet weitere Kurse an! Schauen Sie sich diese an: [![AZD für Einsteiger](https://img.shields.io/badge/AZD%20for%20Beginners-0078D4?style=for-the-badge&labelColor=E5E7EB&color=0078D4)](https://github.com/microsoft/AZD-for-beginners?WT.mc_id=academic-105485-koreyst) [![Edge AI für Einsteiger](https://img.shields.io/badge/Edge%20AI%20for%20Beginners-00B8E4?style=for-the-badge&labelColor=E5E7EB&color=00B8E4)](https://github.com/microsoft/edgeai-for-beginners?WT.mc_id=academic-105485-koreyst) [![MCP für Einsteiger](https://img.shields.io/badge/MCP%20for%20Beginners-009688?style=for-the-badge&labelColor=E5E7EB&color=009688)](https://github.com/microsoft/mcp-for-beginners?WT.mc_id=academic-105485-koreyst) -[![AI Agents für Einsteiger](https://img.shields.io/badge/AI%20Agents%20for%20Beginners-00C49A?style=for-the-badge&labelColor=E5E7EB&color=00C49A)](https://github.com/microsoft/ai-agents-for-beginners?WT.mc_id=academic-105485-koreyst) +[![KI-Agenten für Einsteiger](https://img.shields.io/badge/AI%20Agents%20for%20Beginners-00C49A?style=for-the-badge&labelColor=E5E7EB&color=00C49A)](https://github.com/microsoft/ai-agents-for-beginners?WT.mc_id=academic-105485-koreyst) --- -### Generative AI-Serie +### Generative AI-Reihe [![Generative AI für Einsteiger](https://img.shields.io/badge/Generative%20AI%20for%20Beginners-8B5CF6?style=for-the-badge&labelColor=E5E7EB&color=8B5CF6)](https://github.com/microsoft/generative-ai-for-beginners?WT.mc_id=academic-105485-koreyst) [![Generative AI (.NET)](https://img.shields.io/badge/Generative%20AI%20(.NET)-9333EA?style=for-the-badge&labelColor=E5E7EB&color=9333EA)](https://github.com/microsoft/Generative-AI-for-beginners-dotnet?WT.mc_id=academic-105485-koreyst) [![Generative KI (Java)](https://img.shields.io/badge/Generative%20AI%20(Java)-C084FC?style=for-the-badge&labelColor=E5E7EB&color=C084FC)](https://github.com/microsoft/generative-ai-for-beginners-java?WT.mc_id=academic-105485-koreyst) @@ -189,13 +189,13 @@ Unser Team bietet weitere Kurse an! Schauen Sie sich diese an: --- ### Kerninhalte -[![ML für Einsteiger](https://img.shields.io/badge/ML%20for%20Beginners-22C55E?style=for-the-badge&labelColor=E5E7EB&color=22C55E)](https://aka.ms/ml-beginners?WT.mc_id=academic-105485-koreyst) -[![Data Science für Einsteiger](https://img.shields.io/badge/Data%20Science%20for%20Beginners-84CC16?style=for-the-badge&labelColor=E5E7EB&color=84CC16)](https://aka.ms/datascience-beginners?WT.mc_id=academic-105485-koreyst) -[![KI für Einsteiger](https://img.shields.io/badge/AI%20for%20Beginners-A3E635?style=for-the-badge&labelColor=E5E7EB&color=A3E635)](https://aka.ms/ai-beginners?WT.mc_id=academic-105485-koreyst) -[![Cybersicherheit für Einsteiger](https://img.shields.io/badge/Cybersecurity%20for%20Beginners-F97316?style=for-the-badge&labelColor=E5E7EB&color=F97316)](https://github.com/microsoft/Security-101?WT.mc_id=academic-96948-sayoung) -[![Webentwicklung für Einsteiger](https://img.shields.io/badge/Web%20Dev%20for%20Beginners-EC4899?style=for-the-badge&labelColor=E5E7EB&color=EC4899)](https://aka.ms/webdev-beginners?WT.mc_id=academic-105485-koreyst) -[![IoT für Einsteiger](https://img.shields.io/badge/IoT%20for%20Beginners-14B8A6?style=for-the-badge&labelColor=E5E7EB&color=14B8A6)](https://aka.ms/iot-beginners?WT.mc_id=academic-105485-koreyst) -[![XR-Entwicklung für Einsteiger](https://img.shields.io/badge/XR%20Development%20for%20Beginners-38BDF8?style=for-the-badge&labelColor=E5E7EB&color=38BDF8)](https://github.com/microsoft/xr-development-for-beginners?WT.mc_id=academic-105485-koreyst) +[![ML für Anfänger](https://img.shields.io/badge/ML%20for%20Beginners-22C55E?style=for-the-badge&labelColor=E5E7EB&color=22C55E)](https://aka.ms/ml-beginners?WT.mc_id=academic-105485-koreyst) +[![Data Science für Anfänger](https://img.shields.io/badge/Data%20Science%20for%20Beginners-84CC16?style=for-the-badge&labelColor=E5E7EB&color=84CC16)](https://aka.ms/datascience-beginners?WT.mc_id=academic-105485-koreyst) +[![KI für Anfänger](https://img.shields.io/badge/AI%20for%20Beginners-A3E635?style=for-the-badge&labelColor=E5E7EB&color=A3E635)](https://aka.ms/ai-beginners?WT.mc_id=academic-105485-koreyst) +[![Cybersicherheit für Anfänger](https://img.shields.io/badge/Cybersecurity%20for%20Beginners-F97316?style=for-the-badge&labelColor=E5E7EB&color=F97316)](https://github.com/microsoft/Security-101?WT.mc_id=academic-96948-sayoung) +[![Webentwicklung für Anfänger](https://img.shields.io/badge/Web%20Dev%20for%20Beginners-EC4899?style=for-the-badge&labelColor=E5E7EB&color=EC4899)](https://aka.ms/webdev-beginners?WT.mc_id=academic-105485-koreyst) +[![IoT für Anfänger](https://img.shields.io/badge/IoT%20for%20Beginners-14B8A6?style=for-the-badge&labelColor=E5E7EB&color=14B8A6)](https://aka.ms/iot-beginners?WT.mc_id=academic-105485-koreyst) +[![XR-Entwicklung für Anfänger](https://img.shields.io/badge/XR%20Development%20for%20Beginners-38BDF8?style=for-the-badge&labelColor=E5E7EB&color=38BDF8)](https://github.com/microsoft/xr-development-for-beginners?WT.mc_id=academic-105485-koreyst) --- @@ -207,11 +207,11 @@ Unser Team bietet weitere Kurse an! Schauen Sie sich diese an: ## Hilfe -Wenn Sie feststecken oder Fragen zum Erstellen von KI-Anwendungen haben, treten Sie mit Mitlernenden und erfahrenen Entwicklern in Diskussionen über MCP ein. Es ist eine unterstützende Community, in der Fragen willkommen sind und Wissen frei geteilt wird. +Wenn Sie feststecken oder Fragen zum Erstellen von KI-Apps haben, schließen Sie sich anderen Lernenden und erfahrenen Entwicklern an und diskutieren Sie über MCP. Es ist eine unterstützende Community, in der Fragen willkommen sind und Wissen frei geteilt wird. [![Microsoft Foundry Discord](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) -Wenn Sie Produktfeedback haben oder beim Entwickeln auf Fehler stoßen, besuchen Sie: +Wenn Sie Produktfeedback haben oder beim Erstellen auf Fehler stoßen, besuchen Sie: [![Microsoft Foundry Entwicklerforum](https://img.shields.io/badge/GitHub-Microsoft_Foundry_Developer_Forum-blue?style=for-the-badge&logo=github&color=000000&logoColor=fff)](https://aka.ms/foundry/forum) @@ -219,5 +219,5 @@ Wenn Sie Produktfeedback haben oder beim Entwickeln auf Fehler stoßen, besuchen Haftungsausschluss: -Dieses Dokument wurde mithilfe des KI-Übersetzungsdienstes [Co-op Translator](https://github.com/Azure/co-op-translator) übersetzt. Obwohl wir uns um Genauigkeit bemühen, beachten Sie bitte, dass automatisierte Übersetzungen Fehler oder Ungenauigkeiten enthalten können. Das Originaldokument in seiner ursprünglichen Sprache ist als maßgebliche Quelle zu betrachten. Für kritische Informationen wird eine professionelle menschliche Übersetzung empfohlen. Für Missverständnisse oder Fehlinterpretationen, die aus der Nutzung dieser Übersetzung entstehen, übernehmen wir keine Haftung. +Dieses Dokument wurde mit dem KI‑Übersetzungsdienst Co‑op Translator (https://github.com/Azure/co-op-translator) übersetzt. Obwohl wir uns um Genauigkeit bemühen, können automatisierte Übersetzungen Fehler oder Ungenauigkeiten enthalten. Das Originaldokument in seiner Ausgangssprache ist als maßgebliche Quelle zu betrachten. Für wichtige Informationen wird eine professionelle menschliche Übersetzung empfohlen. Wir übernehmen keine Haftung für Missverständnisse oder Fehlinterpretationen, die aus der Verwendung dieser Übersetzung entstehen. \ No newline at end of file diff --git a/translations/el/README.md b/translations/el/README.md index e0f9258ba..7cc6a48ed 100644 --- a/translations/el/README.md +++ b/translations/el/README.md @@ -1,86 +1,86 @@ [![Άδεια GitHub](https://img.shields.io/github/license/microsoft/ML-For-Beginners.svg)](https://github.com/microsoft/ML-For-Beginners/blob/master/LICENSE) -[![Συνεισφέροντες GitHub](https://img.shields.io/github/contributors/microsoft/ML-For-Beginners.svg)](https://GitHub.com/microsoft/ML-For-Beginners/graphs/contributors/) +[![Συνεργάτες GitHub](https://img.shields.io/github/contributors/microsoft/ML-For-Beginners.svg)](https://GitHub.com/microsoft/ML-For-Beginners/graphs/contributors/) [![Θέματα GitHub](https://img.shields.io/github/issues/microsoft/ML-For-Beginners.svg)](https://GitHub.com/microsoft/ML-For-Beginners/issues/) -[![Pull requests GitHub](https://img.shields.io/github/issues-pr/microsoft/ML-For-Beginners.svg)](https://GitHub.com/microsoft/ML-For-Beginners/pulls/) +[![Αιτήματα έλξης GitHub](https://img.shields.io/github/issues-pr/microsoft/ML-For-Beginners.svg)](https://GitHub.com/microsoft/ML-For-Beginners/pulls/) [![PRs Ευπρόσδεκτα](https://img.shields.io/badge/PRs-welcome-brightgreen.svg?style=flat-square)](http://makeapullrequest.com) -[![Discord Microsoft Foundry](https://img.shields.io/github/watchers/microsoft/ML-For-Beginners.svg?style=social&label=Watch)](https://GitHub.com/microsoft/ML-For-Beginners/watchers/) +[![Παρατηρητές GitHub](https://img.shields.io/github/watchers/microsoft/ML-For-Beginners.svg?style=social&label=Watch)](https://GitHub.com/microsoft/ML-For-Beginners/watchers/) [![Forks GitHub](https://img.shields.io/github/forks/microsoft/ML-For-Beginners.svg?style=social&label=Fork)](https://GitHub.com/microsoft/ML-For-Beginners/network/) [![Αστέρια GitHub](https://img.shields.io/github/stars/microsoft/ML-For-Beginners.svg?style=social&label=Star)](https://GitHub.com/microsoft/ML-For-Beginners/stargazers/) -### 🌐 Υποστήριξη πολλαπλών γλωσσών +### 🌐 Υποστήριξη Πολλών Γλωσσών #### Υποστηρίζεται μέσω GitHub Action (Αυτοματοποιημένο & Πάντα Ενημερωμένο) -[Αραβικά](../ar/README.md) | [Βεγγαλικά](../bn/README.md) | [Βουλγαρικά](../bg/README.md) | [Βιρμανικά (Μιανμάρ)](../my/README.md) | [Κινέζικα (Απλοποιημένα)](../zh/README.md) | [Κινέζικα (Παραδοσιακά, Χονγκ Κονγκ)](../hk/README.md) | [Κινέζικα (Παραδοσιακά, Μακάο)](../mo/README.md) | [Κινέζικα (Παραδοσιακά, Ταϊβάν)](../tw/README.md) | [Κροατικά](../hr/README.md) | [Τσέχικα](../cs/README.md) | [Δανικά](../da/README.md) | [Ολλανδικά](../nl/README.md) | [Εσθονικά](../et/README.md) | [Φινλανδικά](../fi/README.md) | [Γαλλικά](../fr/README.md) | [Γερμανικά](../de/README.md) | [Ελληνικά](./README.md) | [Εβραϊκά](../he/README.md) | [Χίντι](../hi/README.md) | [Ουγγρικά](../hu/README.md) | [Ινδονησιακά](../id/README.md) | [Ιταλικά](../it/README.md) | [Ιαπωνικά](../ja/README.md) | [Κανάντα](../kn/README.md) | [Κορεατικά](../ko/README.md) | [Λιθουανικά](../lt/README.md) | [Μαλαισιανά](../ms/README.md) | [Μαλαγαλικά](../ml/README.md) | [Μαραθικά](../mr/README.md) | [Νεπάλι](../ne/README.md) | [Νιγηριανό Πίτζιν](../pcm/README.md) | [Νορβηγικά](../no/README.md) | [Περσικά (Φαρσί)](../fa/README.md) | [Πολωνικά](../pl/README.md) | [Πορτογαλικά (Βραζιλία)](../br/README.md) | [Πορτογαλικά (Πορτογαλία)](../pt/README.md) | [Πουντζαπικά (Gurmukhi)](../pa/README.md) | [Ρουμανικά](../ro/README.md) | [Ρωσικά](../ru/README.md) | [Σερβικά (Κυριλλικά)](../sr/README.md) | [Σλοβακικά](../sk/README.md) | [Σλοβενικά](../sl/README.md) | [Ισπανικά](../es/README.md) | [Σουαχίλι](../sw/README.md) | [Σουηδικά](../sv/README.md) | [Ταγκαλόγκ (Φιλιππινέζικα)](../tl/README.md) | [Ταμίλ](../ta/README.md) | [Τελούγκου](../te/README.md) | [Ταϊλανδικά](../th/README.md) | [Τουρκικά](../tr/README.md) | [Ουκρανικά](../uk/README.md) | [Ουρντού](../ur/README.md) | [Βιετναμέζικα](../vi/README.md) +[Αραβικά](../ar/README.md) | [Μπενγκάλι](../bn/README.md) | [Βουλγαρικά](../bg/README.md) | [Βιρμανικά (Μιανμάρ)](../my/README.md) | [Κινέζικα (Απλοποιημένα)](../zh/README.md) | [Κινέζικα (Παραδοσιακά, Χονγκ Κονγκ)](../hk/README.md) | [Κινέζικα (Παραδοσιακά, Μακάο)](../mo/README.md) | [Κινέζικα (Παραδοσιακά, Ταϊβάν)](../tw/README.md) | [Κροατικά](../hr/README.md) | [Τσεχικά](../cs/README.md) | [Δανικά](../da/README.md) | [Ολλανδικά](../nl/README.md) | [Εσθονικά](../et/README.md) | [Φινλανδικά](../fi/README.md) | [Γαλλικά](../fr/README.md) | [Γερμανικά](../de/README.md) | [Ελληνικά](./README.md) | [Εβραϊκά](../he/README.md) | [Χίντι](../hi/README.md) | [Ουγγρικά](../hu/README.md) | [Ινδονησιακά](../id/README.md) | [Ιταλικά](../it/README.md) | [Ιαπωνικά](../ja/README.md) | [Κανάντα](../kn/README.md) | [Κορεατικά](../ko/README.md) | [Λιθουανικά](../lt/README.md) | [Μαλαισιανά](../ms/README.md) | [Μαλαγιαλάμ](../ml/README.md) | [Μαράθι](../mr/README.md) | [Νεπάλι](../ne/README.md) | [Νιγηριανή Πίτζιν](../pcm/README.md) | [Νορβηγικά](../no/README.md) | [Περσικά (Φαρσί)](../fa/README.md) | [Πολωνικά](../pl/README.md) | [Πορτογαλικά (Βραζιλία)](../br/README.md) | [Πορτογαλικά (Πορτογαλία)](../pt/README.md) | [Πουντζάμπι (Gurmukhi)](../pa/README.md) | [Ρουμανικά](../ro/README.md) | [Ρωσικά](../ru/README.md) | [Σερβικά (Κυριλλικά)](../sr/README.md) | [Σλοβακικά](../sk/README.md) | [Σλοβενικά](../sl/README.md) | [Ισπανικά](../es/README.md) | [Σουαχίλι](../sw/README.md) | [Σουηδικά](../sv/README.md) | [Ταγκάλογκ (Φιλιππινέζικα)](../tl/README.md) | [Ταμίλ](../ta/README.md) | [Τελούγκου](../te/README.md) | [Ταϊλανδικά](../th/README.md) | [Τουρκικά](../tr/README.md) | [Ουκρανικά](../uk/README.md) | [Ουρντού](../ur/README.md) | [Βιετναμέζικα](../vi/README.md) #### Ελάτε στην Κοινότητά μας -[![Discord Microsoft Foundry](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) +[![Microsoft Foundry Discord](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) -Διοργανώνουμε μια σειρά στο Discord με τίτλο «Μάθε με AI», μάθετε περισσότερα και ενταχθείτε σε εμάς στο [Σειρά Μάθε με AI](https://aka.ms/learnwithai/discord) από 18 - 30 Σεπτεμβρίου, 2025. Θα λάβετε συμβουλές και κόλπα για τη χρήση του GitHub Copilot για Data Science. +Διοργανώνουμε μια σειρά Discord "Μάθε με AI" σε εξέλιξη — μάθετε περισσότερα και εγγραφείτε στη σειρά στο [Learn with AI Series](https://aka.ms/learnwithai/discord) από 18 - 30 Σεπτεμβρίου 2025. Θα λάβετε συμβουλές και κόλπα για τη χρήση του GitHub Copilot για Data Science. -![Σειρά Μάθε με AI](../../translated_images/3.9b58fd8d6c373c20c588c5070c4948a826ab074426c28ceb5889641294373dfc.el.png) +![Σειρά Learn with AI](../../translated_images/3.9b58fd8d6c373c20.el.png) # Μηχανική Μάθηση για Αρχάριους - Ένα Πρόγραμμα Σπουδών -> 🌍 Ταξιδέψτε γύρω από τον κόσμο καθώς εξερευνούμε τη Μηχανική Μάθηση μέσω των πολιτισμών του κόσμου 🌍 +> 🌍 Ταξιδέψτε σε όλο τον κόσμο καθώς εξερευνούμε τη Μηχανική Μάθηση μέσω των πολιτισμών του κόσμου 🌍 -Οι Cloud Advocates της Microsoft με χαρά προσφέρουν ένα πρόγραμμα 12 εβδομάδων, 26 μαθημάτων όλο για την **Μηχανική Μάθηση**. Σε αυτό το πρόγραμμα, θα μάθετε ό,τι μερικές φορές ονομάζεται **παραδοσιακή μηχανική μάθηση**, χρησιμοποιώντας κυρίως τη βιβλιοθήκη Scikit-learn και αποφεύγοντας το deep learning, το οποίο καλύπτεται στο [πρόγραμμα 'AI for Beginners'](https://aka.ms/ai4beginners). Συνδυάστε αυτά τα μαθήματα με το [πρόγραμμα 'Data Science for Beginners'](https://aka.ms/ds4beginners) επίσης! +Οι Cloud Advocates της Microsoft με χαρά προσφέρουν ένα 12-εβδομάδων, 26-μαθημάτων πρόγραμμα σπουδών που αφορά τη **Μηχανική Μάθηση**. Σε αυτό το πρόγραμμα, θα μάθετε για ό,τι μερικές φορές ονομάζεται **κλασική μηχανική μάθηση**, χρησιμοποιώντας κυρίως τη βιβλιοθήκη Scikit-learn και αποφεύγοντας το deep learning, το οποίο καλύπτεται στο [AI for Beginners' curriculum](https://aka.ms/ai4beginners). Συνδυάστε αυτά τα μαθήματα με το ['Data Science for Beginners' curriculum](https://aka.ms/ds4beginners), επίσης! -Ταξιδέψτε μαζί μας ανά τον κόσμο καθώς εφαρμόζουμε αυτές τις κλασικές τεχνικές σε δεδομένα από πολλές περιοχές του κόσμου. Κάθε μάθημα περιλαμβάνει προ- και μετα-μάθημα κουίζ, γραπτές οδηγίες για την ολοκλήρωση του μαθήματος, μια λύση, μια ανάθεση, και περισσότερα. Η παιδαγωγική μας βασισμένη σε έργα σας επιτρέπει να μαθαίνετε ενώ κατασκευάζετε, ένας δοκιμασμένος τρόπος για να «εγκλωβιστούν» νέες δεξιότητες. +Ταξιδέψτε μαζί μας σε όλο τον κόσμο καθώς εφαρμόζουμε αυτές τις κλασικές τεχνικές σε δεδομένα από πολλές περιοχές του κόσμου. Κάθε μάθημα περιλαμβάνει κουίζ πριν και μετά το μάθημα, γραπτές οδηγίες για την ολοκλήρωση του μαθήματος, μια λύση, μια εργασία και άλλα. Η παιδαγωγική μας που βασίζεται σε έργα σας επιτρέπει να μαθαίνετε ενώ κατασκευάζετε, ένας αποδεδειγμένος τρόπος για να "παγιωθούν" νέες δεξιότητες. **✍️ Θερμές ευχαριστίες στους συγγραφείς μας** Jen Looper, Stephen Howell, Francesca Lazzeri, Tomomi Imura, Cassie Breviu, Dmitry Soshnikov, Chris Noring, Anirban Mukherjee, Ornella Altunyan, Ruth Yakubu and Amy Boyd **🎨 Ευχαριστίες επίσης στους εικονογράφους μας** Tomomi Imura, Dasani Madipalli, and Jen Looper -**🙏 Ειδικές ευχαριστίες 🙏 στους Microsoft Student Ambassador συγγραφείς, αναθεωρητές και συμβάλλοντες στο περιεχόμενο**, ιδιαιτέρως Rishit Dagli, Muhammad Sakib Khan Inan, Rohan Raj, Alexandru Petrescu, Abhishek Jaiswal, Nawrin Tabassum, Ioan Samuila, and Snigdha Agarwal +**🙏 Ειδικές ευχαριστίες 🙏 στους Microsoft Student Ambassador συγγραφείς, κριτές και συνεισφέροντες περιεχομένου**, ιδιαίτερα Rishit Dagli, Muhammad Sakib Khan Inan, Rohan Raj, Alexandru Petrescu, Abhishek Jaiswal, Nawrin Tabassum, Ioan Samuila, και Snigdha Agarwal -**🤩 Επιπλέον ευγνωμοσύνη στους Microsoft Student Ambassadors Eric Wanjau, Jasleen Sondhi, και Vidushi Gupta για τα μαθήματα R!** +**🤩 Επιπλέον ευγνωμοσύνη στους Microsoft Student Ambassadors Eric Wanjau, Jasleen Sondhi, και Vidushi Gupta για τα μαθήματα R μας!** # Ξεκινώντας Ακολουθήστε αυτά τα βήματα: -1. **Κάντε Fork το αποθετήριο**: Κάντε κλικ στο κουμπί "Fork" στην επάνω δεξιά γωνία αυτής της σελίδας. -2. **Κλωνοποιήστε (Clone) το αποθετήριο**: `git clone https://github.com/microsoft/ML-For-Beginners.git` +1. **Fork το Αποθετήριο**: Κάντε κλικ στο κουμπί "Fork" πάνω δεξιά σε αυτή τη σελίδα. +2. **Clone το Αποθετήριο**: `git clone https://github.com/microsoft/ML-For-Beginners.git` -> [βρείτε όλους τους επιπλέον πόρους για αυτό το μάθημα στη συλλογή Microsoft Learn](https://learn.microsoft.com/en-us/collections/qrqzamz1nn2wx3?WT.mc_id=academic-77952-bethanycheum) +> [βρείτε όλους τους πρόσθετους πόρους για αυτό το μάθημα στη συλλογή Microsoft Learn](https://learn.microsoft.com/en-us/collections/qrqzamz1nn2wx3?WT.mc_id=academic-77952-bethanycheum) -> 🔧 **Χρειάζεστε βοήθεια;** Ελέγξτε τον [Οδηγό αντιμετώπισης προβλημάτων](TROUBLESHOOTING.md) για λύσεις σε κοινά ζητήματα με την εγκατάσταση, τη ρύθμιση και την εκτέλεση των μαθημάτων. +> 🔧 **Χρειάζεστε βοήθεια;** Δείτε τον [Οδηγό Αντιμετώπισης Προβλημάτων](TROUBLESHOOTING.md) για λύσεις σε κοινά προβλήματα εγκατάστασης, ρύθμισης και εκτέλεσης μαθημάτων. **[Φοιτητές](https://aka.ms/student-page)**, για να χρησιμοποιήσετε αυτό το πρόγραμμα σπουδών, κάντε fork ολόκληρου του repo στον δικό σας λογαριασμό GitHub και ολοκληρώστε τις ασκήσεις μόνοι σας ή με μια ομάδα: -- Ξεκινήστε με ένα προ-διάλεξη κουίζ. -- Διαβάστε τη διάλεξη και ολοκληρώστε τις δραστηριότητες, σταματώντας και σκεπτόμενοι σε κάθε έλεγχο γνώσης. -- Προσπαθήστε να δημιουργήσετε τα έργα κατανοώντας τα μαθήματα αντί να τρέχετε τον κώδικα λύσης· ωστόσο, αυτός ο κώδικας είναι διαθέσιμος στους φακέλους `/solution` σε κάθε μάθημα προσανατολισμένο σε έργα. -- Κάντε το μετα-διάλεξη κουίζ. +- Ξεκινήστε με ένα προ-διάλεξης κουίζ. +- Διαβάστε τη διάλεξη και ολοκληρώστε τις δραστηριότητες, σταματώντας και αναλογιζόμενοι σε κάθε έλεγχο γνώσης. +- Προσπαθήστε να δημιουργήσετε τα έργα κατανοώντας τα μαθήματα αντί να εκτελείτε απλώς τον κώδικα της λύσης· ωστόσο, αυτός ο κώδικας είναι διαθέσιμος στους φακέλους `/solution` σε κάθε μάθημα προσανατολισμένο σε έργο. +- Δώστε το μετα-διάλεξης κουίζ. - Ολοκληρώστε την πρόκληση. -- Ολοκληρώστε την ανάθεση. -- Αφού ολοκληρώσετε μια ομάδα μαθημάτων, επισκεφθείτε το [Discussion Board](https://github.com/microsoft/ML-For-Beginners/discussions) και "μάθετε δυνατά" συμπληρώνοντας το κατάλληλο PAT rubric. Ένα 'PAT' είναι ένα Εργαλείο Αξιολόγησης Προόδου που είναι ένα rubric που συμπληρώνετε για να προωθήσετε τη μάθησή σας. Μπορείτε επίσης να αντιδράσετε σε άλλα PATs ώστε να μάθουμε μαζί. +- Ολοκληρώστε την εργασία. +- Αφού ολοκληρώσετε μια ομάδα μαθημάτων, επισκεφθείτε το [Discussion Board](https://github.com/microsoft/ML-For-Beginners/discussions) και "μάθετε φωναχτά" συμπληρώνοντας το κατάλληλο PAT rubric. Ένα 'PAT' είναι ένα Εργαλείο Αξιολόγησης Προόδου (Progress Assessment Tool) που είναι ένα rubric που συμπληρώνετε για να ενισχύσετε τη μάθησή σας. Μπορείτε επίσης να αντιδράσετε σε άλλα PAT ώστε να μάθουμε μαζί. -> Για περαιτέρω μελέτη, προτείνουμε να ακολουθήσετε αυτά τα [Microsoft Learn](https://docs.microsoft.com/en-us/users/jenlooper-2911/collections/k7o7tg1gp306q4?WT.mc_id=academic-77952-leestott) modules και learning paths. +> Για περαιτέρω μελέτη, προτείνουμε να ακολουθήσετε αυτά τα [Microsoft Learn](https://docs.microsoft.com/en-us/users/jenlooper-2911/collections/k7o7tg1gp306q4?WT.mc_id=academic-77952-leestott) μαθήματα και διαδρομές μάθησης. -**Καθηγητές**, έχουμε [συμπεριλάβει μερικές προτάσεις](for-teachers.md) για το πώς να χρησιμοποιήσετε αυτό το πρόγραμμα σπουδών. +**Καθηγητές**, έχουμε [συμπεριλάβει μερικές προτάσεις](for-teachers.md) σχετικά με το πώς να χρησιμοποιήσετε αυτό το πρόγραμμα σπουδών. --- -## Βίντεο-οδηγίες +## Περιηγήσεις βίντεο -Μερικά από τα μαθήματα είναι διαθέσιμα ως σύντομα βίντεο. Μπορείτε να βρείτε όλα αυτά ενσωματωμένα στα μαθήματα, ή στη [λίστα αναπαραγωγής ML for Beginners στο κανάλι Microsoft Developer YouTube](https://aka.ms/ml-beginners-videos) κάνοντας κλικ στην εικόνα παρακάτω. +Μερικά από τα μαθήματα είναι διαθέσιμα ως βίντεο σύντομης μορφής. Μπορείτε να βρείτε όλα αυτά ενσωματωμένα στα μαθήματα, ή στη [playlist ML for Beginners στο κανάλι Microsoft Developer στο YouTube](https://aka.ms/ml-beginners-videos) κάνοντας κλικ στην εικόνα παρακάτω. -[![Πανό ML για Αρχάριους](../../translated_images/ml-for-beginners-video-banner.63f694a100034bc6251134294459696e070a3a9a04632e9fe6a24aa0de4a7384.el.png)](https://aka.ms/ml-beginners-videos) +[![Μπάνερ ML για αρχάριους](../../translated_images/ml-for-beginners-video-banner.63f694a100034bc6.el.png)](https://aka.ms/ml-beginners-videos) --- @@ -98,67 +98,67 @@ CO_OP_TRANSLATOR_METADATA: Επιλέξαμε δύο παιδαγωγικές αρχές κατά την κατασκευή αυτού του προγράμματος: να είναι πρακτικό και βασισμένο σε έργα (**project-based**) και να περιλαμβάνει **συχνά κουίζ**. Επιπλέον, αυτό το πρόγραμμα έχει ένα κοινό **θέμα** για να του δώσει συνοχή. -Εξασφαλίζοντας ότι το περιεχόμενο ευθυγραμμίζεται με έργα, η διαδικασία γίνεται πιο ελκυστική για τους μαθητές και η διατήρηση εννοιών θα ενισχυθεί. Επιπλέον, ένα χαμηλού κινδύνου κουίζ πριν από ένα μάθημα καθορίζει την πρόθεση του μαθητή προς τη μάθηση ενός θέματος, ενώ ένα δεύτερο κουίζ μετά το μάθημα διασφαλίζει περαιτέρω διατήρηση. Αυτό το πρόγραμμα σχεδιάστηκε για να είναι ευέλικτο και διασκεδαστικό και μπορεί να παρακολουθηθεί ολόκληρο ή κατά τμήματα. Τα έργα ξεκινούν μικρά και γίνονται ολοένα και πιο σύνθετα μέχρι το τέλος του κύκλου των 12 εβδομάδων. Αυτό το πρόγραμμα περιλαμβάνει επίσης επίμετρο για τις εφαρμογές της ΜΜ στον πραγματικό κόσμο, το οποίο μπορεί να χρησιμοποιηθεί ως επιπλέον βαθμολογία ή ως βάση για συζήτηση. +Διασφαλίζοντας ότι το περιεχόμενο στοχεύει σε έργα, η διαδικασία γίνεται πιο ελκυστική για τους μαθητές και θα αυξηθεί η διατήρηση των εννοιών. Επιπλέον, ένα χαμηλού ρίσκου κουίζ πριν από μια τάξη θέτει την πρόθεση του μαθητή προς την εκμάθηση ενός θέματος, ενώ ένα δεύτερο κουίζ μετά την τάξη διασφαλίζει περαιτέρω διατήρηση. Αυτό το πρόγραμμα σχεδιάστηκε να είναι ευέλικτο και διασκεδαστικό και μπορεί να ολοκληρωθεί ολόκληρο ή μεμονωμένα τμήματα. Τα έργα ξεκινούν μικρά και γίνονται ολοένα και πιο σύνθετα μέχρι το τέλος του κύκλου των 12 εβδομάδων. Αυτό το πρόγραμμα περιλαμβάνει επίσης ένα επίμετρο για εφαρμογές πραγματικού κόσμου της ML, που μπορεί να χρησιμοποιηθεί ως επιπλέον εργασία ή ως βάση για συζήτηση. -> Βρείτε τους [Κανόνες Συμπεριφοράς](CODE_OF_CONDUCT.md), [Συνεισφορά](CONTRIBUTING.md), [Μετάφραση](TRANSLATIONS.md), και [Οδηγίες Αντιμετώπισης Προβλημάτων](TROUBLESHOOTING.md). Καλωσορίζουμε την εποικοδομητική σας ανατροφοδότηση! +> Βρείτε τον [Κώδικα Συμπεριφοράς](CODE_OF_CONDUCT.md), [Οδηγίες Συμμετοχής](CONTRIBUTING.md), [Μετάφρασης](TRANSLATIONS.md), και [Αντιμετώπισης Προβλημάτων](TROUBLESHOOTING.md). Καλωσορίζουμε την εποικοδομητική σας ανατροφοδότηση! ## Κάθε μάθημα περιλαμβάνει - προαιρετικό sketchnote - προαιρετικό συμπληρωματικό βίντεο - βίντεο-περιήγηση (σε μερικά μαθήματα μόνο) -- [προ-διάλεξη warmup κουίζ](https://ff-quizzes.netlify.app/en/ml/) +- [προ-διάλεξης warmup κουίζ](https://ff-quizzes.netlify.app/en/ml/) - γραπτό μάθημα -- για μαθήματα προσανατολισμένα σε έργα, βήμα-προς-βήμα οδηγούς για το πώς να κατασκευάσετε το έργο -- ελέγχους γνώσης +- για μαθήματα που βασίζονται σε έργα, βήμα-βήμα οδηγίες για το πώς να χτίσετε το έργο +- έλεγχοι γνώσης - μια πρόκληση - συμπληρωματική ανάγνωση -- ανάθεση -- [μετα-διάλεξη κουίζ](https://ff-quizzes.netlify.app/en/ml/) +- εργασία +- [μετα-διάλεξης κουίζ](https://ff-quizzes.netlify.app/en/ml/) -> **Σημείωση για τις γλώσσες**: Αυτά τα μαθήματα είναι κυρίως γραμμένα σε Python, αλλά πολλά είναι επίσης διαθέσιμα σε R. Για να ολοκληρώσετε ένα μάθημα R, μεταβείτε στον φάκελο `/solution` και αναζητήστε μαθήματα R. Περιλαμβάνουν την επέκταση .rmd που αντιπροσωπεύει ένα **R Markdown** αρχείο το οποίο μπορεί να οριστεί απλά ως ενσωμάτωση των `code chunks` (of R or other languages) και ενός `YAML header` (που καθοδηγεί τον τρόπο μορφοποίησης εξόδων όπως PDF) σε ένα `Markdown document`. Ως εκ τούτου, λειτουργεί ως ένα εξαιρετικό πλαίσιο συγγραφής για την επιστήμη δεδομένων καθώς σας επιτρέπει να συνδυάσετε τον κώδικα σας, την έξοδό του και τις σκέψεις σας επιτρέποντάς σας να τα γράψετε σε Markdown. Επιπλέον, τα R Markdown έγγραφα μπορούν να αποδοθούν σε μορφές εξόδου όπως PDF, HTML, ή Word. +> **Μια σημείωση σχετικά με τις γλώσσες**: Τα μαθήματα αυτά είναι κυρίως γραμμένα σε Python, αλλά πολλά είναι επίσης διαθέσιμα σε R. Για να ολοκληρώσετε ένα μάθημα R, πηγαίνετε στον φάκελο `/solution` και αναζητήστε μαθήματα R. Περιλαμβάνουν μια επέκταση .rmd που αντιπροσωπεύει ένα **R Markdown** αρχείο το οποίο μπορεί να οριστεί απλά ως ενσωμάτωση `code chunks` (σε R ή άλλες γλώσσες) και ένα `YAML header` (που καθοδηγεί πώς να μορφοποιηθούν εξαγωγές όπως PDF) σε ένα `Markdown document`. Ως τέτοιο, χρησιμεύει ως ένα υποδειγματικό πλαίσιο συγγραφής για την επιστήμη δεδομένων καθώς σας επιτρέπει να συνδυάζετε τον κώδικά σας, την έξοδό του, και τις σκέψεις σας γράφοντάς τες σε Markdown. Επιπλέον, τα έγγραφα R Markdown μπορούν να αποδοθούν σε μορφές εξόδου όπως PDF, HTML, ή Word. -> **Σημείωση για τα κουίζ**: Όλα τα κουίζ περιέχονται στον [φάκελο Quiz App](../../quiz-app), για συνολικά 52 κουίζ με τρεις ερωτήσεις το καθένα. Συνδέονται από τα μέσα των μαθημάτων αλλά η εφαρμογή κουίζ μπορεί να τρέξει τοπικά· ακολουθήστε τις οδηγίες στον φάκελο `quiz-app` για τοπική φιλοξενία ή ανάπτυξη στο Azure. +> **Μια σημείωση σχετικά με τα κουίζ**: Όλα τα κουίζ περιέχονται στον [φάκελο Quiz App](../../quiz-app), για συνολικά 52 κουίζ με τρεις ερωτήσεις το καθένα. Συνδέονται μέσα στα μαθήματα αλλά η εφαρμογή κουίζ μπορεί να τρέξει τοπικά· ακολουθήστε τις οδηγίες στον φάκελο `quiz-app` για τοπική φιλοξενία ή ανάπτυξη στο Azure. -| Αριθμός Μαθήματος | Θέμα | Ομαδοποίηση Μαθήματος | Στόχοι Μάθησης | Συνδεδεμένο Μάθημα | Συγγραφέας | +| Lesson Number | Topic | Lesson Grouping | Learning Objectives | Linked Lesson | Author | | :-----------: | :------------------------------------------------------------: | :-------------------------------------------------: | ------------------------------------------------------------------------------------------------------------------------------- | :--------------------------------------------------------------------------------------------------------------------------------------: | :--------------------------------------------------: | -| 01 | Εισαγωγή στη μηχανική μάθηση | [Εισαγωγή](1-Introduction/README.md) | Μάθετε τις βασικές έννοιες που βρίσκονται πίσω από τη μηχανική μάθηση | [Μάθημα](1-Introduction/1-intro-to-ML/README.md) | Muhammad | -| 02 | Ιστορία της μηχανικής μάθησης | [Εισαγωγή](1-Introduction/README.md) | Μάθετε την ιστορία που διέπει αυτόν τον τομέα | [Μάθημα](1-Introduction/2-history-of-ML/README.md) | Jen and Amy | -| 03 | Δικαιοσύνη και μηχανική μάθηση | [Εισαγωγή](1-Introduction/README.md) | Ποιες είναι οι σημαντικές φιλοσοφικές ερωτήσεις γύρω από τη δικαιοσύνη που οι μαθητές πρέπει να λάβουν υπόψη όταν δημιουργούν και εφαρμόζουν μοντέλα μηχανικής μάθησης; | [Μάθημα](1-Introduction/3-fairness/README.md) | Tomomi | -| 04 | Τεχνικές για τη μηχανική μάθηση | [Εισαγωγή](1-Introduction/README.md) | Ποιες τεχνικές χρησιμοποιούν οι ερευνητές ML για να δημιουργήσουν μοντέλα; | [Μάθημα](1-Introduction/4-techniques-of-ML/README.md) | Chris and Jen | +| 01 | Εισαγωγή στη μηχανική μάθηση | [Εισαγωγή](1-Introduction/README.md) | Μάθετε τις βασικές έννοιες πίσω από τη μηχανική μάθηση | [Μάθημα](1-Introduction/1-intro-to-ML/README.md) | Muhammad | +| 02 | Η ιστορία της μηχανικής μάθησης | [Εισαγωγή](1-Introduction/README.md) | Μάθετε την ιστορική εξέλιξη αυτού του πεδίου | [Μάθημα](1-Introduction/2-history-of-ML/README.md) | Jen and Amy | +| 03 | Δικαιοσύνη και μηχανική μάθηση | [Εισαγωγή](1-Introduction/README.md) | Ποια είναι τα σημαντικά φιλοσοφικά ζητήματα γύρω από τη δικαιοσύνη που θα πρέπει να λάβουν υπόψη τους οι μαθητές όταν κατασκευάζουν και εφαρμόζουν ML μοντέλα; | [Μάθημα](1-Introduction/3-fairness/README.md) | Tomomi | +| 04 | Τεχνικές για τη μηχανική μάθηση | [Εισαγωγή](1-Introduction/README.md) | Ποιες τεχνικές χρησιμοποιούν οι ερευνητές ML για να κατασκευάσουν μοντέλα ML; | [Μάθημα](1-Introduction/4-techniques-of-ML/README.md) | Chris and Jen | | 05 | Εισαγωγή στην παλινδρόμηση | [Παλινδρόμηση](2-Regression/README.md) | Ξεκινήστε με Python και Scikit-learn για μοντέλα παλινδρόμησης | [Python](2-Regression/1-Tools/README.md) • [R](../../2-Regression/1-Tools/solution/R/lesson_1.html) | Jen • Eric Wanjau | -| 06 | Τιμές κολοκύθας Βόρειας Αμερικής 🎃 | [Παλινδρόμηση](2-Regression/README.md) | Οπτικοποιήστε και καθαρίστε δεδομένα σε προετοιμασία για ML | [Python](2-Regression/2-Data/README.md) • [R](../../2-Regression/2-Data/solution/R/lesson_2.html) | Jen • Eric Wanjau | -| 07 | Τιμές κολοκύθας Βόρειας Αμερικής 🎃 | [Παλινδρόμηση](2-Regression/README.md) | Δημιουργήστε γραμμικά και πολυωνυμικά μοντέλα παλινδρόμησης | [Python](2-Regression/3-Linear/README.md) • [R](../../2-Regression/3-Linear/solution/R/lesson_3.html) | Jen and Dmitry • Eric Wanjau | -| 08 | Τιμές κολοκύθας Βόρειας Αμερικής 🎃 | [Παλινδρόμηση](2-Regression/README.md) | Δημιουργήστε ένα μοντέλο λογιστικής παλινδρόμησης | [Python](2-Regression/4-Logistic/README.md) • [R](../../2-Regression/4-Logistic/solution/R/lesson_4.html) | Jen • Eric Wanjau | -| 09 | Μια Web εφαρμογή 🔌 | [Web Εφαρμογή](3-Web-App/README.md) | Δημιουργήστε μια web εφαρμογή για να χρησιμοποιήσετε το εκπαιδευμένο μοντέλο σας | [Python](3-Web-App/1-Web-App/README.md) | Jen | -| 10 | Εισαγωγή στην ταξινόμηση | [Ταξινόμηση](4-Classification/README.md) | Καθαρίστε, προετοιμάστε και οπτικοποιήστε τα δεδομένα σας; εισαγωγή στην ταξινόμηση | [Python](4-Classification/1-Introduction/README.md) • [R](../../4-Classification/1-Introduction/solution/R/lesson_10.html) | Jen and Cassie • Eric Wanjau | -| 11 | Νόστιμες ασιατικές και ινδικές κουζίνες 🍜 | [Ταξινόμηση](4-Classification/README.md) | Εισαγωγή στους ταξινομητές | [Python](4-Classification/2-Classifiers-1/README.md) • [R](../../4-Classification/2-Classifiers-1/solution/R/lesson_11.html) | Jen and Cassie • Eric Wanjau | -| 12 | Νόστιμες ασιατικές και ινδικές κουζίνες 🍜 | [Ταξινόμηση](4-Classification/README.md) | Περισσότεροι ταξινομητές | [Python](4-Classification/3-Classifiers-2/README.md) • [R](../../4-Classification/3-Classifiers-2/solution/R/lesson_12.html) | Jen and Cassie • Eric Wanjau | -| 13 | Νόστιμες ασιατικές και ινδικές κουζίνες 🍜 | [Ταξινόμηση](4-Classification/README.md) | Δημιουργήστε μια web εφαρμογή συστάσεων χρησιμοποιώντας το μοντέλο σας | [Python](4-Classification/4-Applied/README.md) | Jen | -| 14 | Εισαγωγή στην ομαδοποίηση | [Ομαδοποίηση](5-Clustering/README.md) | Καθαρίστε, προετοιμάστε και οπτικοποιήστε τα δεδομένα σας; εισαγωγή στην ομαδοποίηση | [Python](5-Clustering/1-Visualize/README.md) • [R](../../5-Clustering/1-Visualize/solution/R/lesson_14.html) | Jen • Eric Wanjau | +| 06 | Τιμές κολοκύθας στη Βόρεια Αμερική 🎃 | [Παλινδρόμηση](2-Regression/README.md) | Οπτικοποιήστε και καθαρίστε δεδομένα σε προετοιμασία για ML | [Python](2-Regression/2-Data/README.md) • [R](../../2-Regression/2-Data/solution/R/lesson_2.html) | Jen • Eric Wanjau | +| 07 | Τιμές κολοκύθας στη Βόρεια Αμερική 🎃 | [Παλινδρόμηση](2-Regression/README.md) | Κατασκευάστε γραμμικά και πολυωνυμικά μοντέλα παλινδρόμησης | [Python](2-Regression/3-Linear/README.md) • [R](../../2-Regression/3-Linear/solution/R/lesson_3.html) | Jen και Dmitry • Eric Wanjau | +| 08 | Τιμές κολοκύθας στη Βόρεια Αμερική 🎃 | [Παλινδρόμηση](2-Regression/README.md) | Κατασκευάστε ένα μοντέλο λογιστικής παλινδρόμησης | [Python](2-Regression/4-Logistic/README.md) • [R](../../2-Regression/4-Logistic/solution/R/lesson_4.html) | Jen • Eric Wanjau | +| 09 | Μια εφαρμογή Web 🔌 | [Εφαρμογή Web](3-Web-App/README.md) | Δημιουργήστε μια εφαρμογή web για να χρησιμοποιήσετε το εκπαιδευμένο σας μοντέλο | [Python](3-Web-App/1-Web-App/README.md) | Jen | +| 10 | Εισαγωγή στην ταξινόμηση | [Ταξινόμηση](4-Classification/README.md) | Καθαρίστε, προετοιμάστε και οπτικοποιήστε τα δεδομένα σας; εισαγωγή στην ταξινόμηση | [Python](4-Classification/1-Introduction/README.md) • [R](../../4-Classification/1-Introduction/solution/R/lesson_10.html) | Jen και Cassie • Eric Wanjau | +| 11 | Νόστιμες Ασιατικές και Ινδικές κουζίνες 🍜 | [Ταξινόμηση](4-Classification/README.md) | Εισαγωγή στους ταξινομητές | [Python](4-Classification/2-Classifiers-1/README.md) • [R](../../4-Classification/2-Classifiers-1/solution/R/lesson_11.html) | Jen και Cassie • Eric Wanjau | +| 12 | Νόστιμες Ασιατικές και Ινδικές κουζίνες 🍜 | [Ταξινόμηση](4-Classification/README.md) | Περισσότεροι ταξινομητές | [Python](4-Classification/3-Classifiers-2/README.md) • [R](../../4-Classification/3-Classifiers-2/solution/R/lesson_12.html) | Jen και Cassie • Eric Wanjau | +| 13 | Νόστιμες Ασιατικές και Ινδικές κουζίνες 🍜 | [Ταξινόμηση](4-Classification/README.md) | Κατασκευάστε μια εφαρμογή web συστάσεων χρησιμοποιώντας το μοντέλο σας | [Python](4-Classification/4-Applied/README.md) | Jen | +| 14 | Εισαγωγή στην ομαδοποίηση | [Ομαδοποίηση](5-Clustering/README.md) | Καθαρίστε, προετοιμάστε και οπτικοποιήστε τα δεδομένα σας; Εισαγωγή στην ομαδοποίηση | [Python](5-Clustering/1-Visualize/README.md) • [R](../../5-Clustering/1-Visualize/solution/R/lesson_14.html) | Jen • Eric Wanjau | | 15 | Εξερεύνηση μουσικών προτιμήσεων της Νιγηρίας 🎧 | [Ομαδοποίηση](5-Clustering/README.md) | Εξερευνήστε τη μέθοδο ομαδοποίησης K-Means | [Python](5-Clustering/2-K-Means/README.md) • [R](../../5-Clustering/2-K-Means/solution/R/lesson_15.html) | Jen • Eric Wanjau | -| 16 | Εισαγωγή στην επεξεργασία φυσικής γλώσσας ☕️ | [Επεξεργασία φυσικής γλώσσας](6-NLP/README.md) | Μάθετε τα βασικά για την επεξεργασία φυσικής γλώσσας δημιουργώντας ένα απλό bot | [Python](6-NLP/1-Introduction-to-NLP/README.md) | Stephen | -| 17 | Συνήθεις εργασίες NLP ☕️ | [Επεξεργασία φυσικής γλώσσας](6-NLP/README.md) | Εμβαθύνετε τις γνώσεις σας στην επεξεργασία φυσικής γλώσσας κατανοώντας τις συνηθισμένες εργασίες που απαιτούνται όταν χειρίζεστε δομές γλώσσας | [Python](6-NLP/2-Tasks/README.md) | Stephen | -| 18 | Μετάφραση και ανάλυση συναισθήματος ♥️ | [Επεξεργασία φυσικής γλώσσας](6-NLP/README.md) | Μετάφραση και ανάλυση συναισθήματος με Jane Austen | [Python](6-NLP/3-Translation-Sentiment/README.md) | Stephen | +| 16 | Εισαγωγή στην επεξεργασία φυσικής γλώσσας ☕️ | [Επεξεργασία φυσικής γλώσσας](6-NLP/README.md) | Μάθετε τα βασικά για την Επεξεργασία Φυσικής Γλώσσας δημιουργώντας ένα απλό bot | [Python](6-NLP/1-Introduction-to-NLP/README.md) | Stephen | +| 17 | Συνήθεις εργασίες NLP ☕️ | [Επεξεργασία φυσικής γλώσσας](6-NLP/README.md) | Εμβαθύνετε τις γνώσεις σας στην NLP κατανοώντας κοινές εργασίες που απαιτούνται όταν χειρίζεστε δομές γλώσσας | [Python](6-NLP/2-Tasks/README.md) | Stephen | +| 18 | Μετάφραση και ανάλυση συναισθήματος ♥️ | [Επεξεργασία φυσικής γλώσσας](6-NLP/README.md) | Μετάφραση και ανάλυση συναισθήματος με κείμενα της Jane Austen | [Python](6-NLP/3-Translation-Sentiment/README.md) | Stephen | | 19 | Ρομαντικά ξενοδοχεία της Ευρώπης ♥️ | [Επεξεργασία φυσικής γλώσσας](6-NLP/README.md) | Ανάλυση συναισθήματος με κριτικές ξενοδοχείων 1 | [Python](6-NLP/4-Hotel-Reviews-1/README.md) | Stephen | | 20 | Ρομαντικά ξενοδοχεία της Ευρώπης ♥️ | [Επεξεργασία φυσικής γλώσσας](6-NLP/README.md) | Ανάλυση συναισθήματος με κριτικές ξενοδοχείων 2 | [Python](6-NLP/5-Hotel-Reviews-2/README.md) | Stephen | | 21 | Εισαγωγή στην πρόβλεψη χρονοσειρών | [Χρονοσειρές](7-TimeSeries/README.md) | Εισαγωγή στην πρόβλεψη χρονοσειρών | [Python](7-TimeSeries/1-Introduction/README.md) | Francesca | -| 22 | ⚡️ Κατανάλωση ρεύματος παγκοσμίως ⚡️ - πρόβλεψη χρονοσειρών με ARIMA | [Χρονοσειρές](7-TimeSeries/README.md) | Πρόβλεψη χρονοσειρών με ARIMA | [Python](7-TimeSeries/2-ARIMA/README.md) | Francesca | -| 23 | ⚡️ Κατανάλωση ρεύματος παγκοσμίως ⚡️ - πρόβλεψη χρονοσειρών με SVR | [Χρονοσειρές](7-TimeSeries/README.md) | Πρόβλεψη χρονοσειρών με Support Vector Regressor | [Python](7-TimeSeries/3-SVR/README.md) | Anirban | +| 22 | ⚡️ Κατανάλωση ενέργειας παγκοσμίως ⚡️ - πρόβλεψη χρονοσειρών με ARIMA | [Χρονοσειρές](7-TimeSeries/README.md) | Πρόβλεψη χρονοσειρών με ARIMA | [Python](7-TimeSeries/2-ARIMA/README.md) | Francesca | +| 23 | ⚡️ Κατανάλωση ενέργειας παγκοσμίως ⚡️ - πρόβλεψη χρονοσειρών με SVR | [Χρονοσειρές](7-TimeSeries/README.md) | Πρόβλεψη χρονοσειρών με Support Vector Regressor | [Python](7-TimeSeries/3-SVR/README.md) | Anirban | | 24 | Εισαγωγή στην ενισχυτική μάθηση | [Ενισχυτική μάθηση](8-Reinforcement/README.md) | Εισαγωγή στην ενισχυτική μάθηση με Q-Learning | [Python](8-Reinforcement/1-QLearning/README.md) | Dmitry | | 25 | Βοηθήστε τον Peter να αποφύγει τον λύκο! 🐺 | [Ενισχυτική μάθηση](8-Reinforcement/README.md) | Ενισχυτική μάθηση με Gym | [Python](8-Reinforcement/2-Gym/README.md) | Dmitry | -| Υστερόγραφο | Σενάρια και εφαρμογές ML στον πραγματικό κόσμο | [ML in the Wild](9-Real-World/README.md) | Ενδιαφέρουσες και αποκαλυπτικές εφαρμογές πραγματικού κόσμου της κλασικής ML | [Μάθημα](9-Real-World/1-Applications/README.md) | Team | -| Υστερόγραφο | Ανάλυση σφαλμάτων μοντέλων σε ML χρησιμοποιώντας το RAI dashboard | [ML in the Wild](9-Real-World/README.md) | Ανάλυση σφαλμάτων μοντέλων στη Μηχανική Μάθηση χρησιμοποιώντας συνιστώσες του Responsible AI dashboard | [Μάθημα](9-Real-World/2-Debugging-ML-Models/README.md) | Ruth Yakubu | +| Υστερόγραφο | Σενάρια ML στον πραγματικό κόσμο και εφαρμογές | [ML στον πραγματικό κόσμο](9-Real-World/README.md) | Ενδιαφέρουσες και αποκαλυπτικές εφαρμογές κλασικής ML | [Μάθημα](9-Real-World/1-Applications/README.md) | Ομάδα | +| Υστερόγραφο | Εντοπισμός σφαλμάτων μοντέλων σε ML χρησιμοποιώντας RAI dashboard | [ML στον πραγματικό κόσμο](9-Real-World/README.md) | Εντοπισμός σφαλμάτων μοντέλων στη Μηχανική Μάθηση χρησιμοποιώντας συστατικά του Responsible AI dashboard | [Μάθημα](9-Real-World/2-Debugging-ML-Models/README.md) | Ruth Yakubu | -> [βρείτε όλους τους επιπλέον πόρους για αυτό το μάθημα στη συλλογή Microsoft Learn μας](https://learn.microsoft.com/en-us/collections/qrqzamz1nn2wx3?WT.mc_id=academic-77952-bethanycheum) +> [βρείτε όλους τους επιπλέον πόρους για αυτό το μάθημα στη συλλογή μας στο Microsoft Learn](https://learn.microsoft.com/en-us/collections/qrqzamz1nn2wx3?WT.mc_id=academic-77952-bethanycheum) ## Πρόσβαση εκτός σύνδεσης -Μπορείτε να τρέξετε αυτή την τεκμηρίωση εκτός σύνδεσης χρησιμοποιώντας το [Docsify](https://docsify.js.org/#/). Δημιουργήστε fork αυτού του αποθετηρίου, [εγκαταστήστε το Docsify](https://docsify.js.org/#/quickstart) στον τοπικό σας υπολογιστή, και στη συνέχεια στο ριζικό φάκελο αυτού του αποθετηρίου, πληκτρολογήστε `docsify serve`. Ο ιστότοπος θα σερβιριστεί στην θύρα 3000 στο localhost σας: `localhost:3000`. +Μπορείτε να τρέξετε αυτήν την τεκμηρίωση εκτός σύνδεσης χρησιμοποιώντας [Docsify](https://docsify.js.org/#/). Κλωνοποιήστε (Fork) αυτό το αποθετήριο, [εγκαταστήστε το Docsify](https://docsify.js.org/#/quickstart) στο τοπικό σας μηχάνημα, και στη συνέχεια στον ριζικό φάκελο αυτού του αποθετηρίου, πληκτρολογήστε `docsify serve`. Η ιστοσελίδα θα σερβίρεται στην πόρτα 3000 στο localhost σας: `localhost:3000`. ## Αρχεία PDF -Βρείτε ένα PDF του προγράμματος σπουδών με συνδέσμους [εδώ](https://microsoft.github.io/ML-For-Beginners/pdf/readme.pdf). +Βρείτε ένα pdf του προγράμματος σπουδών με συνδέσμους [εδώ](https://microsoft.github.io/ML-For-Beginners/pdf/readme.pdf). ## 🎒 Άλλα Μαθήματα @@ -167,28 +167,28 @@ CO_OP_TRANSLATOR_METADATA: ### LangChain -[![LangChain4j για Αρχάριους](https://img.shields.io/badge/LangChain4j%20for%20Beginners-22C55E?style=for-the-badge&&labelColor=E5E7EB&color=0553D6)](https://aka.ms/langchain4j-for-beginners) -[![LangChain.js για Αρχάριους](https://img.shields.io/badge/LangChain.js%20for%20Beginners-22C55E?style=for-the-badge&labelColor=E5E7EB&color=0553D6)](https://aka.ms/langchainjs-for-beginners?WT.mc_id=m365-94501-dwahlin) +[![LangChain4j για αρχάριους](https://img.shields.io/badge/LangChain4j%20for%20Beginners-22C55E?style=for-the-badge&&labelColor=E5E7EB&color=0553D6)](https://aka.ms/langchain4j-for-beginners) +[![LangChain.js για αρχάριους](https://img.shields.io/badge/LangChain.js%20for%20Beginners-22C55E?style=for-the-badge&labelColor=E5E7EB&color=0553D6)](https://aka.ms/langchainjs-for-beginners?WT.mc_id=m365-94501-dwahlin) --- -### Azure / Edge / MCP / Agents -[![AZD για Αρχάριους](https://img.shields.io/badge/AZD%20for%20Beginners-0078D4?style=for-the-badge&labelColor=E5E7EB&color=0078D4)](https://github.com/microsoft/AZD-for-beginners?WT.mc_id=academic-105485-koreyst) -[![Edge AI για Αρχάριους](https://img.shields.io/badge/Edge%20AI%20for%20Beginners-00B8E4?style=for-the-badge&labelColor=E5E7EB&color=00B8E4)](https://github.com/microsoft/edgeai-for-beginners?WT.mc_id=academic-105485-koreyst) -[![MCP για Αρχάριους](https://img.shields.io/badge/MCP%20for%20Beginners-009688?style=for-the-badge&labelColor=E5E7EB&color=009688)](https://github.com/microsoft/mcp-for-beginners?WT.mc_id=academic-105485-koreyst) -[![AI Agents για Αρχάριους](https://img.shields.io/badge/AI%20Agents%20for%20Beginners-00C49A?style=for-the-badge&labelColor=E5E7EB&color=00C49A)](https://github.com/microsoft/ai-agents-for-beginners?WT.mc_id=academic-105485-koreyst) +### Azure / Edge / MCP / Πράκτορες +[![AZD για αρχάριους](https://img.shields.io/badge/AZD%20for%20Beginners-0078D4?style=for-the-badge&labelColor=E5E7EB&color=0078D4)](https://github.com/microsoft/AZD-for-beginners?WT.mc_id=academic-105485-koreyst) +[![Edge AI για αρχάριους](https://img.shields.io/badge/Edge%20AI%20for%20Beginners-00B8E4?style=for-the-badge&labelColor=E5E7EB&color=00B8E4)](https://github.com/microsoft/edgeai-for-beginners?WT.mc_id=academic-105485-koreyst) +[![MCP για αρχάριους](https://img.shields.io/badge/MCP%20for%20Beginners-009688?style=for-the-badge&labelColor=E5E7EB&color=009688)](https://github.com/microsoft/mcp-for-beginners?WT.mc_id=academic-105485-koreyst) +[![AI Agents για αρχάριους](https://img.shields.io/badge/AI%20Agents%20for%20Beginners-00C49A?style=for-the-badge&labelColor=E5E7EB&color=00C49A)](https://github.com/microsoft/ai-agents-for-beginners?WT.mc_id=academic-105485-koreyst) --- ### Σειρά Generative AI -[![Generative AI για Αρχάριους](https://img.shields.io/badge/Generative%20AI%20for%20Beginners-8B5CF6?style=for-the-badge&labelColor=E5E7EB&color=8B5CF6)](https://github.com/microsoft/generative-ai-for-beginners?WT.mc_id=academic-105485-koreyst) +[![Generative AI για αρχάριους](https://img.shields.io/badge/Generative%20AI%20for%20Beginners-8B5CF6?style=for-the-badge&labelColor=E5E7EB&color=8B5CF6)](https://github.com/microsoft/generative-ai-for-beginners?WT.mc_id=academic-105485-koreyst) [![Generative AI (.NET)](https://img.shields.io/badge/Generative%20AI%20(.NET)-9333EA?style=for-the-badge&labelColor=E5E7EB&color=9333EA)](https://github.com/microsoft/Generative-AI-for-beginners-dotnet?WT.mc_id=academic-105485-koreyst) [![Γενετική Τεχνητή Νοημοσύνη (Java)](https://img.shields.io/badge/Generative%20AI%20(Java)-C084FC?style=for-the-badge&labelColor=E5E7EB&color=C084FC)](https://github.com/microsoft/generative-ai-for-beginners-java?WT.mc_id=academic-105485-koreyst) [![Γενετική Τεχνητή Νοημοσύνη (JavaScript)](https://img.shields.io/badge/Generative%20AI%20(JavaScript)-E879F9?style=for-the-badge&labelColor=E5E7EB&color=E879F9)](https://github.com/microsoft/generative-ai-with-javascript?WT.mc_id=academic-105485-koreyst) --- -### Κύρια Μαθήματα +### Βασικά Μαθήματα [![Μηχανική Μάθηση για Αρχάριους](https://img.shields.io/badge/ML%20for%20Beginners-22C55E?style=for-the-badge&labelColor=E5E7EB&color=22C55E)](https://aka.ms/ml-beginners?WT.mc_id=academic-105485-koreyst) [![Επιστήμη Δεδομένων για Αρχάριους](https://img.shields.io/badge/Data%20Science%20for%20Beginners-84CC16?style=for-the-badge&labelColor=E5E7EB&color=84CC16)](https://aka.ms/datascience-beginners?WT.mc_id=academic-105485-koreyst) [![Τεχνητή Νοημοσύνη για Αρχάριους](https://img.shields.io/badge/AI%20for%20Beginners-A3E635?style=for-the-badge&labelColor=E5E7EB&color=A3E635)](https://aka.ms/ai-beginners?WT.mc_id=academic-105485-koreyst) @@ -200,18 +200,18 @@ CO_OP_TRANSLATOR_METADATA: --- ### Σειρά Copilot -[![Copilot για Συνεργατικό Προγραμματισμό με ΤΝ](https://img.shields.io/badge/Copilot%20for%20AI%20Paired%20Programming-FACC15?style=for-the-badge&labelColor=E5E7EB&color=FACC15)](https://aka.ms/GitHubCopilotAI?WT.mc_id=academic-105485-koreyst) +[![Copilot για Προγραμματισμό σε Ζευγάρι με Τεχνητή Νοημοσύνη](https://img.shields.io/badge/Copilot%20for%20AI%20Paired%20Programming-FACC15?style=for-the-badge&labelColor=E5E7EB&color=FACC15)](https://aka.ms/GitHubCopilotAI?WT.mc_id=academic-105485-koreyst) [![Copilot για C#/.NET](https://img.shields.io/badge/Copilot%20for%20C%23/.NET-FBBF24?style=for-the-badge&labelColor=E5E7EB&color=FBBF24)](https://github.com/microsoft/mastering-github-copilot-for-dotnet-csharp-developers?WT.mc_id=academic-105485-koreyst) [![Περιπέτεια Copilot](https://img.shields.io/badge/Copilot%20Adventure-FDE68A?style=for-the-badge&labelColor=E5E7EB&color=FDE68A)](https://github.com/microsoft/CopilotAdventures?WT.mc_id=academic-105485-koreyst) ## Λήψη Βοήθειας -Εάν κολλήσετε ή έχετε οποιεσδήποτε ερωτήσεις σχετικά με την ανάπτυξη εφαρμογών ΤΝ. Συμμετάσχετε με άλλους μαθητές και έμπειρους προγραμματιστές σε συζητήσεις σχετικά με το MCP. Πρόκειται για μια υποστηρικτική κοινότητα όπου οι ερωτήσεις είναι ευπρόσδεκτες και η γνώση μοιράζεται ελεύθερα. +Εάν κολλήσετε ή έχετε οποιεσδήποτε ερωτήσεις σχετικά με τη δημιουργία εφαρμογών τεχνητής νοημοσύνης. Συμμετάσχετε μαζί με άλλους μαθητές και έμπειρους προγραμματιστές σε συζητήσεις σχετικά με το MCP. Είναι μια υποστηρικτική κοινότητα όπου οι ερωτήσεις είναι ευπρόσδεκτες και η γνώση μοιράζεται ελεύθερα. -[![Microsoft Foundry στο Discord](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) +[![Discord του Microsoft Foundry](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) -Εάν έχετε σχόλια για το προϊόν ή σφάλματα κατά τη διάρκεια της ανάπτυξης επισκεφθείτε: +Εάν έχετε σχόλια για το προϊόν ή σφάλματα κατά τη διάρκεια της δημιουργίας, επισκεφτείτε: [![Φόρουμ Προγραμματιστών Microsoft Foundry](https://img.shields.io/badge/GitHub-Microsoft_Foundry_Developer_Forum-blue?style=for-the-badge&logo=github&color=000000&logoColor=fff)](https://aka.ms/foundry/forum) @@ -219,5 +219,5 @@ CO_OP_TRANSLATOR_METADATA: Αποποίηση ευθυνών: -Αυτό το έγγραφο έχει μεταφραστεί χρησιμοποιώντας υπηρεσία αυτόματης μετάφρασης με τεχνητή νοημοσύνη Co-op Translator (https://github.com/Azure/co-op-translator). Παρότι επιδιώκουμε την ακρίβεια, παρακαλούμε να έχετε υπόψη ότι οι αυτόματες μεταφράσεις ενδέχεται να περιέχουν σφάλματα ή ανακρίβειες. Το πρωτότυπο έγγραφο στη γλώσσα του πρέπει να θεωρείται η αυθεντική πηγή. Για κρίσιμες πληροφορίες συνιστάται επαγγελματική ανθρώπινη μετάφραση. Δεν φέρουμε ευθύνη για οποιεσδήποτε παρεξηγήσεις ή λανθασμένες ερμηνείες που μπορεί να προκύψουν από τη χρήση αυτής της μετάφρασης. +Αυτό το έγγραφο έχει μεταφραστεί χρησιμοποιώντας την υπηρεσία αυτόματης μετάφρασης με τεχνητή νοημοσύνη [Co-op Translator](https://github.com/Azure/co-op-translator). Παρά τις προσπάθειές μας για ακρίβεια, παρακαλούμε λάβετε υπόψη ότι οι αυτοματοποιημένες μεταφράσεις ενδέχεται να περιέχουν σφάλματα ή ανακρίβειες. Το πρωτότυπο έγγραφο στη γλώσσα του πρέπει να θεωρείται η αυθεντική/επίσημη πηγή. Για κρίσιμες πληροφορίες, συνιστάται επαγγελματική ανθρώπινη μετάφραση. Δεν φέρουμε καμία ευθύνη για τυχόν παρεξηγήσεις ή λανθασμένες ερμηνείες που προκύπτουν από τη χρήση αυτής της μετάφρασης. \ No newline at end of file diff --git a/translations/en/2-Regression/1-Tools/solution/R/lesson_1-R.ipynb b/translations/en/2-Regression/1-Tools/solution/R/lesson_1-R.ipynb index 9ba800111..1d46e621b 100644 --- a/translations/en/2-Regression/1-Tools/solution/R/lesson_1-R.ipynb +++ b/translations/en/2-Regression/1-Tools/solution/R/lesson_1-R.ipynb @@ -48,7 +48,7 @@ " width=\"630\"/>\n", "
Artwork by @allison_horst
\n", "\n", - "\n" + "\n" ], "metadata": { "id": "LWNNzfqd6feZ" diff --git a/translations/en/2-Regression/2-Data/solution/R/lesson_2-R.ipynb b/translations/en/2-Regression/2-Data/solution/R/lesson_2-R.ipynb index d99b133d6..ef761f8fc 100644 --- a/translations/en/2-Regression/2-Data/solution/R/lesson_2-R.ipynb +++ b/translations/en/2-Regression/2-Data/solution/R/lesson_2-R.ipynb @@ -49,7 +49,7 @@ "
Artwork by @allison_horst
\n", "\n", "\n", - "\n" + "\n" ], "metadata": { "id": "Pg5aexcOPqAZ" @@ -230,7 +230,7 @@ "
Illustration by @allison_horst
\n", "\n", "\n", - "\n" + "\n" ], "metadata": { "id": "o4jLY5-VZO2C" @@ -531,7 +531,7 @@ "
Infographic by Dasani Madipalli
\n", "\n", "\n", - "\n", + "\n", "\n", "There’s a *wise* saying that goes like this:\n", "\n", diff --git a/translations/en/2-Regression/3-Linear/solution/R/lesson_3-R.ipynb b/translations/en/2-Regression/3-Linear/solution/R/lesson_3-R.ipynb index 4a1f8ba04..9b1f4470d 100644 --- a/translations/en/2-Regression/3-Linear/solution/R/lesson_3-R.ipynb +++ b/translations/en/2-Regression/3-Linear/solution/R/lesson_3-R.ipynb @@ -42,7 +42,7 @@ "
Infographic by Dasani Madipalli
\n", "\n", "\n", - "\n", + "\n", "\n", "#### Introduction\n", "\n", @@ -166,7 +166,7 @@ "
Artwork by @allison_horst
\n", "\n", "\n", - "\n" + "\n" ], "metadata": { "id": "WdUKXk7Bs8-V" @@ -809,7 +809,7 @@ "
Infographic by Dasani Madipalli
\n", "\n", "\n", - "\n" + "\n" ], "metadata": { "id": "HOCqJXLTwtWI" diff --git a/translations/en/2-Regression/4-Logistic/solution/R/lesson_4-R.ipynb b/translations/en/2-Regression/4-Logistic/solution/R/lesson_4-R.ipynb index cd3edfc92..2e392c5c5 100644 --- a/translations/en/2-Regression/4-Logistic/solution/R/lesson_4-R.ipynb +++ b/translations/en/2-Regression/4-Logistic/solution/R/lesson_4-R.ipynb @@ -6,7 +6,7 @@ "source": [ "## Build a logistic regression model - Lesson 4\n", "\n", - "![Logistic vs. linear regression infographic](../../../../../../translated_images/linear-vs-logistic.ba180bf95e7ee66721ba10ebf2dac2666acbd64a88b003c83928712433a13c7d.en.png)\n", + "![Logistic vs. linear regression infographic](../../../../../../translated_images/linear-vs-logistic.ba180bf95e7ee667.en.png)\n", "\n", "#### **[Pre-lecture quiz](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/15/)**\n", "\n", @@ -78,7 +78,7 @@ "\n", "Logistic regression doesn't provide the same functionality as linear regression. The former predicts a `binary category` (\"orange or not orange\"), while the latter can predict `continuous values`, such as estimating *how much the price of a pumpkin will increase* based on its origin and harvest time.\n", "\n", - "![Infographic by Dasani Madipalli](../../../../../../translated_images/pumpkin-classifier.562771f104ad5436b87d1c67bca02a42a17841133556559325c0a0e348e5b774.en.png)\n", + "![Infographic by Dasani Madipalli](../../../../../../translated_images/pumpkin-classifier.562771f104ad5436.en.png)\n", "\n", "### Other classifications\n", "\n", @@ -88,7 +88,7 @@ "\n", "- **Ordinal**, which involves ordered categories. This is useful if we want to logically rank our outcomes, such as pumpkins categorized by a finite set of sizes (mini, sm, med, lg, xl, xxl).\n", "\n", - "![Multinomial vs ordinal regression](../../../../../../translated_images/multinomial-vs-ordinal.36701b4850e37d86c9dd49f7bef93a2f94dbdb8fe03443eb68f0542f97f28f29.en.png)\n", + "![Multinomial vs ordinal regression](../../../../../../translated_images/multinomial-vs-ordinal.36701b4850e37d86.en.png)\n", "\n", "#### **Variables DO NOT have to correlate**\n", "\n", diff --git a/translations/en/README.md b/translations/en/README.md index 4a1539605..1b5bf8f41 100644 --- a/translations/en/README.md +++ b/translations/en/README.md @@ -1,8 +1,8 @@ Disclaimer: -This document has been translated using the AI translation service Co-op Translator (https://github.com/Azure/co-op-translator). While we strive for accuracy, please be aware that automated translations may contain errors or inaccuracies. The original document in its native language should be considered the authoritative source. For critical information, professional human translation is recommended. We are not liable for any misunderstandings or misinterpretations arising from the use of this translation. +This document has been translated using AI translation service Co-op Translator (https://github.com/Azure/co-op-translator). While we strive for accuracy, please be aware that automated translations may contain errors or inaccuracies. The original document in its native language should be considered the authoritative source. For critical information, professional human translation is recommended. We are not liable for any misunderstandings or misinterpretations arising from the use of this translation. \ No newline at end of file diff --git a/translations/es/1-Introduction/README.md b/translations/es/1-Introduction/README.md index 914dc5fcd..ad697428a 100644 --- a/translations/es/1-Introduction/README.md +++ b/translations/es/1-Introduction/README.md @@ -11,7 +11,7 @@ CO_OP_TRANSLATOR_METADATA: En esta sección del plan de estudios, se te presentarán los conceptos básicos que sustentan el campo del aprendizaje automático, qué es, y aprenderás sobre su historia y las técnicas que los investigadores utilizan para trabajar con él. ¡Exploremos juntos este nuevo mundo del aprendizaje automático! -![globo](../../../translated_images/globe.59f26379ceb40428672b4d9a568044618a2bf6292ecd53a5c481b90e3fa805eb.es.jpg) +![globo](../../../translated_images/globe.59f26379ceb40428.es.jpg) > Foto de Bill Oxford en Unsplash ### Lecciones diff --git a/translations/es/2-Regression/1-Tools/solution/R/lesson_1-R.ipynb b/translations/es/2-Regression/1-Tools/solution/R/lesson_1-R.ipynb index 82d60f976..35cd6db11 100644 --- a/translations/es/2-Regression/1-Tools/solution/R/lesson_1-R.ipynb +++ b/translations/es/2-Regression/1-Tools/solution/R/lesson_1-R.ipynb @@ -48,7 +48,7 @@ " width=\"630\"/>\n", "
Obra de @allison_horst
\n", "\n", - "\n" + "\n" ], "metadata": { "id": "LWNNzfqd6feZ" diff --git a/translations/es/2-Regression/2-Data/solution/R/lesson_2-R.ipynb b/translations/es/2-Regression/2-Data/solution/R/lesson_2-R.ipynb index 7a59a002c..9906af24e 100644 --- a/translations/es/2-Regression/2-Data/solution/R/lesson_2-R.ipynb +++ b/translations/es/2-Regression/2-Data/solution/R/lesson_2-R.ipynb @@ -50,7 +50,7 @@ "
Obra de @allison_horst
\n", "\n", "\n", - "\n" + "\n" ], "metadata": { "id": "Pg5aexcOPqAZ" @@ -536,7 +536,7 @@ "
Infografía por Dasani Madipalli
\n", "\n", "\n", - "\n", + "\n", "\n", "Hay un dicho *sabio* que dice así:\n", "\n", diff --git a/translations/es/2-Regression/3-Linear/solution/R/lesson_3-R.ipynb b/translations/es/2-Regression/3-Linear/solution/R/lesson_3-R.ipynb index 80fe8fd65..f7022f74a 100644 --- a/translations/es/2-Regression/3-Linear/solution/R/lesson_3-R.ipynb +++ b/translations/es/2-Regression/3-Linear/solution/R/lesson_3-R.ipynb @@ -456,7 +456,7 @@ "
Ilustración por @allison_horst
\n", "\n", "\n", - "\n" + "\n" ], "metadata": { "id": "KEiO0v7kuC9O" @@ -570,7 +570,7 @@ "
Infografía por Dasani Madipalli
\n", "\n", "\n", - "\n" + "\n" ], "metadata": { "id": "YqXjLuWavNxW" @@ -811,7 +811,7 @@ "
Infografía por Dasani Madipalli
\n", "\n", "\n", - "\n" + "\n" ], "metadata": { "id": "HOCqJXLTwtWI" diff --git a/translations/es/2-Regression/4-Logistic/solution/R/lesson_4-R.ipynb b/translations/es/2-Regression/4-Logistic/solution/R/lesson_4-R.ipynb index 0c38bcf17..6d38a1af7 100644 --- a/translations/es/2-Regression/4-Logistic/solution/R/lesson_4-R.ipynb +++ b/translations/es/2-Regression/4-Logistic/solution/R/lesson_4-R.ipynb @@ -6,7 +6,7 @@ "source": [ "## Construir un modelo de regresión logística - Lección 4\n", "\n", - "![Infografía de regresión logística vs. regresión lineal](../../../../../../translated_images/linear-vs-logistic.ba180bf95e7ee66721ba10ebf2dac2666acbd64a88b003c83928712433a13c7d.es.png)\n", + "![Infografía de regresión logística vs. regresión lineal](../../../../../../translated_images/linear-vs-logistic.ba180bf95e7ee667.es.png)\n", "\n", "#### **[Cuestionario previo a la lección](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/15/)**\n", "\n", @@ -78,7 +78,7 @@ "\n", "La regresión logística no ofrece las mismas características que la regresión lineal. La primera ofrece una predicción sobre una `categoría binaria` (\"naranja o no naranja\"), mientras que la segunda es capaz de predecir `valores continuos`, por ejemplo, dado el origen de una calabaza y el momento de la cosecha, *cuánto aumentará su precio*.\n", "\n", - "![Infografía por Dasani Madipalli](../../../../../../translated_images/pumpkin-classifier.562771f104ad5436b87d1c67bca02a42a17841133556559325c0a0e348e5b774.es.png)\n", + "![Infografía por Dasani Madipalli](../../../../../../translated_images/pumpkin-classifier.562771f104ad5436.es.png)\n", "\n", "### Otras clasificaciones\n", "\n", @@ -88,7 +88,7 @@ "\n", "- **Ordinal**, que implica categorías ordenadas, útil si quisiéramos ordenar nuestros resultados lógicamente, como nuestras calabazas que están ordenadas por un número finito de tamaños (mini,pequeño,mediano,grande,xl,xxl).\n", "\n", - "![Regresión multinomial vs ordinal](../../../../../../translated_images/multinomial-vs-ordinal.36701b4850e37d86c9dd49f7bef93a2f94dbdb8fe03443eb68f0542f97f28f29.es.png)\n", + "![Regresión multinomial vs ordinal](../../../../../../translated_images/multinomial-vs-ordinal.36701b4850e37d86.es.png)\n", "\n", "#### **Las variables NO tienen que correlacionarse**\n", "\n", diff --git a/translations/es/2-Regression/README.md b/translations/es/2-Regression/README.md index 2ad272091..e79e0961d 100644 --- a/translations/es/2-Regression/README.md +++ b/translations/es/2-Regression/README.md @@ -12,7 +12,7 @@ CO_OP_TRANSLATOR_METADATA: En América del Norte, las calabazas suelen tallarse con caras aterradoras para Halloween. ¡Descubramos más sobre estos fascinantes vegetales! -![jack-o-lanterns](../../../translated_images/jack-o-lanterns.181c661a9212457d7756f37219f660f1358af27554d856e5a991f16b4e15337c.es.jpg) +![jack-o-lanterns](../../../translated_images/jack-o-lanterns.181c661a9212457d.es.jpg) > Foto por Beth Teutschmann en Unsplash ## Lo que aprenderás diff --git a/translations/es/3-Web-App/README.md b/translations/es/3-Web-App/README.md index c25bf9f2b..ad495fec6 100644 --- a/translations/es/3-Web-App/README.md +++ b/translations/es/3-Web-App/README.md @@ -11,7 +11,7 @@ CO_OP_TRANSLATOR_METADATA: En esta sección del curso, se te presentará un tema práctico de aprendizaje automático: cómo guardar tu modelo de Scikit-learn como un archivo que pueda ser utilizado para hacer predicciones dentro de una aplicación web. Una vez que el modelo esté guardado, aprenderás cómo usarlo en una aplicación web construida con Flask. Primero, crearás un modelo utilizando algunos datos relacionados con avistamientos de OVNIs. Luego, construirás una aplicación web que te permitirá ingresar un número de segundos junto con un valor de latitud y longitud para predecir qué país reportó haber visto un OVNI. -![UFO Parking](../../../translated_images/ufo.9e787f5161da9d4d1dafc537e1da09be8210f2ee996cb638aa5cee1d92867a04.es.jpg) +![UFO Parking](../../../translated_images/ufo.9e787f5161da9d4d.es.jpg) Foto por Michael Herren en Unsplash diff --git a/translations/es/4-Classification/README.md b/translations/es/4-Classification/README.md index 17558342e..f4a37c0ce 100644 --- a/translations/es/4-Classification/README.md +++ b/translations/es/4-Classification/README.md @@ -13,7 +13,7 @@ CO_OP_TRANSLATOR_METADATA: En Asia e India, las tradiciones culinarias son extremadamente diversas y ¡muy deliciosas! Vamos a analizar datos sobre cocinas regionales para tratar de entender sus ingredientes. -![Vendedor de comida tailandesa](../../../translated_images/thai-food.c47a7a7f9f05c21892a1f9dc7bf30669e6d18dfda420c5c7ebb4153f6a304edd.es.jpg) +![Vendedor de comida tailandesa](../../../translated_images/thai-food.c47a7a7f9f05c218.es.jpg) > Foto de Lisheng Chang en Unsplash ## Lo que aprenderás diff --git a/translations/es/5-Clustering/README.md b/translations/es/5-Clustering/README.md index 11b4221b3..328646871 100644 --- a/translations/es/5-Clustering/README.md +++ b/translations/es/5-Clustering/README.md @@ -15,7 +15,7 @@ El agrupamiento es una tarea de aprendizaje automático que busca encontrar obje La diversa audiencia de Nigeria tiene gustos musicales variados. Usando datos extraídos de Spotify (inspirados en [este artículo](https://towardsdatascience.com/country-wise-visual-analysis-of-music-taste-using-spotify-api-seaborn-in-python-77f5b749b421)), analicemos algo de la música popular en Nigeria. Este conjunto de datos incluye información sobre el puntaje de 'bailabilidad', 'acústica', volumen, 'hablabilidad', popularidad y energía de varias canciones. ¡Será interesante descubrir patrones en estos datos! -![Un tocadiscos](../../../translated_images/turntable.f2b86b13c53302dc106aa741de9dc96ac372864cf458dd6f879119857aab01da.es.jpg) +![Un tocadiscos](../../../translated_images/turntable.f2b86b13c53302dc.es.jpg) > Foto de Marcela Laskoski en Unsplash diff --git a/translations/es/6-NLP/README.md b/translations/es/6-NLP/README.md index 6048f910b..486232a93 100644 --- a/translations/es/6-NLP/README.md +++ b/translations/es/6-NLP/README.md @@ -17,7 +17,7 @@ En esta sección del programa, se te presentará uno de los usos más extendidos En estas lecciones aprenderemos los conceptos básicos del NLP construyendo pequeños bots conversacionales para entender cómo el aprendizaje automático ayuda a que estas conversaciones sean cada vez más 'inteligentes'. Viajarás en el tiempo, conversando con Elizabeth Bennett y el Sr. Darcy del clásico de Jane Austen, **Orgullo y Prejuicio**, publicado en 1813. Luego, ampliarás tus conocimientos aprendiendo sobre el análisis de sentimientos a través de reseñas de hoteles en Europa. -![Libro de Orgullo y Prejuicio y té](../../../translated_images/p&p.279f1c49ecd889419e4ce6206525e9aa30d32a976955cd24daa636c361c6391f.es.jpg) +![Libro de Orgullo y Prejuicio y té](../../../translated_images/p&p.279f1c49ecd88941.es.jpg) > Foto por Elaine Howlin en Unsplash ## Lecciones diff --git a/translations/es/7-TimeSeries/README.md b/translations/es/7-TimeSeries/README.md index 929f27cea..5ce830bd6 100644 --- a/translations/es/7-TimeSeries/README.md +++ b/translations/es/7-TimeSeries/README.md @@ -17,7 +17,7 @@ En estas dos lecciones, se te presentará la predicción de series temporales, u Nuestro enfoque regional es el uso eléctrico en el mundo, un conjunto de datos interesante para aprender sobre la predicción del consumo futuro de energía basado en patrones de carga pasados. Puedes ver cómo este tipo de predicción puede ser extremadamente útil en un entorno empresarial. -![red eléctrica](../../../translated_images/electric-grid.0c21d5214db09ffae93c06a87ca2abbb9ba7475ef815129c5b423d7f9a7cf136.es.jpg) +![red eléctrica](../../../translated_images/electric-grid.0c21d5214db09ffa.es.jpg) Foto de [Peddi Sai hrithik](https://unsplash.com/@shutter_log?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText) de torres eléctricas en una carretera en Rajasthan en [Unsplash](https://unsplash.com/s/photos/electric-india?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText) diff --git a/translations/es/8-Reinforcement/README.md b/translations/es/8-Reinforcement/README.md index 40508cad1..b8f4d7070 100644 --- a/translations/es/8-Reinforcement/README.md +++ b/translations/es/8-Reinforcement/README.md @@ -13,7 +13,7 @@ El aprendizaje por refuerzo, RL, se considera uno de los paradigmas básicos del Imagina que tienes un entorno simulado como el mercado de valores. ¿Qué sucede si impones una regulación específica? ¿Tiene un efecto positivo o negativo? Si ocurre algo negativo, necesitas tomar este _refuerzo negativo_, aprender de ello y cambiar de rumbo. Si el resultado es positivo, necesitas construir sobre ese _refuerzo positivo_. -![Pedro y el lobo](../../../translated_images/peter.779730f9ba3a8a8d9290600dcf55f2e491c0640c785af7ac0d64f583c49b8864.es.png) +![Pedro y el lobo](../../../translated_images/peter.779730f9ba3a8a8d.es.png) > ¡Pedro y sus amigos necesitan escapar del lobo hambriento! Imagen por [Jen Looper](https://twitter.com/jenlooper) diff --git a/translations/es/9-Real-World/README.md b/translations/es/9-Real-World/README.md index 8cce4c820..3e22cc9fc 100644 --- a/translations/es/9-Real-World/README.md +++ b/translations/es/9-Real-World/README.md @@ -11,7 +11,7 @@ CO_OP_TRANSLATOR_METADATA: En esta sección del currículo, se te presentarán algunas aplicaciones reales del aprendizaje automático clásico. Hemos investigado en internet para encontrar artículos y documentos técnicos sobre aplicaciones que han utilizado estas estrategias, evitando redes neuronales, aprendizaje profundo e inteligencia artificial tanto como sea posible. Aprende cómo se utiliza el aprendizaje automático en sistemas empresariales, aplicaciones ecológicas, finanzas, arte y cultura, entre otros. -![chess](../../../translated_images/chess.e704a268781bdad85d1876b6c2295742fa0d856e7dcf3659147052df9d3db205.es.jpg) +![chess](../../../translated_images/chess.e704a268781bdad8.es.jpg) > Foto por Alexis Fauvet en Unsplash diff --git a/translations/es/README.md b/translations/es/README.md index f6ee61928..1d26180f1 100644 --- a/translations/es/README.md +++ b/translations/es/README.md @@ -1,87 +1,86 @@ [![Licencia de GitHub](https://img.shields.io/github/license/microsoft/ML-For-Beginners.svg)](https://github.com/microsoft/ML-For-Beginners/blob/master/LICENSE) -[![Colaboradores de GitHub](https://img.shields.io/github/contributors/microsoft/ML-For-Beginners.svg)](https://GitHub.com/microsoft/ML-For-Beginners/graphs/contributors/) -[![Issues de GitHub](https://img.shields.io/github/issues/microsoft/ML-For-Beginners.svg)](https://GitHub.com/microsoft/ML-For-Beginners/issues/) +[![Contribuidores de GitHub](https://img.shields.io/github/contributors/microsoft/ML-For-Beginners.svg)](https://GitHub.com/microsoft/ML-For-Beginners/graphs/contributors/) +[![Incidencias de GitHub](https://img.shields.io/github/issues/microsoft/ML-For-Beginners.svg)](https://GitHub.com/microsoft/ML-For-Beginners/issues/) [![Pull requests de GitHub](https://img.shields.io/github/issues-pr/microsoft/ML-For-Beginners.svg)](https://GitHub.com/microsoft/ML-For-Beginners/pulls/) -[![PRs bienvenidas](https://img.shields.io/badge/PRs-welcome-brightgreen.svg?style=flat-square)](http://makeapullrequest.com) +[![PRs Bienvenidos](https://img.shields.io/badge/PRs-welcome-brightgreen.svg?style=flat-square)](http://makeapullrequest.com) -[![Discord de Microsoft Foundry](https://img.shields.io/badge/PRs-welcome-brightgreen.svg?style=flat-square)](https://discord.gg/nTYy5BXMWG) [![Observadores de GitHub](https://img.shields.io/github/watchers/microsoft/ML-For-Beginners.svg?style=social&label=Watch)](https://GitHub.com/microsoft/ML-For-Beginners/watchers/) [![Forks de GitHub](https://img.shields.io/github/forks/microsoft/ML-For-Beginners.svg?style=social&label=Fork)](https://GitHub.com/microsoft/ML-For-Beginners/network/) [![Estrellas de GitHub](https://img.shields.io/github/stars/microsoft/ML-For-Beginners.svg?style=social&label=Star)](https://GitHub.com/microsoft/ML-For-Beginners/stargazers/) ### 🌐 Soporte multilingüe -#### Soportado mediante GitHub Action (Automatizado y siempre actualizado) +#### Compatible mediante GitHub Action (Automatizado y siempre actualizado) -[Árabe](../ar/README.md) | [Bengalí](../bn/README.md) | [Búlgaro](../bg/README.md) | [Birmano (Myanmar)](../my/README.md) | [Chino (Simplificado)](../zh/README.md) | [Chino (Tradicional, Hong Kong)](../hk/README.md) | [Chino (Tradicional, Macao)](../mo/README.md) | [Chino (Tradicional, Taiwán)](../tw/README.md) | [Croata](../hr/README.md) | [Checo](../cs/README.md) | [Danés](../da/README.md) | [Holandés](../nl/README.md) | [Estonio](../et/README.md) | [Finlandés](../fi/README.md) | [Francés](../fr/README.md) | [Alemán](../de/README.md) | [Griego](../el/README.md) | [Hebreo](../he/README.md) | [Hindi](../hi/README.md) | [Húngaro](../hu/README.md) | [Indonesio](../id/README.md) | [Italiano](../it/README.md) | [Japonés](../ja/README.md) | [Kannada](../kn/README.md) | [Coreano](../ko/README.md) | [Lituano](../lt/README.md) | [Malayo](../ms/README.md) | [Malayalam](../ml/README.md) | [Marathi](../mr/README.md) | [Nepalí](../ne/README.md) | [Pidgin nigeriano](../pcm/README.md) | [Noruego](../no/README.md) | [Persa (Farsi)](../fa/README.md) | [Polaco](../pl/README.md) | [Portugués (Brasil)](../br/README.md) | [Portugués (Portugal)](../pt/README.md) | [Punjabi (Gurmukhi)](../pa/README.md) | [Rumano](../ro/README.md) | [Ruso](../ru/README.md) | [Serbio (Cirílico)](../sr/README.md) | [Eslovaco](../sk/README.md) | [Esloveno](../sl/README.md) | [Español](./README.md) | [Swahili](../sw/README.md) | [Sueco](../sv/README.md) | [Tagalo (Filipino)](../tl/README.md) | [Tamil](../ta/README.md) | [Telugú](../te/README.md) | [Tailandés](../th/README.md) | [Turco](../tr/README.md) | [Ucraniano](../uk/README.md) | [Urdu](../ur/README.md) | [Vietnamita](../vi/README.md) +[Árabe](../ar/README.md) | [Bengalí](../bn/README.md) | [Búlgaro](../bg/README.md) | [Birmano (Myanmar)](../my/README.md) | [Chino (simplificado)](../zh/README.md) | [Chino (tradicional, Hong Kong)](../hk/README.md) | [Chino (tradicional, Macao)](../mo/README.md) | [Chino (tradicional, Taiwán)](../tw/README.md) | [Croata](../hr/README.md) | [Checo](../cs/README.md) | [Danés](../da/README.md) | [Neerlandés](../nl/README.md) | [Estonio](../et/README.md) | [Finés](../fi/README.md) | [Francés](../fr/README.md) | [Alemán](../de/README.md) | [Griego](../el/README.md) | [Hebreo](../he/README.md) | [Hindi](../hi/README.md) | [Húngaro](../hu/README.md) | [Indonesio](../id/README.md) | [Italiano](../it/README.md) | [Japonés](../ja/README.md) | [Kannada](../kn/README.md) | [Coreano](../ko/README.md) | [Lituano](../lt/README.md) | [Malayo](../ms/README.md) | [Malayalam](../ml/README.md) | [Maratí](../mr/README.md) | [Nepalí](../ne/README.md) | [Pidgin nigeriano](../pcm/README.md) | [Noruego](../no/README.md) | [Persa (Farsi)](../fa/README.md) | [Polaco](../pl/README.md) | [Portugués (Brasil)](../br/README.md) | [Portugués (Portugal)](../pt/README.md) | [Punjabi (Gurmukhi)](../pa/README.md) | [Rumano](../ro/README.md) | [Ruso](../ru/README.md) | [Serbio (cirílico)](../sr/README.md) | [Eslovaco](../sk/README.md) | [Esloveno](../sl/README.md) | [Español](./README.md) | [Swahili](../sw/README.md) | [Sueco](../sv/README.md) | [Tagalo (filipino)](../tl/README.md) | [Tamil](../ta/README.md) | [Telugu](../te/README.md) | [Tailandés](../th/README.md) | [Turco](../tr/README.md) | [Ucraniano](../uk/README.md) | [Urdu](../ur/README.md) | [Vietnamita](../vi/README.md) #### Únete a nuestra comunidad [![Discord de Microsoft Foundry](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) -Tenemos una serie en Discord "Learn with AI" en curso, obtén más información y únete a nosotros en [Serie Aprende con IA](https://aka.ms/learnwithai/discord) del 18 al 30 de septiembre de 2025. Recibirás consejos y trucos para usar GitHub Copilot para Ciencia de Datos. +Tenemos una serie en Discord "Learn with AI" en curso; obtén más información y únete a nosotros en [Serie Aprende con IA](https://aka.ms/learnwithai/discord) del 18 al 30 de septiembre de 2025. Obtendrás consejos y trucos para usar GitHub Copilot para Data Science. -![Serie Aprende con IA](../../translated_images/3.9b58fd8d6c373c20c588c5070c4948a826ab074426c28ceb5889641294373dfc.es.png) +![Serie Aprende con IA](../../translated_images/3.9b58fd8d6c373c20.es.png) # Aprendizaje automático para principiantes - Un plan de estudios -> 🌍 Viaja alrededor del mundo mientras exploramos el aprendizaje automático a través de las culturas del mundo 🌍 +> 🌍 Viaja por el mundo mientras exploramos el aprendizaje automático a través de las culturas del mundo 🌍 -Los Cloud Advocates de Microsoft se complacen en ofrecer un plan de estudios de 12 semanas y 26 lecciones sobre **Aprendizaje Automático**. En este plan de estudios, aprenderás sobre lo que a veces se denomina **aprendizaje automático clásico**, utilizando principalmente Scikit-learn como biblioteca y evitando el aprendizaje profundo, que se cubre en nuestro [currículo 'IA para Principiantes'](https://aka.ms/ai4beginners). ¡Combina estas lecciones con nuestro [plan de estudios 'Ciencia de Datos para Principiantes'](https://aka.ms/ds4beginners) también! +Los Cloud Advocates de Microsoft se complacen en ofrecer un plan de estudios de 12 semanas y 26 lecciones centrado en el **Aprendizaje automático**. En este plan de estudios, aprenderás sobre lo que a veces se denomina **aprendizaje automático clásico**, utilizando principalmente Scikit-learn como biblioteca y evitando el aprendizaje profundo, que se trata en nuestro [plan de estudios de AI for Beginners](https://aka.ms/ai4beginners). ¡Combina estas lecciones con nuestro [plan de estudios 'Data Science for Beginners'](https://aka.ms/ds4beginners) también! -Viaja con nosotros por el mundo mientras aplicamos estas técnicas clásicas a datos de muchas regiones del planeta. Cada lección incluye cuestionarios previo y posterior, instrucciones escritas para completar la lección, una solución, una tarea y más. Nuestra pedagogía basada en proyectos te permite aprender mientras construyes, una forma probada para que las nuevas habilidades se "fijen". +Viaja con nosotros por el mundo mientras aplicamos estas técnicas clásicas a datos de muchas regiones. Cada lección incluye cuestionarios previos y posteriores, instrucciones escritas para completar la lección, una solución, una tarea, y más. Nuestra pedagogía basada en proyectos te permite aprender mientras construyes, una forma probada para que las nuevas habilidades se "queden". -**✍️ Un sincero agradecimiento a nuestros autores** Jen Looper, Stephen Howell, Francesca Lazzeri, Tomomi Imura, Cassie Breviu, Dmitry Soshnikov, Chris Noring, Anirban Mukherjee, Ornella Altunyan, Ruth Yakubu and Amy Boyd +**✍️ Muchas gracias a nuestros autores** Jen Looper, Stephen Howell, Francesca Lazzeri, Tomomi Imura, Cassie Breviu, Dmitry Soshnikov, Chris Noring, Anirban Mukherjee, Ornella Altunyan, Ruth Yakubu y Amy Boyd -**🎨 Gracias también a nuestras ilustradoras** Tomomi Imura, Dasani Madipalli, and Jen Looper +**🎨 Gracias también a nuestras ilustradoras** Tomomi Imura, Dasani Madipalli y Jen Looper -**🙏 Agradecimientos especiales 🙏 a nuestros autores, revisores y contribuyentes de contenido Microsoft Student Ambassador**, notablemente Rishit Dagli, Muhammad Sakib Khan Inan, Rohan Raj, Alexandru Petrescu, Abhishek Jaiswal, Nawrin Tabassum, Ioan Samuila, and Snigdha Agarwal +**🙏 Agradecimiento especial 🙏 a nuestros autores, revisores y colaboradores de contenido que son Microsoft Student Ambassadors**, en particular Rishit Dagli, Muhammad Sakib Khan Inan, Rohan Raj, Alexandru Petrescu, Abhishek Jaiswal, Nawrin Tabassum, Ioan Samuila y Snigdha Agarwal -**🤩 Gratitud extra a los Microsoft Student Ambassadors Eric Wanjau, Jasleen Sondhi, y Vidushi Gupta por nuestras lecciones en R!** +**🤩 Gratitud extra a los Microsoft Student Ambassadors Eric Wanjau, Jasleen Sondhi y Vidushi Gupta por nuestras lecciones en R!** -# Cómo empezar +# Primeros pasos Sigue estos pasos: -1. **Bifurca el repositorio**: Haz clic en el botón "Fork" en la esquina superior derecha de esta página. +1. **Haz un fork del repositorio**: Haz clic en el botón "Fork" en la esquina superior derecha de esta página. 2. **Clona el repositorio**: `git clone https://github.com/microsoft/ML-For-Beginners.git` > [encuentra todos los recursos adicionales para este curso en nuestra colección de Microsoft Learn](https://learn.microsoft.com/en-us/collections/qrqzamz1nn2wx3?WT.mc_id=academic-77952-bethanycheum) -> 🔧 **¿Necesitas ayuda?** Consulta nuestra [Guía de solución de problemas](TROUBLESHOOTING.md) para soluciones a problemas comunes con la instalación, la configuración y la ejecución de las lecciones. +> 🔧 **¿Necesitas ayuda?** Consulta nuestra [Guía de solución de problemas](TROUBLESHOOTING.md) para soluciones a problemas comunes con la instalación, configuración y ejecución de las lecciones. -**[Estudiantes](https://aka.ms/student-page)**, para usar este plan de estudios, bifurca todo el repositorio en tu propia cuenta de GitHub y completa los ejercicios por tu cuenta o en grupo: +**[Estudiantes](https://aka.ms/student-page)**, para usar este plan de estudios, haz un fork de todo el repositorio a tu propia cuenta de GitHub y completa los ejercicios por tu cuenta o en grupo: - Comienza con un cuestionario previo a la lección. -- Lee la lección y completa las actividades, pausando y reflexionando en cada verificación de conocimientos. -- Intenta crear los proyectos comprendiendo las lecciones en lugar de ejecutar el código solución; sin embargo, ese código está disponible en las carpetas `/solution` en cada lección orientada a proyectos. +- Lee la lección y completa las actividades, pausando y reflexionando en cada verificación de conocimiento. +- Intenta crear los proyectos comprendiendo las lecciones en lugar de ejecutar el código de la solución; sin embargo, ese código está disponible en las carpetas `/solution` en cada lección orientada a proyectos. - Realiza el cuestionario posterior a la lección. - Completa el desafío. -- Realiza la tarea. -- Después de completar un grupo de lecciones, visita el [Tablero de discusión](https://github.com/microsoft/ML-For-Beginners/discussions) y "aprende en voz alta" completando la rúbrica PAT correspondiente. Un 'PAT' es una Herramienta de Evaluación de Progreso que es una rúbrica que completas para potenciar tu aprendizaje. También puedes reaccionar a otros PATs para que podamos aprender juntos. +- Completa la tarea. +- Después de completar un grupo de lecciones, visita el [Foro de discusión](https://github.com/microsoft/ML-For-Beginners/discussions) y "aprende en voz alta" completando la rúbrica PAT correspondiente. Un 'PAT' es una Progress Assessment Tool (Herramienta de Evaluación de Progreso) que es una rúbrica que completas para avanzar en tu aprendizaje. También puedes reaccionar a otros PATs para que podamos aprender juntos. -> Para un estudio adicional, recomendamos seguir estos módulos y rutas de aprendizaje de [Microsoft Learn](https://docs.microsoft.com/en-us/users/jenlooper-2911/collections/k7o7tg1gp306q4?WT.mc_id=academic-77952-leestott). +> Para un estudio más profundo, recomendamos seguir estos módulos y rutas de aprendizaje de [Microsoft Learn](https://docs.microsoft.com/en-us/users/jenlooper-2911/collections/k7o7tg1gp306q4?WT.mc_id=academic-77952-leestott). -**[Docentes](for-teachers.md)**, hemos incluido algunas sugerencias sobre cómo usar este plan de estudios. +**Docentes**, hemos [incluido algunas sugerencias](for-teachers.md) sobre cómo usar este plan de estudios. --- -## Guías en video +## Tutoriales en video -Algunas de las lecciones están disponibles en formato de video corto. Puedes encontrarlas en línea dentro de las lecciones, o en la [lista de reproducción ML for Beginners en el canal de YouTube de Microsoft Developer](https://aka.ms/ml-beginners-videos) haciendo clic en la imagen a continuación. +Algunas de las lecciones están disponibles en formato de video corto. Puedes encontrarlos integrados en las lecciones o en la [lista de reproducción ML for Beginners en el canal de Microsoft Developer en YouTube](https://aka.ms/ml-beginners-videos) haciendo clic en la imagen a continuación. -[![Banner de ML para principiantes](../../translated_images/ml-for-beginners-video-banner.63f694a100034bc6251134294459696e070a3a9a04632e9fe6a24aa0de4a7384.es.png)](https://aka.ms/ml-beginners-videos) +[![Banner de ML para principiantes](../../translated_images/ml-for-beginners-video-banner.63f694a100034bc6.es.png)](https://aka.ms/ml-beginners-videos) --- @@ -97,69 +96,69 @@ Algunas de las lecciones están disponibles en formato de video corto. Puedes en ## Pedagogía -Hemos elegido dos principios pedagógicos al crear este plan de estudios: asegurar que sea práctico y basado en **proyectos** y que incluya **cuestionarios frecuentes**. Además, este plan de estudios tiene un **tema** común para darle cohesión. +Hemos elegido dos principios pedagógicos al construir este plan de estudios: asegurar que sea práctico y basado en **proyectos** y que incluya **cuestionarios frecuentes**. Además, este plan de estudios tiene un **tema** común para darle cohesión. -Al garantizar que el contenido esté alineado con proyectos, el proceso se vuelve más atractivo para los estudiantes y la retención de conceptos se verá aumentada. Además, un cuestionario de baja presión antes de una clase establece la intención del estudiante hacia el aprendizaje de un tema, mientras que un segundo cuestionario después de la clase asegura una mayor retención. Este plan de estudios fue diseñado para ser flexible y divertido y puede tomarse en su totalidad o en parte. Los proyectos comienzan pequeños y se vuelven cada vez más complejos hacia el final del ciclo de 12 semanas. Este plan de estudios también incluye una posdata sobre las aplicaciones del ML en el mundo real, que puede utilizarse como crédito adicional o como base para la discusión. +Al asegurar que el contenido se alinee con proyectos, el proceso se vuelve más atractivo para los estudiantes y la retención de conceptos se incrementará. Además, un cuestionario de bajo riesgo antes de una clase orienta la intención del estudiante hacia el aprendizaje de un tema, mientras que un segundo cuestionario después de la clase asegura una mayor retención. Este plan de estudios fue diseñado para ser flexible y divertido y se puede tomar en su totalidad o en parte. Los proyectos comienzan pequeños y se vuelven cada vez más complejos al final del ciclo de 12 semanas. Este plan de estudios también incluye un postfacio sobre aplicaciones reales del ML, que puede usarse como crédito extra o como base para la discusión. -> Encuentra nuestras directrices de [Código de conducta](CODE_OF_CONDUCT.md), [Contribuir](CONTRIBUTING.md), [Traducción](TRANSLATIONS.md), y [Solución de problemas](TROUBLESHOOTING.md). ¡Agradecemos tus comentarios constructivos! +> Consulta nuestro [Código de conducta](CODE_OF_CONDUCT.md), [Contribuir](CONTRIBUTING.md), [Traducción](TRANSLATIONS.md) y [Solución de problemas](TROUBLESHOOTING.md). ¡Agradecemos tus comentarios constructivos! ## Cada lección incluye - sketchnote opcional - video complementario opcional -- video explicativo (solo algunas lecciones) +- recorrido en video (solo algunas lecciones) - [cuestionario de calentamiento previo a la lección](https://ff-quizzes.netlify.app/en/ml/) - lección escrita -- para las lecciones basadas en proyectos, guías paso a paso sobre cómo construir el proyecto -- verificaciones de conocimiento +- para lecciones basadas en proyectos, guías paso a paso sobre cómo construir el proyecto +- comprobaciones de conocimiento - un desafío -- lectura complementaria +- lecturas complementarias - tarea - [cuestionario posterior a la lección](https://ff-quizzes.netlify.app/en/ml/) -> **Una nota sobre los idiomas**: Estas lecciones están escritas principalmente en Python, pero muchas también están disponibles en R. Para completar una lección en R, ve a la carpeta `/solution` y busca las lecciones en R. Incluyen una extensión .rmd que representa un archivo **R Markdown** que puede definirse simplemente como una inserción de `code chunks` (de R u otros lenguajes) y un `YAML header` (que guía cómo formatear salidas como PDF) en un `Markdown document`. Como tal, sirve como un marco ejemplar de autoría para ciencia de datos, ya que te permite combinar tu código, su salida y tus ideas escribiéndolas en Markdown. Además, los documentos R Markdown pueden renderizarse a formatos de salida como PDF, HTML o Word. +> **Una nota sobre los idiomas**: Estas lecciones están principalmente escritas en Python, pero muchas también están disponibles en R. Para completar una lección en R, ve a la carpeta `/solution` y busca las lecciones en R. Incluyen una extensión .rmd que representa un archivo **R Markdown** que puede definirse simplemente como una inserción de `code chunks` (de R u otros lenguajes) y un `YAML header` (que guía cómo formatear salidas como PDF) en un `Markdown document`. Como tal, sirve como un marco de autoría ejemplar para la ciencia de datos, ya que permite combinar tu código, su salida y tus pensamientos permitiéndote escribirlos en Markdown. Además, los documentos R Markdown se pueden renderizar a formatos de salida como PDF, HTML o Word. -> **Una nota sobre los cuestionarios**: Todos los cuestionarios están contenidos en la [carpeta Quiz App](../../quiz-app), para un total de 52 cuestionarios de tres preguntas cada uno. Se enlazan desde dentro de las lecciones, pero la aplicación de cuestionarios puede ejecutarse localmente; sigue las instrucciones en la carpeta `quiz-app` para alojarla localmente o desplegarla en Azure. +> **Una nota sobre los cuestionarios**: Todos los cuestionarios están contenidos en la [carpeta Quiz App](../../quiz-app), para un total de 52 cuestionarios de tres preguntas cada uno. Están vinculados desde las lecciones, pero la aplicación de cuestionarios puede ejecutarse localmente; sigue las instrucciones en la carpeta `quiz-app` para alojarla localmente o desplegarla en Azure. | Número de lección | Tema | Agrupación de lecciones | Objetivos de aprendizaje | Lección vinculada | Autor | | :-----------: | :------------------------------------------------------------: | :-------------------------------------------------: | ------------------------------------------------------------------------------------------------------------------------------- | :--------------------------------------------------------------------------------------------------------------------------------------: | :--------------------------------------------------: | -| 01 | Introducción al aprendizaje automático | [Introducción](1-Introduction/README.md) | Aprende los conceptos básicos del aprendizaje automático | [Lección](1-Introduction/1-intro-to-ML/README.md) | Muhammad | -| 02 | La historia del aprendizaje automático | [Introducción](1-Introduction/README.md) | Aprende la historia que subyace en este campo | [Lección](1-Introduction/2-history-of-ML/README.md) | Jen and Amy | -| 03 | Equidad y aprendizaje automático | [Introducción](1-Introduction/README.md) | ¿Cuáles son las cuestiones filosóficas importantes sobre la equidad que los estudiantes deberían considerar al construir y aplicar modelos de aprendizaje automático? | [Lección](1-Introduction/3-fairness/README.md) | Tomomi | -| 04 | Técnicas para el aprendizaje automático | [Introducción](1-Introduction/README.md) | ¿Qué técnicas usan los investigadores de aprendizaje automático para crear modelos? | [Lección](1-Introduction/4-techniques-of-ML/README.md) | Chris and Jen | +| 01 | Introducción al aprendizaje automático | [Introducción](1-Introduction/README.md) | Aprende los conceptos básicos detrás del aprendizaje automático | [Lección](1-Introduction/1-intro-to-ML/README.md) | Muhammad | +| 02 | La historia del aprendizaje automático | [Introducción](1-Introduction/README.md) | Aprende la historia subyacente de este campo | [Lección](1-Introduction/2-history-of-ML/README.md) | Jen y Amy | +| 03 | Equidad y aprendizaje automático | [Introducción](1-Introduction/README.md) | ¿Cuáles son los importantes problemas filosóficos relacionados con la equidad que los estudiantes deben considerar al construir y aplicar modelos de ML? | [Lección](1-Introduction/3-fairness/README.md) | Tomomi | +| 04 | Técnicas para el aprendizaje automático | [Introducción](1-Introduction/README.md) | ¿Qué técnicas usan los investigadores de ML para construir modelos de ML? | [Lección](1-Introduction/4-techniques-of-ML/README.md) | Chris y Jen | | 05 | Introducción a la regresión | [Regresión](2-Regression/README.md) | Comienza con Python y Scikit-learn para modelos de regresión | [Python](2-Regression/1-Tools/README.md) • [R](../../2-Regression/1-Tools/solution/R/lesson_1.html) | Jen • Eric Wanjau | -| 06 | Precios de calabazas en América del Norte 🎃 | [Regresión](2-Regression/README.md) | Visualiza y limpia datos en preparación para el aprendizaje automático | [Python](2-Regression/2-Data/README.md) • [R](../../2-Regression/2-Data/solution/R/lesson_2.html) | Jen • Eric Wanjau | -| 07 | Precios de calabazas en América del Norte 🎃 | [Regresión](2-Regression/README.md) | Construye modelos de regresión lineal y polinómica | [Python](2-Regression/3-Linear/README.md) • [R](../../2-Regression/3-Linear/solution/R/lesson_3.html) | Jen and Dmitry • Eric Wanjau | -| 08 | Precios de calabazas en América del Norte 🎃 | [Regresión](2-Regression/README.md) | Construye un modelo de regresión logística | [Python](2-Regression/4-Logistic/README.md) • [R](../../2-Regression/4-Logistic/solution/R/lesson_4.html) | Jen • Eric Wanjau | +| 06 | Precios de calabazas en Norteamérica 🎃 | [Regresión](2-Regression/README.md) | Visualiza y limpia datos en preparación para ML | [Python](2-Regression/2-Data/README.md) • [R](../../2-Regression/2-Data/solution/R/lesson_2.html) | Jen • Eric Wanjau | +| 07 | Precios de calabazas en Norteamérica 🎃 | [Regresión](2-Regression/README.md) | Construye modelos de regresión lineal y polinómica | [Python](2-Regression/3-Linear/README.md) • [R](../../2-Regression/3-Linear/solution/R/lesson_3.html) | Jen y Dmitry • Eric Wanjau | +| 08 | Precios de calabazas en Norteamérica 🎃 | [Regresión](2-Regression/README.md) | Construye un modelo de regresión logística | [Python](2-Regression/4-Logistic/README.md) • [R](../../2-Regression/4-Logistic/solution/R/lesson_4.html) | Jen • Eric Wanjau | | 09 | Una aplicación web 🔌 | [Aplicación web](3-Web-App/README.md) | Crea una aplicación web para usar tu modelo entrenado | [Python](3-Web-App/1-Web-App/README.md) | Jen | -| 10 | Introducción a la clasificación | [Clasificación](4-Classification/README.md) | Limpia, prepara y visualiza tus datos; introducción a la clasificación | [Python](4-Classification/1-Introduction/README.md) • [R](../../4-Classification/1-Introduction/solution/R/lesson_10.html) | Jen and Cassie • Eric Wanjau | -| 11 | Deliciosas cocinas asiática e india 🍜 | [Clasificación](4-Classification/README.md) | Introducción a los clasificadores | [Python](4-Classification/2-Classifiers-1/README.md) • [R](../../4-Classification/2-Classifiers-1/solution/R/lesson_11.html) | Jen and Cassie • Eric Wanjau | -| 12 | Deliciosas cocinas asiática e india 🍜 | [Clasificación](4-Classification/README.md) | Más clasificadores | [Python](4-Classification/3-Classifiers-2/README.md) • [R](../../4-Classification/3-Classifiers-2/solution/R/lesson_12.html) | Jen and Cassie • Eric Wanjau | +| 10 | Introducción a la clasificación | [Clasificación](4-Classification/README.md) | Limpia, prepara y visualiza tus datos; introducción a la clasificación | [Python](4-Classification/1-Introduction/README.md) • [R](../../4-Classification/1-Introduction/solution/R/lesson_10.html) | Jen y Cassie • Eric Wanjau | +| 11 | Deliciosas cocinas asiática e india 🍜 | [Clasificación](4-Classification/README.md) | Introducción a los clasificadores | [Python](4-Classification/2-Classifiers-1/README.md) • [R](../../4-Classification/2-Classifiers-1/solution/R/lesson_11.html) | Jen y Cassie • Eric Wanjau | +| 12 | Deliciosas cocinas asiática e india 🍜 | [Clasificación](4-Classification/README.md) | Más clasificadores | [Python](4-Classification/3-Classifiers-2/README.md) • [R](../../4-Classification/3-Classifiers-2/solution/R/lesson_12.html) | Jen y Cassie • Eric Wanjau | | 13 | Deliciosas cocinas asiática e india 🍜 | [Clasificación](4-Classification/README.md) | Construye una aplicación web recomendadora usando tu modelo | [Python](4-Classification/4-Applied/README.md) | Jen | | 14 | Introducción al agrupamiento | [Agrupamiento](5-Clustering/README.md) | Limpia, prepara y visualiza tus datos; introducción al agrupamiento | [Python](5-Clustering/1-Visualize/README.md) • [R](../../5-Clustering/1-Visualize/solution/R/lesson_14.html) | Jen • Eric Wanjau | -| 15 | Explorando los gustos musicales de Nigeria 🎧 | [Agrupamiento](5-Clustering/README.md) | Explora el método de agrupamiento K-Means | [Python](5-Clustering/2-K-Means/README.md) • [R](../../5-Clustering/2-K-Means/solution/R/lesson_15.html) | Jen • Eric Wanjau | -| 16 | Introducción al procesamiento de lenguaje natural ☕️ | [Procesamiento de lenguaje natural](6-NLP/README.md) | Aprende los fundamentos del PLN construyendo un bot sencillo | [Python](6-NLP/1-Introduction-to-NLP/README.md) | Stephen | -| 17 | Tareas comunes de PLN ☕️ | [Procesamiento de lenguaje natural](6-NLP/README.md) | Profundiza tus conocimientos de PLN comprendiendo las tareas comunes requeridas al tratar con estructuras del lenguaje | [Python](6-NLP/2-Tasks/README.md) | Stephen | -| 18 | Traducción y análisis de sentimiento ♥️ | [Procesamiento de lenguaje natural](6-NLP/README.md) | Traducción y análisis de sentimiento con Jane Austen | [Python](6-NLP/3-Translation-Sentiment/README.md) | Stephen | -| 19 | Hoteles románticos de Europa ♥️ | [Procesamiento de lenguaje natural](6-NLP/README.md) | Análisis de sentimiento con reseñas de hoteles 1 | [Python](6-NLP/4-Hotel-Reviews-1/README.md) | Stephen | -| 20 | Hoteles románticos de Europa ♥️ | [Procesamiento de lenguaje natural](6-NLP/README.md) | Análisis de sentimiento con reseñas de hoteles 2 | [Python](6-NLP/5-Hotel-Reviews-2/README.md) | Stephen | -| 21 | Introducción al pronóstico de series temporales | [Series temporales](7-TimeSeries/README.md) | Introducción al pronóstico de series temporales | [Python](7-TimeSeries/1-Introduction/README.md) | Francesca | -| 22 | ⚡️ Uso de energía mundial ⚡️ - pronóstico de series temporales con ARIMA | [Series temporales](7-TimeSeries/README.md) | Pronóstico de series temporales con ARIMA | [Python](7-TimeSeries/2-ARIMA/README.md) | Francesca | -| 23 | ⚡️ Uso de energía mundial ⚡️ - pronóstico de series temporales con SVR | [Series temporales](7-TimeSeries/README.md) | Pronóstico de series temporales con Support Vector Regressor | [Python](7-TimeSeries/3-SVR/README.md) | Anirban | +| 15 | Explorando los gustos musicales nigerianos 🎧 | [Agrupamiento](5-Clustering/README.md) | Explora el método de agrupamiento K-Means | [Python](5-Clustering/2-K-Means/README.md) • [R](../../5-Clustering/2-K-Means/solution/R/lesson_15.html) | Jen • Eric Wanjau | +| 16 | Introducción al procesamiento de lenguaje natural ☕️ | [Procesamiento de lenguaje natural](6-NLP/README.md) | Aprende lo básico sobre NLP construyendo un bot sencillo | [Python](6-NLP/1-Introduction-to-NLP/README.md) | Stephen | +| 17 | Tareas comunes de NLP ☕️ | [Procesamiento de lenguaje natural](6-NLP/README.md) | Profundiza tus conocimientos de NLP comprendiendo las tareas comunes necesarias al trabajar con estructuras del lenguaje | [Python](6-NLP/2-Tasks/README.md) | Stephen | +| 18 | Traducción y análisis de sentimientos ♥️ | [Procesamiento de lenguaje natural](6-NLP/README.md) | Traducción y análisis de sentimientos con Jane Austen | [Python](6-NLP/3-Translation-Sentiment/README.md) | Stephen | +| 19 | Hoteles románticos de Europa ♥️ | [Procesamiento de lenguaje natural](6-NLP/README.md) | Análisis de sentimientos con reseñas de hoteles 1 | [Python](6-NLP/4-Hotel-Reviews-1/README.md) | Stephen | +| 20 | Hoteles románticos de Europa ♥️ | [Procesamiento de lenguaje natural](6-NLP/README.md) | Análisis de sentimientos con reseñas de hoteles 2 | [Python](6-NLP/5-Hotel-Reviews-2/README.md) | Stephen | +| 21 | Introducción a la previsión de series temporales | [Series temporales](7-TimeSeries/README.md) | Introducción a la previsión de series temporales | [Python](7-TimeSeries/1-Introduction/README.md) | Francesca | +| 22 | ⚡️ Consumo de energía mundial ⚡️ - previsión de series temporales con ARIMA | [Series temporales](7-TimeSeries/README.md) | Previsión de series temporales con ARIMA | [Python](7-TimeSeries/2-ARIMA/README.md) | Francesca | +| 23 | ⚡️ Consumo de energía mundial ⚡️ - previsión de series temporales con SVR | [Series temporales](7-TimeSeries/README.md) | Previsión de series temporales con Support Vector Regressor | [Python](7-TimeSeries/3-SVR/README.md) | Anirban | | 24 | Introducción al aprendizaje por refuerzo | [Aprendizaje por refuerzo](8-Reinforcement/README.md) | Introducción al aprendizaje por refuerzo con Q-Learning | [Python](8-Reinforcement/1-QLearning/README.md) | Dmitry | -| 25 | ¡Ayuda a Peter a evitar al lobo! 🐺 | [Aprendizaje por refuerzo](8-Reinforcement/README.md) | Aprendizaje por refuerzo con Gym | [Python](8-Reinforcement/2-Gym/README.md) | Dmitry | -| Postscript | Escenarios y aplicaciones del aprendizaje automático en el mundo real | [ML en el mundo real](9-Real-World/README.md) | Aplicaciones interesantes y reveladoras del aprendizaje automático clásico | [Lección](9-Real-World/1-Applications/README.md) | Equipo | -| Postscript | Depuración de modelos en ML usando el panel RAI | [ML en el mundo real](9-Real-World/README.md) | Depuración de modelos en aprendizaje automático usando componentes del panel Responsible AI | [Lección](9-Real-World/2-Debugging-ML-Models/README.md) | Ruth Yakubu | +| 25 | ¡Ayuda a Peter a evitar al lobo! 🐺 | [Aprendizaje por refuerzo](8-Reinforcement/README.md) | Gym de aprendizaje por refuerzo | [Python](8-Reinforcement/2-Gym/README.md) | Dmitry | +| Postscript | Escenarios y aplicaciones del aprendizaje automático en el mundo real | [ML en la vida real](9-Real-World/README.md) | Aplicaciones reales interesantes y reveladoras del ML clásico | [Lección](9-Real-World/1-Applications/README.md) | Equipo | +| Postscript | Depuración de modelos en ML usando el panel RAI | [ML en la vida real](9-Real-World/README.md) | Depuración de modelos en aprendizaje automático usando componentes del panel Responsible AI | [Lección](9-Real-World/2-Debugging-ML-Models/README.md) | Ruth Yakubu | -> [encuentra todos los recursos adicionales para este curso en nuestra colección de Microsoft Learn](https://learn.microsoft.com/en-us/collections/qrqzamz1nn2wx3?WT.mc_id=academic-77952-bethanycheum) +> [Encuentra todos los recursos adicionales para este curso en nuestra colección de Microsoft Learn](https://learn.microsoft.com/en-us/collections/qrqzamz1nn2wx3?WT.mc_id=academic-77952-bethanycheum) ## Acceso sin conexión -Puedes ejecutar esta documentación sin conexión utilizando [Docsify](https://docsify.js.org/#/). Haz un fork de este repositorio, [instala Docsify](https://docsify.js.org/#/quickstart) en tu máquina local, y luego en la carpeta raíz de este repositorio, escribe `docsify serve`. El sitio web se servirá en el puerto 3000 en tu localhost: `localhost:3000`. +Puedes ejecutar esta documentación sin conexión usando [Docsify](https://docsify.js.org/#/). Haz un fork de este repo, [instala Docsify](https://docsify.js.org/#/quickstart) en tu máquina local, y luego en la carpeta raíz de este repo, escribe `docsify serve`. El sitio web se servirá en el puerto 3000 en tu localhost: `localhost:3000`. ## PDFs -Encuentra un pdf del currículo con enlaces [aquí](https://microsoft.github.io/ML-For-Beginners/pdf/readme.pdf). +Encuentra un pdf del plan de estudios con enlaces [aquí](https://microsoft.github.io/ML-For-Beginners/pdf/readme.pdf). ## 🎒 Otros cursos @@ -182,43 +181,43 @@ Encuentra un pdf del currículo con enlaces [aquí](https://microsoft.github.io/ --- ### Serie de IA generativa -[![IA Generativa para principiantes](https://img.shields.io/badge/Generative%20AI%20for%20Beginners-8B5CF6?style=for-the-badge&labelColor=E5E7EB&color=8B5CF6)](https://github.com/microsoft/generative-ai-for-beginners?WT.mc_id=academic-105485-koreyst) -[![IA Generativa (.NET)](https://img.shields.io/badge/Generative%20AI%20(.NET)-9333EA?style=for-the-badge&labelColor=E5E7EB&color=9333EA)](https://github.com/microsoft/Generative-AI-for-beginners-dotnet?WT.mc_id=academic-105485-koreyst) -[![IA generativa (Java)](https://img.shields.io/badge/Generative%20AI%20(Java)-C084FC?style=for-the-badge&labelColor=E5E7EB&color=C084FC)](https://github.com/microsoft/generative-ai-for-beginners-java?WT.mc_id=academic-105485-koreyst) -[![IA generativa (JavaScript)](https://img.shields.io/badge/Generative%20AI%20(JavaScript)-E879F9?style=for-the-badge&labelColor=E5E7EB&color=E879F9)](https://github.com/microsoft/generative-ai-with-javascript?WT.mc_id=academic-105485-koreyst) +[![IA generativa para principiantes](https://img.shields.io/badge/Generative%20AI%20for%20Beginners-8B5CF6?style=for-the-badge&labelColor=E5E7EB&color=8B5CF6)](https://github.com/microsoft/generative-ai-for-beginners?WT.mc_id=academic-105485-koreyst) +[![IA generativa (.NET)](https://img.shields.io/badge/Generative%20AI%20(.NET)-9333EA?style=for-the-badge&labelColor=E5E7EB&color=9333EA)](https://github.com/microsoft/Generative-AI-for-beginners-dotnet?WT.mc_id=academic-105485-koreyst) +[![IA Generativa (Java)](https://img.shields.io/badge/Generative%20AI%20(Java)-C084FC?style=for-the-badge&labelColor=E5E7EB&color=C084FC)](https://github.com/microsoft/generative-ai-for-beginners-java?WT.mc_id=academic-105485-koreyst) +[![IA Generativa (JavaScript)](https://img.shields.io/badge/Generative%20AI%20(JavaScript)-E879F9?style=for-the-badge&labelColor=E5E7EB&color=E879F9)](https://github.com/microsoft/generative-ai-with-javascript?WT.mc_id=academic-105485-koreyst) --- -### Aprendizaje fundamental -[![ML para principiantes](https://img.shields.io/badge/ML%20for%20Beginners-22C55E?style=for-the-badge&labelColor=E5E7EB&color=22C55E)](https://aka.ms/ml-beginners?WT.mc_id=academic-105485-koreyst) -[![Ciencia de datos para principiantes](https://img.shields.io/badge/Data%20Science%20for%20Beginners-84CC16?style=for-the-badge&labelColor=E5E7EB&color=84CC16)](https://aka.ms/datascience-beginners?WT.mc_id=academic-105485-koreyst) -[![IA para principiantes](https://img.shields.io/badge/AI%20for%20Beginners-A3E635?style=for-the-badge&labelColor=E5E7EB&color=A3E635)](https://aka.ms/ai-beginners?WT.mc_id=academic-105485-koreyst) -[![Ciberseguridad para principiantes](https://img.shields.io/badge/Cybersecurity%20for%20Beginners-F97316?style=for-the-badge&labelColor=E5E7EB&color=F97316)](https://github.com/microsoft/Security-101?WT.mc_id=academic-96948-sayoung) -[![Desarrollo web para principiantes](https://img.shields.io/badge/Web%20Dev%20for%20Beginners-EC4899?style=for-the-badge&labelColor=E5E7EB&color=EC4899)](https://aka.ms/webdev-beginners?WT.mc_id=academic-105485-koreyst) -[![IoT para principiantes](https://img.shields.io/badge/IoT%20for%20Beginners-14B8A6?style=for-the-badge&labelColor=E5E7EB&color=14B8A6)](https://aka.ms/iot-beginners?WT.mc_id=academic-105485-koreyst) -[![Desarrollo XR para principiantes](https://img.shields.io/badge/XR%20Development%20for%20Beginners-38BDF8?style=for-the-badge&labelColor=E5E7EB&color=38BDF8)](https://github.com/microsoft/xr-development-for-beginners?WT.mc_id=academic-105485-koreyst) +### Aprendizaje principal +[![ML para Principiantes](https://img.shields.io/badge/ML%20for%20Beginners-22C55E?style=for-the-badge&labelColor=E5E7EB&color=22C55E)](https://aka.ms/ml-beginners?WT.mc_id=academic-105485-koreyst) +[![Ciencia de Datos para Principiantes](https://img.shields.io/badge/Data%20Science%20for%20Beginners-84CC16?style=for-the-badge&labelColor=E5E7EB&color=84CC16)](https://aka.ms/datascience-beginners?WT.mc_id=academic-105485-koreyst) +[![IA para Principiantes](https://img.shields.io/badge/AI%20for%20Beginners-A3E635?style=for-the-badge&labelColor=E5E7EB&color=A3E635)](https://aka.ms/ai-beginners?WT.mc_id=academic-105485-koreyst) +[![Ciberseguridad para Principiantes](https://img.shields.io/badge/Cybersecurity%20for%20Beginners-F97316?style=for-the-badge&labelColor=E5E7EB&color=F97316)](https://github.com/microsoft/Security-101?WT.mc_id=academic-96948-sayoung) +[![Desarrollo Web para Principiantes](https://img.shields.io/badge/Web%20Dev%20for%20Beginners-EC4899?style=for-the-badge&labelColor=E5E7EB&color=EC4899)](https://aka.ms/webdev-beginners?WT.mc_id=academic-105485-koreyst) +[![IoT para Principiantes](https://img.shields.io/badge/IoT%20for%20Beginners-14B8A6?style=for-the-badge&labelColor=E5E7EB&color=14B8A6)](https://aka.ms/iot-beginners?WT.mc_id=academic-105485-koreyst) +[![Desarrollo XR para Principiantes](https://img.shields.io/badge/XR%20Development%20for%20Beginners-38BDF8?style=for-the-badge&labelColor=E5E7EB&color=38BDF8)](https://github.com/microsoft/xr-development-for-beginners?WT.mc_id=academic-105485-koreyst) --- ### Serie Copilot -[![Copilot para programación en pareja con IA](https://img.shields.io/badge/Copilot%20for%20AI%20Paired%20Programming-FACC15?style=for-the-badge&labelColor=E5E7EB&color=FACC15)](https://aka.ms/GitHubCopilotAI?WT.mc_id=academic-105485-koreyst) +[![Copilot para Programación Pareada con IA](https://img.shields.io/badge/Copilot%20for%20AI%20Paired%20Programming-FACC15?style=for-the-badge&labelColor=E5E7EB&color=FACC15)](https://aka.ms/GitHubCopilotAI?WT.mc_id=academic-105485-koreyst) [![Copilot para C#/.NET](https://img.shields.io/badge/Copilot%20for%20C%23/.NET-FBBF24?style=for-the-badge&labelColor=E5E7EB&color=FBBF24)](https://github.com/microsoft/mastering-github-copilot-for-dotnet-csharp-developers?WT.mc_id=academic-105485-koreyst) [![Aventura Copilot](https://img.shields.io/badge/Copilot%20Adventure-FDE68A?style=for-the-badge&labelColor=E5E7EB&color=FDE68A)](https://github.com/microsoft/CopilotAdventures?WT.mc_id=academic-105485-koreyst) ## Obtener ayuda -Si te quedas atascado o tienes alguna pregunta sobre construir aplicaciones de IA. Únete a otros aprendices y desarrolladores experimentados en discusiones sobre MCP. Es una comunidad de apoyo donde las preguntas son bienvenidas y el conocimiento se comparte libremente. +Si te quedas atascado o tienes alguna pregunta sobre la creación de aplicaciones de IA. Únete a otros aprendices y desarrolladores experimentados en discusiones sobre MCP. Es una comunidad de apoyo donde las preguntas son bienvenidas y el conocimiento se comparte libremente. [![Discord de Microsoft Foundry](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) -Si tienes comentarios sobre el producto o errores mientras construyes visita: +Si tienes comentarios sobre el producto o errores mientras construyes, visita: -[![Foro de desarrolladores de Microsoft Foundry](https://img.shields.io/badge/GitHub-Microsoft_Foundry_Developer_Forum-blue?style=for-the-badge&logo=github&color=000000&logoColor=fff)](https://aka.ms/foundry/forum) +[![Foro de Desarrolladores de Microsoft Foundry](https://img.shields.io/badge/GitHub-Microsoft_Foundry_Developer_Forum-blue?style=for-the-badge&logo=github&color=000000&logoColor=fff)](https://aka.ms/foundry/forum) --- Descargo de responsabilidad: -Este documento ha sido traducido mediante el servicio de traducción por IA Co-op Translator (https://github.com/Azure/co-op-translator). Aunque nos esforzamos por la precisión, tenga en cuenta que las traducciones automatizadas pueden contener errores o inexactitudes. El documento original en su idioma nativo debe considerarse la fuente autorizada. Para información crítica, se recomienda una traducción profesional realizada por un traductor humano. No nos hacemos responsables de malentendidos o interpretaciones erróneas que puedan derivarse del uso de esta traducción. +Este documento ha sido traducido utilizando el servicio de traducción por IA Co-op Translator (https://github.com/Azure/co-op-translator). Aunque nos esforzamos por la exactitud, tenga en cuenta que las traducciones automatizadas pueden contener errores o inexactitudes. El documento original en su idioma debe considerarse la fuente autorizada. Para información crítica, se recomienda una traducción profesional realizada por un traductor humano. No nos hacemos responsables de malentendidos o interpretaciones erróneas que surjan del uso de esta traducción. \ No newline at end of file diff --git a/translations/et/1-Introduction/1-intro-to-ML/README.md b/translations/et/1-Introduction/1-intro-to-ML/README.md index c526b0a01..8b7ef403c 100644 --- a/translations/et/1-Introduction/1-intro-to-ML/README.md +++ b/translations/et/1-Introduction/1-intro-to-ML/README.md @@ -42,7 +42,7 @@ Termin 'masinõpe' on üks tänapäeva populaarsemaid ja sagedamini kasutatavaid --- ## Hüppekurv -![ml hüppekurv](../../../../translated_images/hype.07183d711a17aafe70915909a0e45aa286ede136ee9424d418026ab00fec344c.et.png) +![ml hüppekurv](../../../../translated_images/hype.07183d711a17aafe.et.png) > Google Trends näitab termini 'masinõpe' hiljutist hüppekurvi @@ -69,7 +69,7 @@ Kuigi termineid võib segamini ajada, on masinõpe (ML) tehisintellekti oluline --- ## AI, ML, süvaõpe -![AI, ML, süvaõpe, andmeteadus](../../../../translated_images/ai-ml-ds.537ea441b124ebf69c144a52c0eb13a7af63c4355c2f92f440979380a2fb08b8.et.png) +![AI, ML, süvaõpe, andmeteadus](../../../../translated_images/ai-ml-ds.537ea441b124ebf6.et.png) > Diagramm, mis näitab AI, ML-i, süvaõppe ja andmeteaduse vahelisi seoseid. Infograafik autorilt [Jen Looper](https://twitter.com/jenlooper), inspireeritud [sellest graafikust](https://softwareengineering.stackexchange.com/questions/366996/distinction-between-ai-ml-neural-networks-deep-learning-and-data-mining) diff --git a/translations/et/1-Introduction/2-history-of-ML/README.md b/translations/et/1-Introduction/2-history-of-ML/README.md index 11ac82586..f19665734 100644 --- a/translations/et/1-Introduction/2-history-of-ML/README.md +++ b/translations/et/1-Introduction/2-history-of-ML/README.md @@ -9,7 +9,7 @@ CO_OP_TRANSLATOR_METADATA: --> # Masinõppe ajalugu -![Masinõppe ajaloo kokkuvõte visandmärkmetes](../../../../translated_images/ml-history.a1bdfd4ce1f464d9a0502f38d355ffda384c95cd5278297a46c9a391b5053bc4.et.png) +![Masinõppe ajaloo kokkuvõte visandmärkmetes](../../../../translated_images/ml-history.a1bdfd4ce1f464d9.et.png) > Visandmärkmed: [Tomomi Imura](https://www.twitter.com/girlie_mac) ## [Eelloengu viktoriin](https://ff-quizzes.netlify.app/en/ml/) @@ -71,14 +71,14 @@ Uuringuid rahastasid hästi valitsusasutused, arvutusvõimekus ja algoritmid are * [Shakey robot](https://wikipedia.org/wiki/Shakey_the_robot), kes suutis liikuda ja otsustada, kuidas ülesandeid 'intelligentselt' täita. - ![Shakey, intelligentne robot](../../../../translated_images/shakey.4dc17819c447c05bf4b52f76da0bdd28817d056fdb906252ec20124dd4cfa55e.et.jpg) + ![Shakey, intelligentne robot](../../../../translated_images/shakey.4dc17819c447c05b.et.jpg) > Shakey aastal 1972 --- * Eliza, varajane 'vestlusrobot', suutis inimestega vestelda ja toimida primitiivse 'terapeudina'. Õpite Eliza kohta rohkem NLP õppetundides. - ![Eliza, robot](../../../../translated_images/eliza.84397454cda9559bb5ec296b5b8fff067571c0cccc5405f9c1ab1c3f105c075c.et.png) + ![Eliza, robot](../../../../translated_images/eliza.84397454cda9559b.et.png) > Eliza versioon, vestlusrobot --- diff --git a/translations/et/1-Introduction/3-fairness/README.md b/translations/et/1-Introduction/3-fairness/README.md index 63b3daad1..ce5d1a1e6 100644 --- a/translations/et/1-Introduction/3-fairness/README.md +++ b/translations/et/1-Introduction/3-fairness/README.md @@ -9,7 +9,7 @@ CO_OP_TRANSLATOR_METADATA: --> # Masinõppe lahenduste loomine vastutustundliku tehisintellektiga -![Vastutustundliku tehisintellekti kokkuvõte masinõppes sketšimärkmetes](../../../../translated_images/ml-fairness.ef296ebec6afc98a44566d7b6c1ed18dc2bf1115c13ec679bb626028e852fa1d.et.png) +![Vastutustundliku tehisintellekti kokkuvõte masinõppes sketšimärkmetes](../../../../translated_images/ml-fairness.ef296ebec6afc98a.et.png) > Sketšimärkmed: [Tomomi Imura](https://www.twitter.com/girlie_mac) ## [Loengu-eelne viktoriin](https://ff-quizzes.netlify.app/en/ml/) @@ -51,10 +51,10 @@ Tehisintellekti süsteemid peaksid kohtlema kõiki õiglaselt ja vältima sarnas - **Üle- või alaesindatus**. Idee, et teatud rühma ei nähta teatud ametis, ja iga teenus või funktsioon, mis seda jätkuvalt edendab, aitab kaasa kahjule. - **Stereotüpiseerimine**. Teatud rühma seostamine eelnevalt määratud omadustega. Näiteks inglise ja türgi keele vahel tõlkiv süsteem võib eksida sõnadega, millel on sooga seotud stereotüüpsed seosed. -![Tõlge türgi keelde](../../../../translated_images/gender-bias-translate-en-tr.f185fd8822c2d4372912f2b690f6aaddd306ffbb49d795ad8d12a4bf141e7af0.et.png) +![Tõlge türgi keelde](../../../../translated_images/gender-bias-translate-en-tr.f185fd8822c2d437.et.png) > Tõlge türgi keelde -![Tõlge tagasi inglise keelde](../../../../translated_images/gender-bias-translate-tr-en.4eee7e3cecb8c70e13a8abbc379209bc8032714169e585bdeac75af09b1752aa.et.png) +![Tõlge tagasi inglise keelde](../../../../translated_images/gender-bias-translate-tr-en.4eee7e3cecb8c70e.et.png) > Tõlge tagasi inglise keelde Tehisintellekti süsteemide kavandamisel ja testimisel peame tagama, et tehisintellekt oleks õiglane ega oleks programmeeritud tegema eelarvamuslikke või diskrimineerivaid otsuseid, mida ka inimestel on keelatud teha. Õigluse tagamine tehisintellektis ja masinõppes jääb keeruliseks sotsiaal-tehniliseks väljakutseks. @@ -97,7 +97,7 @@ Tehisintellekti süsteemid peaksid olema arusaadavad. Läbipaistvuse oluline osa Inimesed, kes kavandavad ja rakendavad tehisintellekti süsteeme, peavad vastutama selle eest, kuidas nende süsteemid toimivad. Vastutuse vajadus on eriti oluline tundlike tehnoloogiate, nagu näotuvastus, puhul. Viimasel ajal on näotuvastustehnoloogia järele olnud kasvav nõudlus, eriti õiguskaitseorganisatsioonide poolt, kes näevad tehnoloogia potentsiaali näiteks kadunud laste leidmisel. Kuid need tehnoloogiad võivad valitsuse poolt potentsiaalselt ohustada kodanike põhiõigusi, võimaldades näiteks konkreetsete isikute pidevat jälgimist. Seetõttu peavad andmeteadlased ja organisatsioonid vastutama selle eest, kuidas nende tehisintellekti süsteem mõjutab üksikisikuid või ühiskonda. -[![Juhtiv tehisintellekti teadlane hoiatab massilise jälgimise eest näotuvastuse kaudu](../../../../translated_images/accountability.41d8c0f4b85b6231301d97f17a450a805b7a07aaeb56b34015d71c757cad142e.et.png)](https://www.youtube.com/watch?v=Wldt8P5V6D0 "Microsofti lähenemine vastutustundlikule tehisintellektile") +[![Juhtiv tehisintellekti teadlane hoiatab massilise jälgimise eest näotuvastuse kaudu](../../../../translated_images/accountability.41d8c0f4b85b6231.et.png)](https://www.youtube.com/watch?v=Wldt8P5V6D0 "Microsofti lähenemine vastutustundlikule tehisintellektile") > 🎥 Klõpsake ülaloleval pildil, et vaadata videot: Hoiatused massilise jälgimise eest näotuvastuse kaudu diff --git a/translations/et/1-Introduction/4-techniques-of-ML/README.md b/translations/et/1-Introduction/4-techniques-of-ML/README.md index 447840bf6..659954b94 100644 --- a/translations/et/1-Introduction/4-techniques-of-ML/README.md +++ b/translations/et/1-Introduction/4-techniques-of-ML/README.md @@ -97,7 +97,7 @@ Masinõppe kontekstis viitab mudeli sobitamine mudeli aluseks oleva funktsiooni 🎓 **Alasobitamine** ja **ülesobitamine** on levinud probleemid, mis halvendavad mudeli kvaliteeti, kuna mudel sobitub kas liiga halvasti või liiga hästi. See põhjustab mudeli ennustusi, mis on kas liiga tihedalt seotud või liiga lõdvalt seotud treeningandmetega. Ülesobitunud mudel ennustab treeningandmeid liiga hästi, kuna see on õppinud andmete üksikasju ja müra liiga hästi. Alasobitunud mudel pole täpne, kuna see ei suuda täpselt analüüsida ei oma treeningandmeid ega andmeid, mida see pole veel "näinud". -![ülesobitunud mudel](../../../../translated_images/overfitting.1c132d92bfd93cb63240baf63ebdf82c30e30a0a44e1ad49861b82ff600c2b5c.et.png) +![ülesobitunud mudel](../../../../translated_images/overfitting.1c132d92bfd93cb6.et.png) > Infograafik: [Jen Looper](https://twitter.com/jenlooper) ## Parameetrite häälestamine diff --git a/translations/et/1-Introduction/README.md b/translations/et/1-Introduction/README.md index e62a69833..d1a224d7f 100644 --- a/translations/et/1-Introduction/README.md +++ b/translations/et/1-Introduction/README.md @@ -11,7 +11,7 @@ CO_OP_TRANSLATOR_METADATA: Selles õppekava osas tutvustatakse teile masinõppe valdkonna aluskontseptsioone, mis see on, ning saate teada selle ajaloost ja tehnikatest, mida teadlased selle valdkonnaga töötamiseks kasutavad. Uurime koos seda uut ML-i maailma! -![globe](../../../translated_images/globe.59f26379ceb40428672b4d9a568044618a2bf6292ecd53a5c481b90e3fa805eb.et.jpg) +![globe](../../../translated_images/globe.59f26379ceb40428.et.jpg) > Foto autorilt Bill Oxford lehel Unsplash ### Õppetunnid diff --git a/translations/et/2-Regression/1-Tools/README.md b/translations/et/2-Regression/1-Tools/README.md index ed6435d78..a9b36d4e9 100644 --- a/translations/et/2-Regression/1-Tools/README.md +++ b/translations/et/2-Regression/1-Tools/README.md @@ -9,7 +9,7 @@ CO_OP_TRANSLATOR_METADATA: --> # Alusta Pythoni ja Scikit-learniga regressioonimudelite jaoks -![Regressioonide kokkuvõte visuaalses märkmes](../../../../translated_images/ml-regression.4e4f70e3b3ed446e3ace348dec973e133fa5d3680fbc8412b61879507369b98d.et.png) +![Regressioonide kokkuvõte visuaalses märkmes](../../../../translated_images/ml-regression.4e4f70e3b3ed446e.et.png) > Visuaalne märge: [Tomomi Imura](https://www.twitter.com/girlie_mac) @@ -81,7 +81,7 @@ Selles kaustas leiad faili _notebook.ipynb_. hello notebook ``` -![VS Code avatud märkmikuga](../../../../translated_images/notebook.4a3ee31f396b88325607afda33cadcc6368de98040ff33942424260aa84d75f2.et.jpg) +![VS Code avatud märkmikuga](../../../../translated_images/notebook.4a3ee31f396b8832.et.jpg) Sa saad oma koodi vaheldumisi kommentaaridega täiendada, et märkmikku ise dokumenteerida. @@ -211,7 +211,7 @@ Uues koodilahtris laadi diabeedi andmekogum, kutsudes `load_diabetes()`. Sisend plt.show() ``` - ![hajusdiagramm, mis näitab diabeediga seotud andmepunkte](../../../../translated_images/scatterplot.ad8b356bcbb33be68d54050e09b9b7bfc03e94fde7371f2609ae43f4c563b2d7.et.png) + ![hajusdiagramm, mis näitab diabeediga seotud andmepunkte](../../../../translated_images/scatterplot.ad8b356bcbb33be6.et.png) ✅ Mõtle veidi, mis siin toimub. Sirgjoon kulgeb läbi paljude väikeste andmepunktide, kuid mida see täpselt teeb? Kas näed, kuidas saaksid seda joont kasutada, et ennustada, kuhu uus, seni nägemata andmepunkt peaks graafiku y-telje suhtes sobituma? Proovi sõnastada selle mudeli praktiline kasutus. Palju õnne, sa ehitasid oma esimese lineaarse regressioonimudeli, tegid sellega ennustuse ja kuvad selle graafikul! diff --git a/translations/et/2-Regression/1-Tools/solution/R/lesson_1-R.ipynb b/translations/et/2-Regression/1-Tools/solution/R/lesson_1-R.ipynb index 94277e12e..6aa1e0996 100644 --- a/translations/et/2-Regression/1-Tools/solution/R/lesson_1-R.ipynb +++ b/translations/et/2-Regression/1-Tools/solution/R/lesson_1-R.ipynb @@ -46,7 +46,7 @@ "Sellega öeldes, alustame selle ülesandega!\n", "\n", "

\n", - " \n", "

Kunstiteos: @allison_horst
\n" ], diff --git a/translations/et/2-Regression/2-Data/README.md b/translations/et/2-Regression/2-Data/README.md index cd18f2d33..e45874dd0 100644 --- a/translations/et/2-Regression/2-Data/README.md +++ b/translations/et/2-Regression/2-Data/README.md @@ -9,7 +9,7 @@ CO_OP_TRANSLATOR_METADATA: --> # Ehita regressioonimudel Scikit-learniga: andmete ettevalmistamine ja visualiseerimine -![Andmete visualiseerimise infograafika](../../../../translated_images/data-visualization.54e56dded7c1a804d00d027543f2881cb32da73aeadda2d4a4f10f3497526114.et.png) +![Andmete visualiseerimise infograafika](../../../../translated_images/data-visualization.54e56dded7c1a804.et.png) Infograafika autor: [Dasani Madipalli](https://twitter.com/dasani_decoded) @@ -183,7 +183,7 @@ Proovi luua mõned põhilised graafikud, et kuvada just loodud andmeraami. Mida plt.show() ``` - ![Hajuvusdiagramm, mis näitab hinna ja kuu suhet](../../../../translated_images/scatterplot.b6868f44cbd2051c6680ccdbb1510697d06a3ff6cd4abda656f5009c0ed4e3fc.et.png) + ![Hajuvusdiagramm, mis näitab hinna ja kuu suhet](../../../../translated_images/scatterplot.b6868f44cbd2051c.et.png) Kas see on kasulik graafik? Kas miski selles üllatab sind? @@ -200,7 +200,7 @@ Et graafikud kuvaksid kasulikke andmeid, tuleb andmeid tavaliselt kuidagi rühmi plt.ylabel("Pumpkin Price") ``` - ![Tulpdiagramm, mis näitab hinna ja kuu suhet](../../../../translated_images/barchart.a833ea9194346d769c77a3a870f7d8aee51574cd1138ca902e5500830a41cbce.et.png) + ![Tulpdiagramm, mis näitab hinna ja kuu suhet](../../../../translated_images/barchart.a833ea9194346d76.et.png) See on kasulikum andmete visualiseerimine! Näib, et kõrvitsate kõrgeim hind esineb septembris ja oktoobris. Kas see vastab sinu ootustele? Miks või miks mitte? diff --git a/translations/et/2-Regression/2-Data/solution/R/lesson_2-R.ipynb b/translations/et/2-Regression/2-Data/solution/R/lesson_2-R.ipynb index dbd405d64..7693d7453 100644 --- a/translations/et/2-Regression/2-Data/solution/R/lesson_2-R.ipynb +++ b/translations/et/2-Regression/2-Data/solution/R/lesson_2-R.ipynb @@ -45,12 +45,12 @@ "\n", "\n", "

\n", - " \n", "

Kunstiteos: @allison_horst
\n", "\n", "\n", - "\n" + "\n" ], "metadata": { "id": "Pg5aexcOPqAZ" @@ -226,7 +226,7 @@ "## 3. Dplyr: Andmete manipuleerimise grammatika\n", "\n", "

\n", - " \n", "

Kunstiteos: @allison_horst
\n" ], @@ -529,12 +529,12 @@ "## 4. Andmete visualiseerimine ggplot2 abil\n", "\n", "

\n", - " \n", "

Infograafika autor: Dasani Madipalli
\n", "\n", "\n", - "\n", + "\n", "\n", "On olemas *tark* ütlus, mis kõlab järgmiselt:\n", "\n", diff --git a/translations/et/2-Regression/3-Linear/README.md b/translations/et/2-Regression/3-Linear/README.md index d90fd3384..140302543 100644 --- a/translations/et/2-Regression/3-Linear/README.md +++ b/translations/et/2-Regression/3-Linear/README.md @@ -9,7 +9,7 @@ CO_OP_TRANSLATOR_METADATA: --> # Ehita regressioonimudel Scikit-learniga: neli viisi regressiooniks -![Lineaarse ja polünoomse regressiooni infograafika](../../../../translated_images/linear-polynomial.5523c7cb6576ccab0fecbd0e3505986eb2d191d9378e785f82befcf3a578a6e7.et.png) +![Lineaarse ja polünoomse regressiooni infograafika](../../../../translated_images/linear-polynomial.5523c7cb6576ccab.et.png) > Infograafika autor: [Dasani Madipalli](https://twitter.com/dasani_decoded) ## [Eelloengu viktoriin](https://ff-quizzes.netlify.app/en/ml/) @@ -66,13 +66,13 @@ Teeme seda, kuna soovime modelleerida joont, millel on kõigi meie andmepunktide > > `X` on 'selgitav muutuja'. `Y` on 'sõltuv muutuja'. Joone kalle on `b` ja `a` on y-teljelõige, mis viitab `Y` väärtusele, kui `X = 0`. > ->![kalle arvutamine](../../../../translated_images/slope.f3c9d5910ddbfcf9096eb5564254ba22c9a32d7acd7694cab905d29ad8261db3.et.png) +>![kalle arvutamine](../../../../translated_images/slope.f3c9d5910ddbfcf9.et.png) > > Kõigepealt arvutage kalle `b`. Infograafika autor: [Jen Looper](https://twitter.com/jenlooper) > > Teisisõnu, viidates meie kõrvitsate andmete algsele küsimusele: "ennusta kõrvitsa hinda busheli kohta kuu järgi", viitaks `X` hinnale ja `Y` müügikuule. > ->![võrrandi täitmine](../../../../translated_images/calculation.a209813050a1ddb141cdc4bc56f3af31e67157ed499e16a2ecf9837542704c94.et.png) +>![võrrandi täitmine](../../../../translated_images/calculation.a209813050a1ddb1.et.png) > > Arvutage Y väärtus. Kui maksate umbes 4 dollarit, peab olema aprill! Infograafika autor: [Jen Looper](https://twitter.com/jenlooper) > @@ -114,11 +114,11 @@ Nüüd, kui olete aru saanud lineaarse regressiooni matemaatikast, loome regress Eelmises õppetunnis olete tõenäoliselt näinud, et keskmine hind erinevate kuude kohta näeb välja selline: -Keskmine hind kuu järgi +Keskmine hind kuu järgi See viitab sellele, et peaks olema mingi korrelatsioon, ja me võime proovida treenida lineaarse regressiooni mudelit, et ennustada seost `Kuu` ja `Hinna` vahel või `AastaPäeva` ja `Hinna` vahel. Siin on hajuvusdiagramm, mis näitab viimast seost: -Hajuvusdiagramm hinna ja aasta päeva vahel +Hajuvusdiagramm hinna ja aasta päeva vahel Vaatame, kas korrelatsioon on olemas, kasutades funktsiooni `corr`: @@ -137,7 +137,7 @@ for i,var in enumerate(new_pumpkins['Variety'].unique()): ax = df.plot.scatter('DayOfYear','Price',ax=ax,c=colors[i],label=var) ``` -Hajuvusdiagramm hinna ja aasta päeva vahel +Hajuvusdiagramm hinna ja aasta päeva vahel Meie uurimine viitab sellele, et sordil on müügikuupäevast suurem mõju üldisele hinnale. Seda näeme ka tulpdiagrammist: @@ -145,7 +145,7 @@ Meie uurimine viitab sellele, et sordil on müügikuupäevast suurem mõju üldi new_pumpkins.groupby('Variety')['Price'].mean().plot(kind='bar') ``` -Tulpdiagramm hinna ja sordi vahel +Tulpdiagramm hinna ja sordi vahel Keskendume hetkeks ainult ühele kõrvitsasordile, 'pie type', ja vaatame, millist mõju kuupäev hinnale avaldab: @@ -153,7 +153,7 @@ Keskendume hetkeks ainult ühele kõrvitsasordile, 'pie type', ja vaatame, milli pie_pumpkins = new_pumpkins[new_pumpkins['Variety']=='PIE TYPE'] pie_pumpkins.plot.scatter('DayOfYear','Price') ``` -Hajuvusdiagramm hinna ja aasta päeva vahel +Hajuvusdiagramm hinna ja aasta päeva vahel Kui arvutame nüüd korrelatsiooni `Hinna` ja `AastaPäeva` vahel, kasutades funktsiooni `corr`, saame tulemuseks umbes `-0.27` - mis tähendab, et ennustava mudeli treenimine on mõistlik. @@ -228,7 +228,7 @@ plt.scatter(X_test,y_test) plt.plot(X_test,pred) ``` -Lineaarne regressioon +Lineaarne regressioon ## Polünoomiline regressioon @@ -257,7 +257,7 @@ pipeline.fit(X_train,y_train) Pipeline'i saab kasutada samamoodi nagu algset `LinearRegression` objekti, st saame pipeline'i `fit`-ida ja seejärel kasutada `predict`, et saada prognoositulemused. Siin on graafik, mis näitab testandmeid ja lähenduskõverat: -Polünoomiline regressioon +Polünoomiline regressioon Polünoomilist regressiooni kasutades saame veidi madalama MSE ja kõrgema determinatsiooni, kuid mitte märkimisväärselt. Peame arvesse võtma ka teisi omadusi! @@ -275,7 +275,7 @@ Ideaalis tahame olla võimelised prognoosima hindu erinevate kõrvitsasortide ja Siin näed, kuidas keskmine hind sõltub sordist: -Keskmine hind sordi järgi +Keskmine hind sordi järgi Sordi arvesse võtmiseks peame esmalt selle numbriliseks vormiks teisendama ehk **kodeerima**. Selleks on mitu võimalust: diff --git a/translations/et/2-Regression/3-Linear/solution/R/lesson_3-R.ipynb b/translations/et/2-Regression/3-Linear/solution/R/lesson_3-R.ipynb index 301a38c88..66f94a9bd 100644 --- a/translations/et/2-Regression/3-Linear/solution/R/lesson_3-R.ipynb +++ b/translations/et/2-Regression/3-Linear/solution/R/lesson_3-R.ipynb @@ -37,7 +37,7 @@ "source": [ "## Lineaarne ja polünoomne regressioon kõrvitsate hinnastamiseks - Õppetund 3\n", "

\n", - " \n", "

Infograafika autor: Dasani Madipalli
\n", "\n", @@ -159,12 +159,12 @@ "## **2. Tants andmetega: andmeraami loomine, mida kasutatakse modelleerimiseks**\n", "\n", "

\n", - " \n", "

Kunstiteos: @allison_horst
\n", "\n", "\n", - "\n" + "\n" ], "metadata": { "id": "WdUKXk7Bs8-V" @@ -453,7 +453,7 @@ "Selleks vajad kahte lisakäsku: `prep()` ja `bake()`, ning nagu alati, aitavad meie väikesed R-sõbrad [`Allison Horst`](https://github.com/allisonhorst/stats-illustrations) sul sellest paremini aru saada!\n", "\n", "

\n", - " \n", "

Illustratsioon autorilt @allison_horst
\n" ], @@ -564,12 +564,12 @@ "## 4. Lineaarse regressioonimudeli loomine\n", "\n", "

\n", - " \n", "

Infograafik: Dasani Madipalli
\n", "\n", "\n", - "\n" + "\n" ], "metadata": { "id": "YqXjLuWavNxW" @@ -805,7 +805,7 @@ "## 5. Loo polünoomse regressiooni mudel\n", "\n", "

\n", - " \n", "

Infograafik: Dasani Madipalli
\n" ], diff --git a/translations/et/2-Regression/4-Logistic/README.md b/translations/et/2-Regression/4-Logistic/README.md index 0816ab16d..0878b48ab 100644 --- a/translations/et/2-Regression/4-Logistic/README.md +++ b/translations/et/2-Regression/4-Logistic/README.md @@ -9,7 +9,7 @@ CO_OP_TRANSLATOR_METADATA: --> # Logistiline regressioon kategooriate ennustamiseks -![Logistilise ja lineaarse regressiooni infograafik](../../../../translated_images/linear-vs-logistic.ba180bf95e7ee66721ba10ebf2dac2666acbd64a88b003c83928712433a13c7d.et.png) +![Logistilise ja lineaarse regressiooni infograafik](../../../../translated_images/linear-vs-logistic.ba180bf95e7ee667.et.png) ## [Eelloengu viktoriin](https://ff-quizzes.netlify.app/en/ml/) @@ -52,7 +52,7 @@ Logistiline regressioon erineb lineaarse regressioonist, mida sa õppisid varem, Logistiline regressioon ei paku samu funktsioone kui lineaarne regressioon. Esimene pakub ennustust binaarse kategooria kohta ("valge või mitte valge"), samas kui teine suudab ennustada pidevaid väärtusi, näiteks arvestades kõrvitsa päritolu ja koristusaega, _kui palju selle hind tõuseb_. -![Kõrvitsa klassifikatsioonimudel](../../../../translated_images/pumpkin-classifier.562771f104ad5436b87d1c67bca02a42a17841133556559325c0a0e348e5b774.et.png) +![Kõrvitsa klassifikatsioonimudel](../../../../translated_images/pumpkin-classifier.562771f104ad5436.et.png) > Infograafik autorilt [Dasani Madipalli](https://twitter.com/dasani_decoded) ### Muud klassifikatsioonid @@ -62,7 +62,7 @@ On olemas ka teisi logistilise regressiooni tüüpe, sealhulgas multinomiaalne j - **Multinomiaalne**, mis hõlmab rohkem kui ühte kategooriat - "Oranž, Valge ja Triibuline". - **Ordinaalne**, mis hõlmab järjestatud kategooriaid, kasulik, kui tahame oma tulemusi loogiliselt järjestada, näiteks kõrvitsad, mis on järjestatud piiratud arvu suuruste järgi (mini, väike, keskmine, suur, XL, XXL). -![Multinomiaalne vs ordinaalne regressioon](../../../../translated_images/multinomial-vs-ordinal.36701b4850e37d86c9dd49f7bef93a2f94dbdb8fe03443eb68f0542f97f28f29.et.png) +![Multinomiaalne vs ordinaalne regressioon](../../../../translated_images/multinomial-vs-ordinal.36701b4850e37d86.et.png) ### Muutujad EI PEA korreleeruma @@ -118,7 +118,7 @@ Seaborn pakub huvitavaid viise andmete visualiseerimiseks. Näiteks saad võrrel ) ``` - ![Visualiseeritud andmete ruudustik](../../../../translated_images/pumpkins_catplot_1.c55c409b71fea2ecc01921e64b91970542101f90bcccfa4aa3a205db8936f48b.et.png) + ![Visualiseeritud andmete ruudustik](../../../../translated_images/pumpkins_catplot_1.c55c409b71fea2ec.et.png) Vaadates andmeid, näed, kuidas `Color` andmed seostuvad `Variety`-ga. @@ -197,7 +197,7 @@ Parim viis sellise analüüsi tegemiseks on andmete graafikule kandmine. Kasutam g.set(xlabel="Item Size", ylabel="").set(xlim=(0,6)) g.set_titles(row_template="{row_name}") ``` -![Visualiseeritud andmete kategooriline graafik](../../../../translated_images/pumpkins_catplot_2.87a354447880b3889278155957f8f60dd63db4598de5a6d0fda91c334d31f9f1.et.png) +![Visualiseeritud andmete kategooriline graafik](../../../../translated_images/pumpkins_catplot_2.87a354447880b388.et.png) ### Kasuta 'swarm' graafikut @@ -215,7 +215,7 @@ Saad visualiseerida muutujaid kõrvuti Seaborn graafikutega. sns.swarmplot(x="Color", y="ord__Item Size", data=encoded_pumpkins, palette=palette) ``` - ![Visualiseeritud andmete 'swarm'](../../../../translated_images/swarm_2.efeacfca536c2b577dc7b5f8891f28926663fbf62d893ab5e1278ae734ca104e.et.png) + ![Visualiseeritud andmete 'swarm'](../../../../translated_images/swarm_2.efeacfca536c2b57.et.png) **Ole ettevaatlik**: ülaltoodud kood võib genereerida hoiatuse, kuna Seaborn ei suuda esitada sellist hulka andmepunkte 'swarm' graafikus. Võimalik lahendus on vähendada markeri suurust, kasutades 'size' parameetrit. Kuid ole teadlik, et see mõjutab graafiku loetavust. @@ -223,7 +223,7 @@ Saad visualiseerida muutujaid kõrvuti Seaborn graafikutega. > > Logistiline regressioon tugineb 'maksimaalse tõenäosuse' kontseptsioonile, kasutades [sigmoidfunktsioone](https://wikipedia.org/wiki/Sigmoid_function). 'Sigmoidfunktsioon' graafikul näeb välja nagu 'S'-kuju. See võtab väärtuse ja kaardistab selle vahemikku 0 kuni 1. Selle kõverat nimetatakse ka 'logistiliseks kõveraks'. Selle valem näeb välja selline: > -> ![logistiline funktsioon](../../../../translated_images/sigmoid.8b7ba9d095c789cf72780675d0d1d44980c3736617329abfc392dfc859799704.et.png) +> ![logistiline funktsioon](../../../../translated_images/sigmoid.8b7ba9d095c789cf.et.png) > > kus sigmoidi keskpunkt asub x-i 0 punktis, L on kõvera maksimaalne väärtus ja k on kõvera järskus. Kui funktsiooni tulemus on suurem kui 0.5, antakse vastavale sildile binaarse valiku klass '1'. Kui mitte, klassifitseeritakse see kui '0'. @@ -372,7 +372,7 @@ plt.show() Kasutades Matplotlibi, joonista mudeli [Vastuvõtu Tööomaduste Kõver](https://scikit-learn.org/stable/auto_examples/model_selection/plot_roc.html?highlight=roc) ehk ROC. ROC kõveraid kasutatakse sageli klassifikaatori väljundi vaatamiseks tõeliste ja valepositiivsete osas. "ROC kõveratel on tavaliselt tõeliste positiivsete määr Y-teljel ja valepositiivsete määr X-teljel." Seega on kõvera järskus ja kaugus keskjoonest kõverani olulised: soovid kõverat, mis kiiresti tõuseb ja liigub üle joone. Meie puhul on alguses valepositiivsed, kuid seejärel tõuseb joon korralikult üles ja üle: -![ROC](../../../../translated_images/ROC_2.777f20cdfc4988ca683ade6850ac832cb70c96c12f1b910d294f270ef36e1a1c.et.png) +![ROC](../../../../translated_images/ROC_2.777f20cdfc4988ca.et.png) Lõpuks kasuta Scikit-learn'i [`roc_auc_score` API-t](https://scikit-learn.org/stable/modules/generated/sklearn.metrics.roc_auc_score.html?highlight=roc_auc#sklearn.metrics.roc_auc_score), et arvutada tegelik 'Kõvera Alune Pindala' (AUC): diff --git a/translations/et/2-Regression/4-Logistic/solution/R/lesson_4-R.ipynb b/translations/et/2-Regression/4-Logistic/solution/R/lesson_4-R.ipynb index 8faa991ba..4eb469d84 100644 --- a/translations/et/2-Regression/4-Logistic/solution/R/lesson_4-R.ipynb +++ b/translations/et/2-Regression/4-Logistic/solution/R/lesson_4-R.ipynb @@ -6,7 +6,7 @@ "source": [ "## Logistilise regressioonimudeli loomine - Õppetund 4\n", "\n", - "![Logistilise vs. lineaarse regressiooni infograafik](../../../../../../translated_images/linear-vs-logistic.ba180bf95e7ee66721ba10ebf2dac2666acbd64a88b003c83928712433a13c7d.et.png)\n", + "![Logistilise vs. lineaarse regressiooni infograafik](../../../../../../translated_images/linear-vs-logistic.ba180bf95e7ee667.et.png)\n", "\n", "#### **[Loengu-eelne viktoriin](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/15/)**\n", "\n", @@ -78,7 +78,7 @@ "\n", "Logistiline regressioon ei paku samu võimalusi kui lineaarregressioon. Esimene annab ennustuse `binaarse kategooria` kohta (\"oranž või mitte oranž\"), samas kui viimane suudab ennustada `jätkuvaid väärtusi`, näiteks arvestades kõrvitsa päritolu ja koristusaega, *kui palju selle hind tõuseb*.\n", "\n", - "![Infograafik autorilt Dasani Madipalli](../../../../../../translated_images/pumpkin-classifier.562771f104ad5436b87d1c67bca02a42a17841133556559325c0a0e348e5b774.et.png)\n", + "![Infograafik autorilt Dasani Madipalli](../../../../../../translated_images/pumpkin-classifier.562771f104ad5436.et.png)\n", "\n", "### Muud klassifikatsioonid\n", "\n", @@ -88,7 +88,7 @@ "\n", "- **Ordinaalne**, mis hõlmab järjestatud kategooriaid, kasulik, kui tahame tulemusi loogiliselt järjestada, näiteks meie kõrvitsad, mis on järjestatud kindla arvu suuruste järgi (mini, väike, keskmine, suur, väga suur, hiiglaslik).\n", "\n", - "![Multinomiaalne vs ordinaalne regressioon](../../../../../../translated_images/multinomial-vs-ordinal.36701b4850e37d86c9dd49f7bef93a2f94dbdb8fe03443eb68f0542f97f28f29.et.png)\n", + "![Multinomiaalne vs ordinaalne regressioon](../../../../../../translated_images/multinomial-vs-ordinal.36701b4850e37d86.et.png)\n", "\n", "#### **Muutujad EI PEA korreleeruma**\n", "\n", diff --git a/translations/et/2-Regression/README.md b/translations/et/2-Regression/README.md index 0fa74facd..497cd800a 100644 --- a/translations/et/2-Regression/README.md +++ b/translations/et/2-Regression/README.md @@ -12,7 +12,7 @@ CO_OP_TRANSLATOR_METADATA: Põhja-Ameerikas nikerdatakse kõrvitsatesse sageli hirmutavaid nägusid Halloweeni jaoks. Uurime lähemalt neid põnevaid köögivilju! -![jack-o-lanterns](../../../translated_images/jack-o-lanterns.181c661a9212457d7756f37219f660f1358af27554d856e5a991f16b4e15337c.et.jpg) +![jack-o-lanterns](../../../translated_images/jack-o-lanterns.181c661a9212457d.et.jpg) > Foto autor Beth Teutschmann lehel Unsplash ## Mida sa õpid diff --git a/translations/et/3-Web-App/README.md b/translations/et/3-Web-App/README.md index 6618e2534..ddf37eee0 100644 --- a/translations/et/3-Web-App/README.md +++ b/translations/et/3-Web-App/README.md @@ -11,7 +11,7 @@ CO_OP_TRANSLATOR_METADATA: Selles õppekava osas tutvustatakse teile rakenduslikku masinõppe teemat: kuidas salvestada oma Scikit-learn mudel failina, mida saab kasutada ennustuste tegemiseks veebirakenduses. Kui mudel on salvestatud, õpite, kuidas seda kasutada Flaskis ehitatud veebirakenduses. Kõigepealt loote mudeli, kasutades andmeid, mis käsitlevad UFO-vaatlusi! Seejärel ehitate veebirakenduse, mis võimaldab sisestada sekundite arvu koos laius- ja pikkuskraadi väärtustega, et ennustada, milline riik teatas UFO nägemisest. -![UFO Parkimine](../../../translated_images/ufo.9e787f5161da9d4d1dafc537e1da09be8210f2ee996cb638aa5cee1d92867a04.et.jpg) +![UFO Parkimine](../../../translated_images/ufo.9e787f5161da9d4d.et.jpg) Foto autor Michael Herren lehel Unsplash diff --git a/translations/et/4-Classification/1-Introduction/README.md b/translations/et/4-Classification/1-Introduction/README.md index d1796baf5..34aedbcfd 100644 --- a/translations/et/4-Classification/1-Introduction/README.md +++ b/translations/et/4-Classification/1-Introduction/README.md @@ -11,7 +11,7 @@ CO_OP_TRANSLATOR_METADATA: Nendes neljas õppetunnis uurid klassikalise masinõppe põhivaldkonda - _klassifikatsiooni_. Vaatame erinevate klassifikatsioonialgoritmide kasutamist andmekogumiga, mis käsitleb Aasia ja India suurepäraseid kööke. Loodetavasti oled näljane! -![ainult näpuotsaga!](../../../../translated_images/pinch.1b035ec9ba7e0d408313b551b60c721c9c290b2dd2094115bc87e6ddacd114c9.et.png) +![ainult näpuotsaga!](../../../../translated_images/pinch.1b035ec9ba7e0d40.et.png) > Tähista pan-Aasia kööke nendes õppetundides! Pilt: [Jen Looper](https://twitter.com/jenlooper) @@ -38,7 +38,7 @@ Klassifikatsioon on üks masinõppe teadlase ja andmeteadlase põhitegevusi. Ala Teaduslikumalt öeldes loob sinu klassifikatsioonimeetod ennustava mudeli, mis võimaldab kaardistada sisendmuutujate ja väljundmuutujate vahelisi seoseid. -![binaarne vs. mitmeklassiline klassifikatsioon](../../../../translated_images/binary-multiclass.b56d0c86c81105a697dddd82242c1d11e4d78b7afefea07a44627a0f1111c1a9.et.png) +![binaarne vs. mitmeklassiline klassifikatsioon](../../../../translated_images/binary-multiclass.b56d0c86c81105a6.et.png) > Binaarsed vs. mitmeklassilised probleemid, mida klassifikatsioonialgoritmid peavad lahendama. Infograafika: [Jen Looper](https://twitter.com/jenlooper) @@ -134,7 +134,7 @@ Nüüd muutub töö huvitavamaks. Uurime andmete jaotust köökide kaupa. df.cuisine.value_counts().plot.barh() ``` - ![köögiandmete jaotus](../../../../translated_images/cuisine-dist.d0cc2d551abe5c25f83d73a5f560927e4a061e9a4560bac1e97d35682ef3ca6d.et.png) + ![köögiandmete jaotus](../../../../translated_images/cuisine-dist.d0cc2d551abe5c25.et.png) Kööke on piiratud arv, kuid andmete jaotus on ebaühtlane. Saad selle parandada! Enne seda uurime veidi rohkem. @@ -188,7 +188,7 @@ Nüüd saad sügavamale andmetesse kaevuda ja teada saada, millised on tüüpili thai_ingredient_df.head(10).plot.barh() ``` - ![tai](../../../../translated_images/thai.0269dbab2e78bd38a132067759fe980008bdb80b6d778e5313448dbe12bed846.et.png) + ![tai](../../../../translated_images/thai.0269dbab2e78bd38.et.png) 1. Tee sama jaapani andmete jaoks: @@ -197,7 +197,7 @@ Nüüd saad sügavamale andmetesse kaevuda ja teada saada, millised on tüüpili japanese_ingredient_df.head(10).plot.barh() ``` - ![jaapani](../../../../translated_images/japanese.30260486f2a05c463c8faa62ebe7b38f0961ed293bd9a6db8eef5d3f0cf17155.et.png) + ![jaapani](../../../../translated_images/japanese.30260486f2a05c46.et.png) 1. Nüüd hiina koostisosade jaoks: @@ -206,7 +206,7 @@ Nüüd saad sügavamale andmetesse kaevuda ja teada saada, millised on tüüpili chinese_ingredient_df.head(10).plot.barh() ``` - ![hiina](../../../../translated_images/chinese.e62cafa5309f111afd1b54490336daf4e927ce32bed837069a0b7ce481dfae8d.et.png) + ![hiina](../../../../translated_images/chinese.e62cafa5309f111a.et.png) 1. Joonista india koostisosad: @@ -215,7 +215,7 @@ Nüüd saad sügavamale andmetesse kaevuda ja teada saada, millised on tüüpili indian_ingredient_df.head(10).plot.barh() ``` - ![india](../../../../translated_images/indian.2c4292002af1a1f97a4a24fec6b1459ee8ff616c3822ae56bb62b9903e192af6.et.png) + ![india](../../../../translated_images/indian.2c4292002af1a1f9.et.png) 1. Lõpuks joonista korea koostisosad: @@ -224,7 +224,7 @@ Nüüd saad sügavamale andmetesse kaevuda ja teada saada, millised on tüüpili korean_ingredient_df.head(10).plot.barh() ``` - ![korea](../../../../translated_images/korean.4a4f0274f3d9805a65e61f05597eeaad8620b03be23a2c0a705c023f65fad2c0.et.png) + ![korea](../../../../translated_images/korean.4a4f0274f3d9805a.et.png) 1. Nüüd eemalda kõige levinumad koostisosad, mis tekitavad segadust erinevate köökide vahel, kutsudes `drop()`: diff --git a/translations/et/4-Classification/1-Introduction/solution/R/lesson_10-R.ipynb b/translations/et/4-Classification/1-Introduction/solution/R/lesson_10-R.ipynb index b4234fc0b..1b2b4d078 100644 --- a/translations/et/4-Classification/1-Introduction/solution/R/lesson_10-R.ipynb +++ b/translations/et/4-Classification/1-Introduction/solution/R/lesson_10-R.ipynb @@ -39,7 +39,7 @@ "Nendes neljas õppetükis uurime klassikalise masinõppe põhivaldkonda - *klassifikatsiooni*. Vaatame, kuidas kasutada erinevaid klassifikatsioonialgoritme, kasutades andmekogumit, mis käsitleb Aasia ja India köögi imelisi roogasid. Loodetavasti olete näljased!\n", "\n", "

\n", - " \n", "

Tähistage pan-Aasia kööke nendes õppetundides! Pilt: Jen Looper
\n", "\n", @@ -64,7 +64,7 @@ "Teaduslikumalt öeldes loob teie klassifikatsioonimeetod ennustava mudeli, mis võimaldab teil kaardistada sisendmuutujate ja väljundmuutujate vahelist seost.\n", "\n", "

\n", - " \n", "

Binaarsed vs. mitmeklassilised probleemid, mida klassifikatsioonialgoritmid lahendavad. Infograafika: Jen Looper
\n", "\n", @@ -224,7 +224,7 @@ "> [Tibble](https://tibble.tidyverse.org/) on kaasaegne andmeraamistik.\n", "\n", "

\n", - " \n", "

Illustratsioon: @allison_horst
\n" ], @@ -514,7 +514,7 @@ "## Andmete eeltöötlus retseptide abil 👩‍🍳👨‍🍳 - Tasakaalustamata andmete käsitlemine ⚖️\n", "\n", "

\n", - " \n", "

Illustratsioon: @allison_horst
\n", "\n", @@ -709,7 +709,7 @@ "[Cassie Breviu](https://www.twitter.com/cassieview) ja [Jen Looper](https://www.twitter.com/jenlooper) selle mooduli algse Python-versiooni loomise eest ♥️\n", "\n", "

\n", - " \n", "

Illustratsioon: @allison_horst
\n" ],