10 Best Machine Learning Textbooks that All Data Scientists Should Read

Article by Daniel Smith | June 13, 2019

Machine learning is an intimidating topic to tackle for the first time. The term encompasses so many fields, research topics and business use cases, that it can be difficult to even know where to start. To combat this, it’s often a good idea to turn to textbooks that will introduce you to the basic principles of your new field of research. This holds true for AI and machine learning, especially if you have a background in statistics or programming. When used alongside more focused online articles like our introduction to training data, they can be an essential part of a powerful toolkit with which to learn and grow.

In this article, we’ll showcase some of the best textbooks that the field has to offer. Frequently used in university courses and recommended by professors and engineers alike, the following textbooks provide a tried and tested introduction to the wider world of AI. Even if you’ve got bags of experience with machine learning, picking up one of these textbooks could be a great refresher. After all, there’s always something new to learn.

 

Deep Learning

Ian Goodfellow, Yoshua Bengio, and Aaron Courville

ISBN: 978-0262035613
Buy the book: on Amazon here, or read it in its entirety for free here.

When it comes to deep learning, this book is the best place to start. This comprehensive textbook provides both the general knowledge and the mathematical footing you need to get started with your own work. Deep Learning has been endorsed by a host of prominent figures in machine learning, from Geoffrey Hinton to Yann LeCun, and contains useful information for people in both research and industry.

 

 

Artificial Intelligence: A Modern Approach

Stuart J. Russell and Peter Norvig

ISBN: 978-9332543515
Buy the book: on Amazon here.

Russell and Norvig’s book is the cornerstone of a range of university-level AI programmes. Ideally suited for beginners, Artificial Intelligence provides a thorough introduction to the field and an overview of several key research topics, walking the reader through the ways in which intelligent agents reach decisions and explaining neural networks in depth. If you only own one book about AI, this is the one you need.

 

 

The Elements of Statistical Learning: Data Mining, Inference, and Prediction

Trevor Hastie, Robert Tibshirani, and Jerome Friedman

ISBN: 978-0387848570
Buy the book: on Amazon here.

A consistent favorite of the machine learning community, The Elements of Statistical Learning covers a broad range of topics within its conceptual framework. It can be used either as an introduction to or reference book for topics including neural networks, random forests, and testing methods. However, the book has also been written in a style that encourages the reader to investigate things for themselves. In this way, it forms not just an introduction, but also encourages the development of skills that are useful for a later career in machine learning. The most recent version was released in 2013.

 

The Hundred-Page Machine Learning Book

Andriy Burkov

ISBN: 978-1999579500
Buy the book: on Amazon here, or read extended versions of various chapters on the book’s website here.

This project began as a LinkedIn challenge to the author and grew into a machine learning bestseller. As the title suggests, it’s one of the most succinct introductions to the field that’s currently in print. However, Burkov doesn’t avoid the necessary math, cramming both theory and practice into a mind-bogglingly small paperback. With its wide breadth of topic coverage and endorsements from machine learning thought leaders, this short title should be on the bookshelves of all newcomers to machine learning.

 

Pattern Recognition and Machine Learning

Christopher M. Bishop

ISBN: 978-0387310732
Buy the book: on Amazon here.

Bishop’s book has been an important university text since it was first published in 2006. Although it assumes knowledge of a certain amount of linear algebra and multivariate calculus, it is a key reference point for anyone looking to understand the statistical techniques behind machine learning. It also includes a test and extensive questions at the end of the book to reinforce what you’ve learned.

 

 

Applied Predictive Modeling

Max Kuhn and Kjell Johnson

ISBN: 978-1461468486
Buy the book: on Amazon here.

Kuhn and Johnson’s book is a great choice for any students or developers looking for an introduction to predictive models and the modeling process. It covers the predictive modeling process from the beginning, starting with data preprocessing and moving through to regression and classification techniques. It focuses on solving real problems throughout, using hands-on examples and providing corresponding code in R for each stage. It also contains sets of problems in each chapter that are designed to help the reader apply what they’ve learned.

 

Machine Learning

Tom M. Mitchell

ISBN: 978-0070428072
Buy the book: on Amazon here, or read draft chapters for a possible second edition here.

Machine Learning is a compact text that provides a great introduction to the basics of machine learning. From neural networks to Bayesian learning, Mitchell explains a wide variety of concepts and algorithms at a high level. Although it doesn’t contain much in the way of tutorials or implementation advice, it should give you a solid base from which to do more in-depth research.

 

 

Python Machine Learning

Sebastian Raschka and Vahid Mirjalili

ISBN: 978-1783555130
Buy the book: on Amazon here.

For those looking to jump straight into programming, a language-specific introduction to machine learning can prove very useful. Python Machine Learning is a great choice for a more technical introduction to the topic. The book explains how to implement a range of popular machine learning algorithms, with a particular focus on using scikit-learn to do so. This is a great choice for those looking to improve their understanding of algorithm development.

 

 

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

Aurélien Géron

ISBN: 978-1491962299
Buy the book: on Amazon here.

This practical book is focused on teaching programmers how to implement machine learning programs using both the scikit-learn and TensorFlow frameworks. Géron’s explanation hinges on examples and exercises to help you learn a range of techniques, from linear regression to deep neural networks. Although it’s light on theory, this is a great book to seek out if your main goal is to quickly and intuitively learn how to build your own machine learning algorithms.

 

 

Speech and Language Processing

Daniel Jurafsky and James H. Martin

ISBN: 978-0131873216
Buy the book: on Amazon here.

For those who have a little more basic knowledge, there are also some great textbooks which give comprehensive introductions to specific fields of machine learning. Speech and Language Processing would be our pick if this is your goal. Recommended to us by several experts, this is a great source of information for anyone with an interest in natural language processing. It covers a range of language technology, unifying ideas from a range of traditionally distinct courses. With an emphasis on practical applications, this is a great introductory volume to the possibilities presented by speech and language processing.

 

 

By reading a combination of these textbooks, you’re sure to build up a solid base of machine learning knowledge, as well as a reference library that you can return to again and again throughout your time working in the field. Even if you only read one, the progress you make will give you the motivation to continue learning, improving, and making an impact.

Once you’re ready and able to create machine learning algorithms of your own, don’t forget that data is absolutely crucial to the success of your project. From image annotation to ontology creation, Lionbridge is an experienced provider of machine learning data to researchers, engineers, and businesses who need datasets they can trust. For comprehensive annotations and a solid ground truth, look to us for all your annotation needs.

Discover how we can improve your model
The Author
Daniel Smith

Daniel writes a variety of content for Lionbridge’s website as part of the marketing team. Born and raised in the UK, he first came to Japan by chance in 2013 and is continually surprised that no one has thrown him out yet. Outside of Lionbridge, he loves to travel, take photos and listen to music that his neighbors really, really hate.

    Welcome!

    Sign up to our newsletter for fresh developments from the world of training data. Lionbridge brings you interviews with industry experts, dataset collections and more.