The Most Important Machine Learning Books

The list of books that you should buy (and read) to become an expert in Machine Learning

Posted by Stacy on 15-10-2018

We compiled the list of the most cited machine learning books online. As it usually happens, older books, as well as free ones, are cited more frequently. We discounted some of them based on our own impression after reading those books.

Machine Learning Theory

The Hundred-Page Machine Learning Book (2019)

Author: Andriy Burkov

Read first, buy later

The Elements of Statistical Learning

The best book to start learning machine learning. It covers both supervised and unsupervised learning and combines an easy to read style with intuition and mathematical rigor.

The Elements of Statistical Learning (2009)

Authors: Trevor Hastie, Robert Tibshirani, Jerome Friedman

Free

The Elements of Statistical Learning

A universally acclaimed book recommended to students as a textbook for a university Machine Learning class. The reader should have a good understanding of the underlying linear algebra, statistics, and probability theory. Considered a classic book on the topic.

Understanding Machine Learning: From Theory to Algorithms (2014)

Authors: Shai Shalev-Shwartz and Shai Ben-David

Free

Understanding Machine Learning: From Theory to Algorithms

A relatively new book with both rigorous presentation of the machine learning theory and how this theory finds its implementation in various machine learning algorithms.

Reinforcement Learning: An Introduction (1998)

Authors: Richard Sutton and Andrew Barto

Understanding Machine Learning: From Theory to Algorithms

A book on a subfield of machine learning called reinforcement learning (RL), written by the pioneers in the RL research. One of the rare books covering such an important subfield of machine learning in detail.

Deep Learning (2016)

Authors: Ian Goodfellow, Yoshua Bengio, and Aaron Courville

Free

Understanding Machine Learning: From Theory to Algorithms

This book is written by deep learning pioneers: Yoshua Bengio and Ian Goodfellow. It contains the state of the art in neural network learning theory as of 2016. However, it's very math heavy and hard to read for an unprepared reader.

Machine Learning Practice

Hands-On Machine Learning with Scikit-Learn and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems (2017)

Author: Aurélien Géron

Hands-On Machine Learning with Scikit-Learn and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems

A perfect mix of theory and practice. Recommended to those who can't wait to start coding but would also like to learn the underlying theory at the same time.

Python Machine Learning: Machine Learning and Deep Learning with Python, scikit-learn, and TensorFlow (2017)

Authors: Sebastian Raschka and Vahid Mirjalili

Python Machine Learning: Machine Learning and Deep Learning with Python, scikit-learn, and TensorFlow

Another book that combines machine learning theory with practical applications. It is recommended to the reader already familiar with the basics of machine learning.

Machine Learning Yearning (2018)

Author: Andrew Ng

Free

Python Machine Learning: Machine Learning and Deep Learning with Python, scikit-learn, and TensorFlow

This book written by one of the most influential machine learning scientists and teachers, Andrew Ng, doesn't teach you the deep learning theory, it teaches engineers how to build neural network-based solutions in practice. As a prerequisite for this book, it is recommended to take the deep learning specialization on Coursera or have a basic understanding of how neural networks work.

Other Noticeable Books

Below are other remarkable books, in no specific order:

  • Pattern Recognition and Machine Learning (Christopher Bishop, 2006)

  • FREE Mining of Massive Datasets (Jure Leskovec, Anand Rajaraman, Jeff Ullman, 2010)

  • Machine Learning (Tom Mitchell, 1997)

  • FREE Neural Networks and Deep Learning (Michael Nielsen, 2015)

  • FREE An Introduction to Statistical Learning (with applications in R) (Gareth James, Daniela Witten, Trevor Hastie, and Robert Tibshirani, 2017)

  • Programming Collective Intelligence (Toby Segaran, 2018)

  • Machine Learning for Hackers (Drew Conway and John Myles White, 2012)

  • Machine Learning For Absolute Beginners: A Plain English Introduction (Oliver Theobald, 2017)

  • Introduction to Machine Learning with Python: A Guide for Data Scientists (Sarah Guido and Andreas Müller, 2016)

  • Fundamentals of Machine Learning for Predictive Data Analytics (John Kelleher, Brian Mac Namee, and Aoife D'Arcy, 2016)

  • Deep Learning with Python (François Chollet, 2017)

  • Make Your Own Neural Network (Tariq Rashid, 2016)

  • Machine Learning: A Probabilistic Perspective (Kevin Murphy, 2012)

  • Machine Learning: An Algorithmic Perspective (Stephen Marsland, 2009)

  • Machine Learning in Action (Peter Harrington, 2012)

  • FREE Building Machine Learning Systems with Python (Willi Richert and Luis Pedro Coelho, 2013)

  • Machine Learning: The Art and Science of Algorithms that Make Sense of Data (Peter Flach, 2012)

  • Machine Learning For Dummies (John Paul Mueller and Luca Massaron, 2016)

  • Introduction to Machine Learning (Ethem Alpaydin, 2009)

  • Data Mining: Practical Machine Learning Tools and Techniques (Ian Witten, Eibe Frank, Mark Hall, 2011)


This list is constantly updated. Didn't find the book you think is great? Let us know and we will consider adding this book to the list.

Read our previous post "Glossary of Machine Learning Terms" or subscribe to our RSS feed.

Found a mistyping or an inconsistency in the text? Let us know and we will improve it.


Like it? Share it!