Resources#
These are starting points rather than a required reading list. Choose a practical tutorial when you want to build something, or a mathematical text when you want to understand an assumption more deeply. Package documentation is listed separately in the Software Toolkit.
Practical starting points#
Hands-On Machine Learning with Scikit-Learn and PyTorch by Aurélien Géron is a broad, implementation-focused introduction aligned with this site’s PyTorch-first stack.
Deep Learning with Python, Third Edition by François Chollet presents high-level deep-learning workflows with Keras 3 and modern backends.
An Introduction to Statistical Learning combines accessible explanations with freely available editions and labs, including Python material.
Dive into Deep Learning is an interactive, notebook-based introduction with a PyTorch implementation.
Mathematical and probabilistic foundations#
The Elements of Statistical Learning by Trevor Hastie, Robert Tibshirani, and Jerome Friedman offers a more mathematical treatment of statistical learning.
Pattern Recognition and Machine Learning by Christopher Bishop develops probabilistic pattern recognition and approximate inference.
Deep Learning by Ian Goodfellow, Yoshua Bengio, and Aaron Courville is a comprehensive neural-network reference.
Probabilistic Machine Learning by Kevin Murphy provides a modern probabilistic perspective.
Mathematics for Machine Learning by Marc Peter Deisenroth, A. Aldo Faisal, and Cheng Soon Ong reviews the linear algebra, calculus, probability, and optimization behind common methods.
Lectures and online courses#
Machine Learning Specialization offers a structured, beginner-friendly introduction. Some implementation choices differ from this site’s PyTorch-first stack, but the core concepts transfer.
Deep Learning Specialization focuses on neural networks and practical deep-learning methods.
fast.ai emphasizes building useful models early and understanding the practical decisions behind them.
Google Machine Learning Crash Course provides short lessons, visual explanations, and browser-based exercises.
MIT 6.036: Introduction to Machine Learning provides mathematically oriented lectures and course materials.
Stanford Machine Learning lectures cover a broad set of foundational methods and modeling ideas.
Steve Brunton’s Eigensteve channel is a particularly useful source for optimization, dynamical systems, and physics-informed machine learning.
More visual explanations, exercises, and collections
MLU Explain uses focused visual explanations for machine-learning concepts.
ML Pen-and-Paper Exercises provides mathematical practice without tying the questions to one software framework.
The Hundred-Page Machine Learning Book is a compact overview and quick reference.
DAIR.AI ML Course Notes collects notes and links across many machine-learning topics.
Machine Learning Guide is a broad index of tools, courses, books, and communities.