ageron/handson-ml Alternatives

Use as a modern, comprehensive book-code alternative covering the same ML+Dl curriculum with scikit-learn and PyTorch.

Code Repository for Machine Learning with PyTorch and Scikit-Learn

Choose when you want algorithms explained from first principles with NumPy instead of sklearn/TensorFlow.

ML algorithms implemented and derived from first-principles in Jupyter Notebooks and NumPy

Choose for a structured MOOC with videos and quizzes, focused solely on scikit-learn (no deep learning).

Machine learning in Python with scikit-learn MOOC

Choose when you want to build ML models from scratch in plain Python rather than use library APIs.

Master the fundamentals of machine learning, deep learning, and mathematical optimization by building key concepts and models from scratch using Python.

Choose for a broader Python data science handbook that includes ML along with numpy/pandas/visualization.

Python Data Science Handbook: full text in Jupyter Notebooks

Choose when you want minimal standalone implementations of ML algorithms for reference, not a full tutorial.

Minimal and clean examples of machine learning algorithms implementations

Choose when you already know classic ML and need a Keras/TensorFlow deep-learning-only companion.

Jupyter notebooks for the code samples of the book "Deep Learning with Python"

Choose for Raschka's older first-edition book code with scikit-learn and Theano if you prefer that teaching style.

The "Python Machine Learning (1st edition)" book code repository and info resource

Choose for a deep-learning-only academic lecture and lab series, albeit no longer updated.

Slides and Jupyter notebooks for the Deep Learning lectures at Master Year 2 Data Science from Institut Polytechnique de Paris

Choose for an early, simple scikit-learn book code if you want a short introduction and don't mind outdated material.

Source code for the "Learning scikit-learn: Machine Learning in Python"

Choose for a modern PyTorch deep-learning-only course (Zero to Mastery) instead of broad ML.

Materials for the Learn PyTorch for Deep Learning: Zero to Mastery course.

Choose for a practical but unmaintained ML book code covering scikit-learn and Keras.

Master the essential skills needed to recognize and solve complex real-world problems with Machine Learning and Deep Learning by leveraging the highly popular Python Machine Learning Eco-system.

Choose for the classic NN/DL book that explains backprop from scratch, but only covers neural networks and is dated.

Code samples for my book "Neural Networks and Deep Learning"

Choose for the fastai deep-learning book, but only if you want a DL-focused, fastai-based path.

The fastai book, published as Jupyter Notebooks

Choose for the comprehensive 'Dive into Deep Learning' Chinese book code, but it covers deep learning only.

《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。