Master machine learning through clarity, not complexity―in a book engineered to teach with exceptional conciseness.

Translated into 11 languages and used in thousands of universities worldwide, this book takes a unique approach: it assumes that your time is valuable. Instead of drowning you in theory or skimming the surface, it delivers a complete education in modern machine learning, focusing on what matters in practice. From fundamental algorithms that form the backbone of many applications, to cutting-edge deep learning and neural networks, you'll understand how these tools work and how to use them.

What sets this book apart is its careful progression through key concepts. You'll start with essential mathematical concepts and gradually progress through the most practically important machine learning algorithms. You'll learn practical skills like feature engineering, regularization, handling imbalanced datasets, ensembles, and model evaluation that help turn theory into working systems.

The book covers not just supervised learning, but also clustering, topic modeling, metric learning, learning to rank, and recommendation systems, giving you a complete toolkit for solving modern machine learning challenges.

This isn't just another theoretical textbook. Every chapter reflects the author's real-world experience, focusing on techniques that work in practice. Whether you're building a recommendation system, analyzing customer data, or working with images and text, you'll find practical guidance here.

This isn't a high-level overview either. The book explores each concept with precisely the right level of technical detail—enough to create those crucial "a-ha!" moments of understanding, but not so much that you get overwhelmed by mathematical notation or theoretical abstractions. It hits that sweet spot where complex ideas click into place naturally, making it valuable for both newcomers looking to build a strong foundation and experienced practitioners seeking to expand their toolkit.

What's Inside

• Supervised and unsupervised learning algorithms, including deep neural networks
• Clear, intuitive explanations of algorithms and mathematics that preserve essential details
• Practical techniques for building, debugging, and evaluating models
• Advanced topics including ensembles, recommender systems, and metric learning

About the Reader

The book assumes a basic foundation in college-level mathematics. However, it's entirely self-contained, introducing all necessary mathematical concepts through intuitive explanations. This approach ensures that readers with basic mathematical knowledge can follow along without getting lost in complex equations.

Endorsements

Peter Norvig, Research Director at Google, co-author of AIMA, the most popular AI textbook in the world: "Burkov has undertaken a very useful but impossibly hard task in reducing all of machine learning to 100 pages. He succeeds well in choosing the topics — both theory and practice — that will be useful to practitioners, and for the reader who understands that this is the first 100 (or actually 150) pages you will read, not the last, provides a solid introduction to the field."

Aurélien Géron, Senior AI Engineer, author of the bestseller Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: "The breadth of topics the book covers is amazing for just 100 pages (plus few bonus pages!). Burkov doesn't hesitate to go into the math equations: that's one thing that short books usually drop. I really liked how the author explains the core concepts in just a few words. The book can be very useful for newcomers in the field, as well as for old-timers who can gain from such a broad view of the field."

More endorsements on themlbook.com