10 Must-Read Machine Learning Books

Aurélie Drouet

December 21, 2020

7 Minute Read

With the year coming to a close and not many other things to do than to stay put at home, this holiday season could be the perfect time to dive deeper into some books. If you have a passing interest or are just looking for a refresher in all things Machine Learning, we have put together a list of 10 books. Although published at varying points in the development of Deep Learning and Machine Learning, each book offers unique insights. It was near impossible to narrow the list to just ten, but we couldn’t look past those below.


1. Grokking Deep Learning
Andrew W Trask (2009)

Grokking Deep Learning is suggested to be a perfect place to delve into the subset of Machine Learning, not only describing and explaining APIs and frameworks, but also talking the reader through how they can actually build algorithms from scratch. This hands-on style of writing will help you build an AI capable of beating you in a classic game of Atari and Neural Networks capable of understanding basic images. While this is not a beginners guide, experience with calculus is not required, merely a high school level of mathematical understanding.

2. The Hundred-Page Machine Learning Book
Andriy Burkov (2019)

An all you need to know guide to Machine Learning in just 100 pages, what more could you need? The Director of Data Science at Gartner, Andriy, suggests that you are a mere read of this book away from being ready to build complex AI systems, pass an interview or start your own business. Also available on Kindle, the 2019 release covers gradient descent, cluster analysis, dimensionality reduction and more. Is it for you? Andriy suggests that it is suitable for those both working in the field and those dipping their toe to find out more about the increasingly complex field of Machine Learning.


3. Introduction to Machine Learning with Python: A Guide for Data Scientists
Sarah Guido & Andreas C. Mueller (2016)

Although released in 2016, this 400 word bible for Machine Learning gives a great grounding in the basics of ML, providing a thorough and hands-on approach to Python use in ML. Learn not only what the most important concepts and algorithms are, but also when and how to use them. Imperative topics including machine learning workflow: data preprocessing and working with data are covered, as well as training algorithms, evaluating results, and implementing those algorithms into a production-level system


4. Machine Learning For Absolute Beginners: A Plain English Introduction
Oliver Theobold (2017)

A curveball, maybe, as we realize that those reading this list may have experience in the field, however, Machine Learning for Absolute Beginners walks through ML history and works in plain english with no coding experience necessary. What exactly will you be learning? The very basics including, decision trees, regression analysis, data reduction, k-means and more, giving you a great underlying understanding of the building blocks used in Machine Learning and how they can be used. Finally, some career advice with Oliver talking you through career options and how best to utilize the ML knowledge just picked up post-read.


5. Mathematics for Machine Learning
Marc Peter Deisenroth (2020)

This textbook puts the normally disparate course style of teaching in Mathematics to shame, combining together all of the fundamental mathematical tools needed to understand machine learning, including linear algebra, analytic geometry, matrix decompositions, vector calculus, optimization, probability and statistics. These concepts are then used to derive four central machine learning methods: linear regression, principal component analysis, Gaussian mixture models and support vector machines, giving a brilliant starting point for those entering the field and those looking for a refresher. Alongside the textual information, this book also includes examples and tests to ensure the reader's understanding.


6. Pattern Recognition and Machine Learning
Christopher M. Bishop (2007)

Christopher Bishop’s Pattern Recognition and Machine Learning presents approximate inference algorithms that permit fast approximate answers in situations where exact answers are not feasible. The first of its kind on pattern recognition to present the Bayesian viewpoint, uses graphical models to describe probability distributions, which at the time, was not evident in any other ML text. Unlike some of the other inclusions on this list, familiarity with multivariate calculus and basic linear algebra is required, and some experience in the use of probabilities would be helpful though not essential.


7. Probabilistic Graphical Models: Principles and Techniques
Daphne Koller & Nir Friedman (2009)

A general framework for constructing and using probabilistic models of complex systems that would enable a computer to use available information for making decisions. This book isn’t for beginners, nor for the faint of heart as it dives right into probabilistic graphical models in detail, including Bayesian and Markov Networks, inference, and learning from complete / incomplete data. If you want to get the most out of this book, there’s an option to attend Daphne Koller’s lectures on Probabilistic Graphical Models at Stanford University, on Coursera. Fun fact, Koller is actually one of the founders of Coursera, an online education platform.


8. Machine Learning: A Bayesian and Optimization Perspective (Net Developers)
Sergios Theodoridis (2015)

The book builds carefully from the basic classical methods to the most recent trends of the time, including chapters on pattern recognition, statistical/adaptive signal processing, statistical/Bayesian learning, as well as short courses on sparse modeling, deep learning, and probabilistic graphical models. All of the major techniques you’ll need to know prior to working in the field are covered, including Mean/Least-Squares regression and filtering, Kalman filtering, stochastic approximation and online learning, Bayesian classification, decision trees, logistic regression and boosting methods. Alongside all of the theoretical text, this book includes case studies, code to be experimented with and more.


9. Machine Learning: A Probabilistic Perspective
Kevin P. Murphy & Francis Bach (2012)

Kevin describes this text as a comprehensive introduction to machine learning methods that use probabilistic models and inference as a unifying approach. This overview text combines breadth and depth, offering necessary background material on such topics as probability, optimization, and linear algebra as well as discussion of recent developments in the field, including conditional random fields, L1 regularization, and deep learning. Rather than providing a cookbook of different heuristic methods, the book stresses a principled model-based approach, often using the language of graphical models to specify models in a concise and intuitive way. Alongside this, the software platforms used in examples are freely available online. Unlike some of the other texts in this list, Machine Learning: A Probabilistic Perspective is suitable for upper-level undergraduates, giving an ideal introduction to ML and Mathematical formulas.


10. Hands-on Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems
Aurelien Geron (2019)

In the last few years, breakthroughs in Deep Learning have boosted the entire field of machine learning. Now, even programmers who know close to nothing about this technology can use simple, efficient tools to implement programs capable of learning from data. Through minimal use of theory and maximum practical examples, this text helps you gain an intuitive understanding of the concepts and tools for building intelligent systems. You'll learn a range of techniques, starting with simple linear regression and progressing to deep neural networks. With regular examples throughout, it’s a great book to not only grasp how and why it all works, but to also test it yourself.