machine learning education / notebook tutorials
A Chinese translation of practicalAI: a set of Jupyter notebooks that teach hands-on machine learning and deep learning with PyTorch in Google Colab.
Same problem, same approach. Swapping one for another is a config change, not a rewrite.
When you need the same PyTorch-based notebook format in an actively maintained English version covering both ML and deep learning.
A series of Jupyter notebooks that walk you through the fundamentals of Machine Learning and Deep Learning in Python using Scikit-Learn, PyTorch, and Hugging Face libraries.
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
When you prefer fastai's higher-level API and a book-led, top-down learning path over framework-native PyTorch notebooks.
The fastai book, published as Jupyter Notebooks
When you want a broad assortment of standalone ML/DL code examples to consult rather than a single guided notebook sequence.
A resource for learning about Machine learning & Deep Learning
When your target stack is TensorFlow/Keras and you want a structured university course with notebooks.
T81-558: Keras - Applications of Deep Neural Networks @Washington University in St. Louis
When you want a Chinese theoretical textbook on neural networks and deep learning, not an interactive coding course.
邱锡鹏《神经网络与深度学习》第二版与通识版：电子书、章节目录、学习资源与勘误。
When you want a lesson-based curriculum with quizzes and assignments using multiple ML libraries, rather than the seed's open PyTorch notebooks.
12 Weeks, 24 Lessons, AI for All!
When you want the same kind of broad Hands-on ML notebook course but with TensorFlow/Keras instead of PyTorch.
A series of Jupyter notebooks that walk you through the fundamentals of Machine Learning and Deep Learning in Python using Scikit-Learn, Keras and TensorFlow 2.
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
When you only need classical ML algorithms and want NumPy-based derivations in notebooks, without deep learning.
ML algorithms implemented and derived from first-principles in Jupyter Notebooks and NumPy
When you are learning deep learning in Chinese and specifically want Li Hongyi's course notebooks rather than the broader ML+DL seed.
《李宏毅深度学习教程》（李宏毅老师推荐👍，苹果书🍎），PDF下载地址：https://github.com/datawhalechina/leedl-tutorial/releases
When you want a traditional ML course (with scikit-learn) and don't need the deep learning sections of the seed.
Open Machine Learning Course
When you want MIT's TensorFlow deep learning lab notebooks and your scope is deep learning only.
Lab Materials for MIT 6.S191: Introduction to Deep Learning
When you want minimal, clean Python implementations of core ML algorithms for reading, not a PyTorch notebook course.
Minimal and clean examples of machine learning algorithms implementations
When you specifically need legacy TensorFlow v1/v2 example snippets for comparison or historical reference.
TensorFlow Tutorial and Examples for Beginners (support TF v1 & v2)
When you already know ML basics and want rigorous advanced PyTorch deep learning notebooks from the UvA course.
Repository of Jupyter notebook tutorials for teaching the Deep Learning Course at the University of Amsterdam (MSc AI), Fall 2023
When you want a polished, comprehensive Chinese ML+DL notebook textbook and can accept a repository not updated recently.
《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。
When you want a popular, beginner-friendly PyTorch deep learning zero-to-mastery course that doesn't cover classical ML.
Materials for the Learn PyTorch for Deep Learning: Zero to Mastery course.
When you want the code backing Raschka's older ML book, with scikit-learn and pre-PyTorch neural network code.
The "Python Machine Learning (1st edition)" book code repository and info resource
When you're learning scikit-learn via video companion notebooks and need only that library's basics.
Jupyter notebooks from the scikit-learn video series
When you want a very rudimentary, challenge-style ML code path; it is not deep or comprehensive compared to the seed.
100 Days of ML Coding
When you want a Chinese language handbook focused on learning PyTorch's APIs, but it does not cover the seed's full ML/DL scope.
pytorch handbook是一本开源的书籍，目标是帮助那些希望和使用PyTorch进行深度学习开发和研究的朋友快速入门，其中包含的Pytorch教程全部通过测试保证可以成功运行
When you want plain Python implementations of fundamental ML algorithms without the deep learning or PyTorch notebook material.
Plain python implementations of basic machine learning algorithms
When you want Raschka's older tutorial collection for pattern classification/ML tasks, as a reference instead of a full course.
A collection of tutorials and examples for solving and understanding machine learning and pattern classification tasks
When you want a collection of notes/experiments/videos to tinker with deep learning rather than a coherent course.
Videos, notes and experiments to understand deep learning
These projects were analysed and named practicalAI-cn among their alternatives. The relationship is not symmetric — how practicalAI-cn rates them is a separate judgement, made when practicalAI-cn is analysed in its own right.
calls practicalAI-cn “choose when you want a concise exercise-driven Chinese PyTorch course instead of a broad handbook.”
pytorch handbook是一本开源的书籍，目标是帮助那些希望和使用PyTorch进行深度学习开发和研究的朋友快速入门，其中包含的Pytorch教程全部通过测试保证可以成功运行
calls practicalAI-cn “For Chinese-language learners who want hands-on ML notebooks in their native language.”
A resource for learning about Machine learning & Deep Learning
calls practicalAI-cn “Choose it for a Chinese practicalAI course with PyTorch examples and a project-based curriculum.”
Build your neural network easy and fast, 莫烦Python中文教学
calls practicalAI-cn “choose for a structured Chinese-language PyTorch AI course instead of a 100-day challenge.”
100 Days of ML Coding
calls practicalAI-cn “Chinese-language ML course notebooks; alternative for Chinese speakers wanting a practical ML focus”
Python Data Science Handbook: full text in Jupyter Notebooks
calls practicalAI-cn “Choose for a structured, PyTorch-based ML curriculum in Chinese rather than TensorFlow examples.”
TensorFlow Tutorial and Examples for Beginners (support TF v1 & v2)
calls practicalAI-cn “Choose for a Chinese-language practical ML course with notebooks.”
🤖 Python examples of popular machine learning algorithms with interactive Jupyter demos and math being explained
calls practicalAI-cn “choose for a hands-on Chinese introduction with practical projects, if you prefer applied learning over theory.”
邱锡鹏《神经网络与深度学习》第二版与通识版：电子书、章节目录、学习资源与勘误。
calls practicalAI-cn “Choose for a practical, hands-on Chinese course, but it focuses on application more than theory.”
《李宏毅深度学习教程》（李宏毅老师推荐👍，苹果书🍎），PDF下载地址：https://github.com/datawhalechina/leedl-tutorial/releases
calls practicalAI-cn “Choose for a Chinese-language hands-on practical AI course rather than an English book repo.”
The "Python Machine Learning (1st edition)" book code repository and info resource
calls practicalAI-cn “when you want a translated notebook-based practical AI course, particularly for Chinese-speaking learners.”
Open Machine Learning Course
calls practicalAI-cn “When you want a Chinese version of the practicalAI course, which teaches ML with PyTorch in a project-based way.”
A collection of machine learning examples and tutorials.
calls practicalAI-cn “Choose when you want a Chinese-translated practical ML curriculum with end-to-end projects rather than MIT's lecture-aligned labs.”
Lab Materials for MIT 6.S191: Introduction to Deep Learning
calls practicalAI-cn “Chinese-translated practical AI notebooks; choose for Chinese-language instruction.”
Data science Python notebooks: Deep learning (TensorFlow, Theano, Caffe, Keras), scikit-learn, Kaggle, big data (Spark, Hadoop MapReduce, HDFS), matplotlib, pandas, NumPy, SciPy, Python essentials, AWS, and various command lines.
calls practicalAI-cn “Use it if you want a Chinese-language, hands-on introductory AI course rather than the full compendium.”
Become a cracked AI/ML researcher/engineer with this unconventional textbook covering maths, computing, and ML with intuition.