Best Deep Learning Books: Updated for 2019-2020

Are you looking to do some deep learning about deep learning? I’ve done my fair share of digging to pull together this list. Just so you don't have to.

Here it is — the list of the best machine learning & deep learning books for 2019.

What's new in 2020?! Here's the list updated for 2020.

• Deep Learning by Ian Goodfellow, Yoshua Bengio, Aaron Courville
• Grokking Deep Learning by Andrew W. Trask
• Deep Learning with Python by Francois Chollet
• Hands-On Machine Learning with Scikit-Learn and TensorFlow by Aurélien Géron
• The Hundred-Page Machine Learning Book by Andriy Burkov
• Reinforcement Learning: An Introduction (2nd Edition) by Richard S. Sutton, Andrew G. Barto
• Deep Reinforcement Learning Hands-On by Maxim Lapan
• Learning From Data by Yaser S. Abu-Mostafa, Malik Magdon-Ismail, Hsuan-Tien Lin.
• The Book of Why by Judea Pearl, Dana Mackenzie.
• Machine Learning Yearning by Andrew Ng.
• Interpretable Machine Learning by Christoph Molnar.
• Neural Networks and Deep Learning by Michael Nielsen.

Deep Learning

Authors: Ian Goodfellow, Yoshua Bengio, Aaron Courville.
Where you can get it: Buy on Amazon or read here for free.
Supplement: You can also find the lectures with slides and exercises (github repo).
Category: Deep Learning.

This book is widely considered to the "Bible" of Deep Learning. Written by three experts, including one of the godfathers of the field, this is the most comprehensive book you can find. The book is quite technical but the authors do a great job at explaining everything you need to know to get started.

Book abstract:

Deep learning is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts. Because the computer gathers knowledge from experience, there is no need for a human computer operator to formally specify all the knowledge that the computer needs. The hierarchy of concepts allows the computer to learn complicated concepts by building them out of simpler ones; a graph of these hierarchies would be many layers deep. This book introduces a broad range of topics in deep learning.

The text offers mathematical and conceptual background, covering relevant concepts in linear algebra, probability theory and information theory, numerical computation, and machine learning. It describes deep learning techniques used by practitioners in industry, including deep feedforward networks, regularization, optimization algorithms, convolutional networks, sequence modeling, and practical methodology; and it surveys such applications as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames. Finally, the book offers research perspectives, covering such theoretical topics as linear factor models, autoencoders, representation learning, structured probabilistic models, Monte Carlo methods, the partition function, approximate inference, and deep generative models.

Deep Learning can be used by undergraduate or graduate students planning careers in either industry or research, and by software engineers who want to begin using deep learning in their products or platforms. A website offers supplementary material for both readers and instructors.

Grokking Deep Learning

Author: Andrew W. Trask
Where you can get it: Buy on Amazon or Manning publications.
Supplement: You can find the companion code on Github.
Category: Deep Learning.
About the readers: For readers with high school-level math and intermediate programming skills.

For those of you who don't know, Andrew Trask is the force behind OpenMined: an open-source community focused on researching, developing, and promoting tools for secure, privacy-preserving, value-aligned artificial intelligence. He writes a great blog. No surprises on his book making our list. Yes, he's a FloydHub friend. No, we're not biased. We've really loved the first principles approach of learning from the ground up with NumPy. This is probably the best approach you can follow to learn how Deep Learning works behind the scenes.

Book abstract:

Grokking Deep Learning teaches you to build deep learning neural networks from scratch! In his engaging style, seasoned deep learning expert Andrew Trask shows you the science under the hood, so you grok for yourself every detail of training neural networks. Using only Python and its math-supporting library, NumPy, you'll train your own neural networks to see and understand images, translate text into different languages, and even write like Shakespeare! When you're done, you'll be fully prepared to move on to mastering deep learning frameworks.

Deep Learning with Python

Author: Francois Chollet
Where you can get it: Buy on Amazon, Manning publications or O'Reilly - Safari.
Supplement: You can find the companion code on Github.
Category: Deep Learning.
About the readers: Readers need intermediate Python skills. No previous experience with Keras, TensorFlow, or machine learning is required.

From the Keras inventor (and another FloydHub friend), this book will literally take you by the hand and lead you to the mesmerizing mazes of Deep Learning - with Keras of course. Similar to Grokking Deep Learning this book strikes the right balance between theory and coding. Not to mention Francois's ability to create great mental images.  

Book abstract:

Deep Learning with Python introduces the field of deep learning using the Python language and the powerful Keras library. Written by Keras creator and Google AI researcher François Chollet, this book builds your understanding through intuitive explanations and practical examples. You'll explore challenging concepts and practice with applications in computer vision, natural-language processing, and generative models. By the time you finish, you'll have the knowledge and hands-on skills to apply deep learning in your own projects.

Hands-On Machine Learning with Scikit-Learn and TensorFlow

Concepts, Tools, and Techniques to Build Intelligent Systems (2nd edition)

Author: Aurélien Géron.
Where you can get it: Buy the first edition on Amazon. You can get the second edition on Amazon or O'Reilly Shop.
Supplement: You can find the companion code on Github.
Categories: Machine & Deep Learning.

Aurélien shines as a great communicator of ideas and uses examples effectively. You'll get to apply what they are learning pretty quickly as you work through the book.  To get a feel for his passion and communication style, check out his YouTube channel.

Book abstract (2nd edition):

Through a series of recent breakthroughs, deep learning has 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.

The updated edition of this best-selling book uses concrete examples, minimal theory, and two production-ready Python frameworks—Scikit-Learn and TensorFlow 2.0—to help you gain an intuitive understanding of the concepts and tools for building intelligent systems. Practitioners will learn a range of techniques that they can quickly put to use on the job. Part 1 employs Scikit-Learn to introduce fundamental machine learning tasks, such as simple linear regression. Part 2, which has been significantly updated, employs Keras and TensorFlow 2.0 to guide the reader through more advanced machine learning methods using deep neural networks. With exercises in each chapter to help you apply what you’ve learned, all you need is programming experience to get started.

NEW FOR THE SECOND EDITION:Updated all code to TensorFlow 2.o Introduced the high-level Keras API. New and expanded coverage including TensorFlow’s Data API, Eager Execution, Estimators API, deploying on Google Cloud ML, handling time series, embeddings and more.

The Hundred-Page Machine Learning Book

Author: Andriy Burkov.
Where you can get it: Buy on Amazon. This book is distributed on the “read first, buy later” principle. The read first, buy later principle implies that you can freely download the book, read it and share it with your friends and colleagues. If you liked the book, only then you have to buy it.
Supplement: You can find the companion wiki and the code examples on Github.
Categories: Machine & Deep Learning.

The book was born from a challenge on LinkedIn (where Andriy is an influencer and Top Voice). His book doesn't need too much of an introduction: Amazon best seller in his category and probably the best knowledge compression on paper ever made on this topic.

Here is what the experts think:

Reinforcement Learning: An Introduction (2nd Edition)

Authors: Richard S. Sutton, Andrew G. Barto.
Where you can get it: Buy on Amazon. You can read the final draft of 2nd edition for free.
Categories: Machine Learning, Reinforcement Learning, Deep Learning, Deep Reinforcement Learning, Artificial Intelligence.

If the Deep Learning book is considered the Bible for Deep Learning, this masterpiece earns that title for Reinforcement Learning. If you want to get started in RL, this is the way. Just like you predicted (pat on the back), this is a pretty technical read. Our advice is take a break after each chapter, load up on the coffee and actually implement the algorithms (à la these famous repos).  

Book abstract:

Reinforcement learning, one of the most active research areas in artificial intelligence, is a computational approach to learning whereby an agent tries to maximize the total amount of reward it receives while interacting with a complex, uncertain environment. In Reinforcement Learning, Richard Sutton and Andrew Barto provide a clear and simple account of the field's key ideas and algorithms. This second edition has been significantly expanded and updated, presenting new topics and updating coverage of other topics.

Like the first edition, this second edition focuses on core online learning algorithms, with the more mathematical material set off in shaded boxes. Part I covers as much of reinforcement learning as possible without going beyond the tabular case for which exact solutions can be found. Many algorithms presented in this part are new to the second edition, including UCB, Expected Sarsa, and Double Learning. Part II extends these ideas to function approximation, with new sections on such topics as artificial neural networks and the Fourier basis, and offers expanded treatment of off-policy learning and policy-gradient methods. Part III has new chapters on reinforcement learning's relationships to psychology and neuroscience, as well as an updated case-studies chapter including AlphaGo and AlphaGo Zero, Atari game playing, and IBM Watson's wagering strategy. The final chapter discusses the future societal impacts of reinforcement learning.

Deep Reinforcement Learning Hands-On

Apply modern RL methods, with deep Q-networks, value iteration, policy gradients, TRPO, AlphaGo Zero and more

Authors: Maxim Lapan.
Where you can get it: Buy on Amazon or Packt.
Supplement: You can find the companion code on Github.
Categories: Machine Learning, Reinforcement Learning, Deep Learning, Deep Reinforcement Learning, Artificial Intelligence.

I came across Maxim's book from one his blog posts. I literally fell in love with his writing style and the attention to detail (so should you). This book offers a practical approach to RL by balancing theory with coding practice. A book to get your hands dirty but also with a ton of knowledge about how to do it correctly and understand what is happening behind the scenes. The best hands-on style book on RL.

Book abstract:

Recent developments in reinforcement learning (RL), combined with deep learning (DL), have seen unprecedented progress made towards training agents to solve complex problems in a human-like way. Google’s use of algorithms to play and defeat the well-known Atari arcade games has propelled the field to prominence, and researchers are generating new ideas at a rapid pace.

Deep Reinforcement Learning Hands-On is a comprehensive guide to the very latest DL tools and their limitations. You will evaluate methods including Cross-entropy and policy gradients, before applying them to real-world environments. Take on both the Atari set of virtual games and family favorites such as Connect4. The book provides an introduction to the basics of RL, giving you the know-how to code intelligent learning agents to take on a formidable array of practical tasks. Discover how to implement Q-learning on ‘grid world’ environments, teach your agent to buy and trade stocks, and find out how natural language models are driving the boom in chatbots.

Learning From Data

Authors: Yaser S. Abu-Mostafa, Malik Magdon-Ismail, Hsuan-Tien Lin.
Where you can get it: Buy on Amazon.
Category: Machine Learning.
Supplement: You can find the companion lectures and videos.

If you want to get started with the key concepts of Machine Learning, then you will love this book: easy to follow, simple and clean. Probably the best resource after the Andrew Ng courses to get started!  This was my first book and course on Machine Learning :)

Book abstract:

This book, together with specially prepared online material freely accessible to our readers, provides a complete introduction to Machine Learning, the technology that enables computational systems to adaptively improve their performance with experience accumulated from the observed data. Such techniques are widely applied in engineering, science, finance, and commerce. This book is designed for a short course on machine learning. It is a short course, not a hurried course. From over a decade of teaching this material, we have distilled what we believe to be the core topics that every student of the subject should know. In addition, our readers are given free access to online e-Chapters that we update with the current trends in Machine Learning, such as deep learning and support vector machines. We chose the title `learning from data' that faithfully describes what the subject is about, and made it a point to cover the topics in a story-like fashion. Our hope is that the reader can learn all the fundamentals of the subject by reading the book cover to cover. Learning from data has distinct theoretical and practical tracks. In this book, we balance the theoretical and the practical, the mathematical and the heuristic. Theory that establishes the conceptual framework for learning is included, and so are heuristics that impact the performance of real learning systems. What we have emphasized are the necessary fundamentals that give any student of learning from data a solid foundation. The authors are professors at California Institute of Technology (Caltech), Rensselaer Polytechnic Institute (RPI), and National Taiwan University (NTU), where this book is the text for their popular courses on machine learning. The authors also consult extensively with financial and commercial companies on machine learning applications, and have led winning teams in machine learning competitions.

The Book of Why

Authors: Judea Pearl, Dana Mackenzie.
Where you can get it: Buy on Amazon.
Categories: Data Science, AI and Machine Learning.

This is the most controversial book on our list. The author introduces the causality framework to overcome curve-fitting of ML/DL models and his views on our path to achieve Artificial General Intelligence. This is the right book if you are looking for something to make you think (a lot)!

Book abstract:

"Correlation is not causation." This mantra, chanted by scientists for more than a century, has led to a virtual prohibition on causal talk. Today, that taboo is dead. The causal revolution, instigated by Judea Pearl and his colleagues, has cut through a century of confusion and established causality--the study of cause and effect--on a firm scientific basis. His work explains how we can know easy things, like whether it was rain or a sprinkler that made a sidewalk wet; and how to answer hard questions, like whether a drug cured an illness. Pearl's work enables us to know not just whether one thing causes another: it lets us explore the world that is and the worlds that could have been. It shows us the essence of human thought and key to artificial intelligence. Anyone who wants to understand either needs The Book of Why.

Machine Learning Yearning

Author: Andrew Ng.
Where you can get it: You can get the latest draft for free.
Category: Machine Learning, Deep Learning, Strategy & Planning.

This book comes from the years of practical experience that Andrew acquired while he led the Deep Learning teams at Baidu and Google Brain. This is one of few resources that show you how to set up your ML/DL projects to work for real and your compass to help you to efficiently navigate in your experiments. This is a must read.

Book abstract:

AI is transforming numerous industries. Machine Learning Yearning, a free book that Dr. Andrew Ng is currently writing, teaches you how to structure Machine Learning projects.

This book is focused not on teaching you ML algorithms, but on how to make ML algorithms work. After reading Machine Learning Yearning, you will be able to:

- Prioritize the most promising directions for an AI project
- Diagnose errors in a machine learning system
- Build ML in complex settings, such as mismatched training/test sets
- Set up an ML project to compare to and/or surpass human-level performance
- Know when and how to apply end-to-end learning, transfer learning, and multi-task learning.

Interpretable Machine Learning

A Guide for Making Black Box Models Explainable

Author:  Christoph Molnar.
Where you can get it: Buy on LeanPub. You can read it for free.
Category: Machine Learning, Intrepretability.

Interpretability is rapidly becoming a hot topic to solve in Deep Learning. Unboxing the black box is still an active research area for Deep Learning, but luckily for Machine Learning models we actually have more tools available - this is one of the good ones.

Book abstract:

Machine learning has great potential for improving products, processes and research. But computers usually do not explain their predictions which is a barrier to the adoption of machine learning. This book is about making machine learning models and their decisions interpretable.

After exploring the concepts of interpretability, you will learn about simple, interpretable models such as decision trees, decision rules and linear regression. Later chapters focus on general model-agnostic methods for interpreting black box models like feature importance and accumulated local effects and explaining individual predictions with Shapley values and LIME.

All interpretation methods are explained in depth and discussed critically. How do they work under the hood? What are their strengths and weaknesses? How can their outputs be interpreted? This book will enable you to select and correctly apply the interpretation method that is most suitable for your machine learning project.

The book focuses on machine learning models for tabular data (also called relational or structured data) and less on computer vision and natural language processing tasks. Reading the book is recommended for machine learning practitioners, data scientists, statisticians, and anyone else interested in making machine learning models interpretable.

Neural Networks and Deep Learning

Author: Michael Nielsen.
Where you can get it: You can read it for free.
Supplement: You can find the companion code on Github.
Categories: Machine Learning, Deep Learning.

Neural Networks and Deep Learning is THE free online book. Period.

Book abstract:

Neural networks are one of the most beautiful programming paradigms ever invented. In the conventional approach to programming, we tell the computer what to do, breaking big problems up into many small, precisely defined tasks that the computer can easily perform. By contrast, in a neural network we don't tell the computer how to solve our problem. Instead, it learns from observational data, figuring out its own solution to the problem at hand.

Automatically learning from data sounds promising. However, until 2006 we didn't know how to train neural networks to surpass more traditional approaches, except for a few specialized problems. What changed in 2006 was the discovery of techniques for learning in so-called deep neural networks. These techniques are now known as deep learning. They've been developed further, and today deep neural networks and deep learning achieve outstanding performance on many important problems in computer vision, speech recognition, and natural language processing. They're being deployed on a large scale by companies such as Google, Microsoft, and Facebook.

The purpose of this book is to help you master the core concepts of neural networks, including modern techniques for deep learning. After working through the book you will have written code that uses neural networks and deep learning to solve complex pattern recognition problems. And you will have a foundation to use neural networks and deep learning to attack problems of your own devising

If books aren’t your thing, don't worry. Jump to Best Deep Learning Courses: Updated for 2019 .

Thanks to Charlie Harrington, Michael Trazzi, Emil Wallner and Sam Lynn-Evans for reviewing this post and suggesting some of the titles.

FloydHub Call for AI writers

Want to write amazing articles like Alessio and play your role in the long road to Artificial General Intelligence? We are looking for passionate writers, to build the world's best blog for practical applications of groundbreaking A.I. techniques. FloydHub has a large reach within the AI community and with your help, we can inspire the next wave of AI. Apply now and join the crew!