How Smart Machines Think

How Smart Machines Think

By Sean Gerrish

Foreword by Kevin Scott

Everything you've always wanted to know about self-driving cars, Netflix recommendations, IBM's Watson, and video game-playing computer programs.





Everything you've always wanted to know about self-driving cars, Netflix recommendations, IBM's Watson, and video game-playing computer programs.

The future is here: Self-driving cars are on the streets, an algorithm gives you movie and TV recommendations, IBM's Watson triumphed on Jeopardy over puny human brains, computer programs can be trained to play Atari games. But how do all these things work? In this book, Sean Gerrish offers an engaging and accessible overview of the breakthroughs in artificial intelligence and machine learning that have made today's machines so smart.

Gerrish outlines some of the key ideas that enable intelligent machines to perceive and interact with the world. He describes the software architecture that allows self-driving cars to stay on the road and to navigate crowded urban environments; the million-dollar Netflix competition for a better recommendation engine (which had an unexpected ending); and how programmers trained computers to perform certain behaviors by offering them treats, as if they were training a dog. He explains how artificial neural networks enable computers to perceive the world—and to play Atari video games better than humans. He explains Watson's famous victory on Jeopardy, and he looks at how computers play games, describing AlphaGo and Deep Blue, which beat reigning world champions at the strategy games of Go and chess. Computers have not yet mastered everything, however; Gerrish outlines the difficulties in creating intelligent agents that can successfully play video games like StarCraft that have evaded solution—at least for now.

Gerrish weaves the stories behind these breakthroughs into the narrative, introducing readers to many of the researchers involved, and keeping technical details to a minimum. Science and technology buffs will find this book an essential guide to a future in which machines can outsmart people.


$17.95 T ISBN: 9780262038409 312 pp. | 6 in x 9 in 62 b&w illus.


$17.95 T ISBN: 9780262537971 312 pp. | 6 in x 9 in 62 b&w illus.


Kevin Scott.


  • Gerrish offers a fresh and contemporary look at AI, machine learning, and deep learning by presenting the topics in light of how the technologies have surfaced in familiar memes like the Jeopardy TV game show, Netflix, video games like StarCraft, board games like Go, chess, Sudoku, and also self-driving cars.

    Inside Big Data

  • An excellent primer for the engineer interested in putting AI in context.

    E&T Magazine

  • How Smart Machines Think by Sean Gerrish. If you want to discuss recent AI achievements with your students, such as how self-driving cars work, how Watson beat two of the best human Jeopardy! players, how NetFlix uses AI to recommend movies to people, and how AlphaGo beat one of the best human Go players, this book is for you.

    Getting Smart


  • How Smart Machines Think is an enjoyable and insightful 'look under the hood' at recent AI developments. Gerrish introduces complex and important concepts in terms that any reader can understand.

    Ray Kurzweil, Author of New York Times bestsellers, How to Create a Mind: The Secret of Human Thought Revealed and The Singularity is Near: When Humans Transcend Biology

  • An excellent layman's introduction to contemporary AI and machine learning. Gerrish clearly explains the key ideas behind the winning entries in various recent high-profile competitions, such as the DARPA Grand Challenge for self-driving cars and the Jeopardy! Challenge for question-answering. In addition, he emphasizes the role of collaborative human effort in building these systems, both in terms of openly publishing basic research, as well as carrying out the relevant engineering. This more nuanced portrait of progress makes claims of AI autonomously taking over the world much less worrisome.

    Kevin Murphy, Senior Staff Research Scientist, Google, and Author of Machine Learning: A Probabilistic Approach

  • If you're curious about what made some of the recent AI successes possible, from winning at Go to self-driving cars, this fascinating book is for you.

    Pedro Domingos, Professor of Computer Science, and Author of The Master Algorithm

    The University of Washington