10 Insightful AI Books To Read in 2021
Want to improve your understanding and skills in the AI/ML domain this year? Check out these 10 best books published over the past two years that offer deep insights into the fundamentals and applications of AI.
Over the past two years, we've seen the release of many books that provide deep insights about the fundamental concepts, technical process, and applications of artificial intelligence. This list highlights books authored by renowned computer scientists and practitioners who are entrenched in the AI industry. No matter you are a researcher, an engineer, or a business professional in the AI/ML domain, your are bound to find a few interesting books to add to your reading list this year!
Rebooting AI (2019)
Author: Gary Marcus and Ernest Davis
In this book, professors at New York University Gary Marcus and Ernest Davis explain the technological and theoretical gap between creating successful AI which is constrained to a fixed set of rules (or a fixed environment), and creating successful AI which can effectively interact with the complexities and intricacies of an open world. This book is for researchers and entrepreneurs who want to make practical predictions on the immediate future of AI. Gary Marcus is a Professor of Psychology and Neural Science and CEO of Robust.AI, and Ernest Davis is a Professor of Computer Science. Noam Chomsky reviewed this book, saying it is “lucid and deeply informed, from a critical but sympathetic perspective”.
Artificial Intelligence: A Guide for Thinking Humans (2020)
Author: Melanie Mitchell
Much like the previous book, Professor of Computer Science at Portland State University, Melanie Mitchell, provides insights into where the AI industry is heading, however she goes into explicit detail about what AI is, what it is not, and the technology’s history. Michael S. Gazzaniga, Director of the SAGE Center for the Study of Mind commented on this book saying “if you think you understand AI and all of the related issues, you don't. By the time you finish this exceptionally lucid and riveting book you will breathe more easily and wisely”. This book is designed for engineers and researchers.
You Look Like a Thing and I Love You: How Artificial Intelligence Works and Why It's Making the World a Weirder Place (2019)
Author: Janelle Shane
Research Scientist at Boulder Nonlinear Systems, Janelle Shane, explores the way that AI typically relates to the world, and how that contrasts with how we relate to the world. This book is also a celebration of those differences, taking a stark look at the sheer weirdness of AI; aimed at people who are fascinated in AI on a conceptual level, rather than theoretical. Ryan North, author of How to Invent Everything called this book “an incredibly accessible, informative, and hilarious look at how the AIs deciding things around us operate”.
Human Compatible: Artificial Intelligence and the Problem of Control (2019)
Author: Stuart Russel
Stuart Russel, Professor of Computer Science at UC Berkeley, discusses AI’s biggest “what if”: what if we finally create entities that are far more intelligent than us? However, unlike others, Russel provides a practical and fascinating solution, arguing that if AI’s are deprived of being certain about human preferences, then they will act with humility and altruism, rather than seek their own objectives. This is a must-read for AI researchers interested in applying moral philosophy to their work.
The Hundred-Page Machine Learning Book (2019)
Author: Andriy Burkov
Moving away from the more conceptual books listed, The Hundred-Page Machine Learning Book provides a concise and practical look at the most fundamental questions in ML. It covers topics such as neural networks, supervised and unsupervised learning, feature engineering, and many more; it does this through clear explanations along with equations and illustrations. This book is aimed at ML engineers, data scientists, and entrepreneurs who want to feel confident when discussing AI. Andriy Burkov is a Director of Data Science and ML Team Leader at Gartner.
Interpretable Machine Learning: A Guide for Making Black Box Models Explainable (2019)
Author: Christoph Molnar
In this book, Interpretable Machine Learning Researcher and Ph.D, Christoph Molnar focuses on ML’s biggest issue with adoption: that these systems seldom explain their inner-workings meaning a great deal of a machine’s processes are hidden within a black box. Christoph Molnar explains the most significant methods of peeking into these black boxes, and weighs their strengths and weaknesses.
Machine Learning Yearning (Dec 2018)
Author: Andrew Ng
Rather than being focused on teaching ML algorithms, Andrew Ng focuses this book on how to create algorithms, and how to best structure them in real-world deployments. This is a deeply practical book, aimed at helping engineers build efficient and useful algorithms. This is for people who already have the relevant programming knowledge, and are looking to best apply that.
Machine Learning Engineering (2020)
Author: Andriy Burkov
Returning to Andriy Burkov, this book is designed to be the most comprehensive applied AI book on the market, covering best practices, design patterns, and significant solutions to machine learning problems. Like his previous book “The Hundred-Page Machine Learning Book”, this is meant to be an overview of the industry, however, at 310 pages, it goes much further in-depth. This book is for ML engineers. Cassie Kozyrkov, Chief Decision Scientist at Google reviewed it, saying that “if you intend to use machine learning to solve business problems at scale, I'm delighted you got your hands on this book”.
Hands-on Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems (2nd Edition, 2019)
Author: Aurélien Géron
Like Machine Learning Engineering, Aurélien Géron’s book is a practical guide aimed at giving programmers the necessary ML insights and information. Specifically, this book is for beginners in the industry. It starts with an overview of what ML is, and then dives into more specific topics such as decisions trees, neural networks, custom models, and preprocessing data. It also focuses on two frameworks: Python’s Scikit-Learn and TensorFlow. This 2nd edition has 250 more pages than the first edition; it now covers unsupervised learning techniques, and expands further on neural networks, including deep computer vision using convolution neural networks. Aurélien Géron was a Founder and Senior Artificial Intelligence Engineer at Kiwisoft, and before that YouTube Product Manager.
Approaching (Almost) Any Machine Learning Problem (2020)
Author: Abhishek Thakur
This book provides practical solutions to theoretical problems in machine learning, aimed at individuals who have a strong theoretical grasp of Machine Learning, but who do not yet have the technical skills to put their knowledge to use. It is filled with programming examples that are designed to be followed along by the reader. Abhishek Thakur, Open Source Researcher at NLP software company Hugging Face, and world’s first Quadruple Kaggle Grandmaster, focuses on topics including evaluation metrics, cross validation, categorical data handling, hyperparameter tuning, and other pressing topics in ML.
Anybody who has built their career around AI and ML will find these books useful for progressing through the field, and grasping some of the most complex, practical, and pressing issues that the field faces. These books are helpful companions for anybody who wishes to enrich their technical skills, productivity, and understanding of the area.