HenryNdubuaku/maths-cs-ai-compendium Alternatives

Use it when you need a guided production-ML/MLOps curriculum rather than a math/CS theory compendium.

Learn how to develop, deploy and iterate on production-grade ML applications.

Use it when you prefer a structured, free ML-engineering bootcamp with a schedule instead of a self-study compendium.

Learn ML engineering for free in 4 months! Register here 👇🏼

Use it when you want a classic lecture/homework-driven open ML course rather than an intuition-first compendium.

Open Machine Learning Course

Use it when you want a Python build-and-ship AI-engineering curriculum instead of a reference-style compendium.

Learn it. Build it. Ship it for others.

Use it for code-first scikit-learn/Keras/TensorFlow ML/DL notebooks instead of the seed's broader math/CS survey.

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.

Use it when your focus is ML systems/edge deployment rather than the seed's broad math/CS/AI foundations.

Machine Learning Systems: Foundations, Scaling, Agentic AI, and Physical AI (Vols I–IV) • Harvard CS249r | https://mlsysbook.ai

Use it for applied training/inference engineering of large models instead of a general theoretical compendium.

Machine Learning Engineering Open Book

Use it for code-first Scikit-Learn/PyTorch/Hugging Face ML/DL tutorials instead of a broad math/CS compendium.

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.

Use it if you want a fastai-centric practical deep-learning book and accept it hasn't had updates in about two years.

The fastai book, published as Jupyter Notebooks

Use it only if you want a compact, unmaintained intro ML course with Python notebooks and don't need recent updates.

:speech_balloon: Machine Learning Course with Python:

Use it if you're following fast.ai video lectures and want practical notebooks, though it is several years old and narrower than the seed.

The fast.ai course notebooks

Use it for a rigorous math+coding interactive deep-learning textbook, but it is deep-learning-only and last updated about two years ago.

Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.

Use it for legacy Python data-science/ML notebook examples when you can work with outdated libraries.

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.

Use it if you want a Chinese-language, hands-on introductory AI course rather than the full compendium.

AI实战-practicalAI 中文版

Use it when you want NumPy first-principles derivations of core ML algorithms, not the seed's wider CS/math/AI scope.

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

Use it when you only need ML math prerequisites like linear algebra, calculus, and statistics, not full AI coverage.

Machine Learning Foundations: Linear Algebra, Calculus, Statistics & Computer Science