In this Book

  • How Smart Machines Think
  • Book
  • Sean Gerrish. Foreword by Kevin Scott
  • 2018
  • Published by: The MIT Press
summary

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 thingswork? 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.

Table of Contents

restricted access Download Full Book restricted access Download Full EPUB
  1. Cover
  2. restricted access
    • View HTML View
    • Download PDF Download
  1. Half Title, Title Page, Copyright, Dedication
  2. restricted access
    • Download PDF Download
  1. Contents
  2. pp. vii-viii
  3. restricted access
    • Download PDF Download
  1. Foreword
  2. Kevin Scott
  3. pp. ix-x
  4. restricted access
    • Download PDF Download
  1. Preface
  2. pp. xi-xii
  3. restricted access
    • View HTML View
    • Download PDF Download
  1. Acknowledgments
  2. pp. xiii-xiv
  3. restricted access
    • View HTML View
    • Download PDF Download
  1. 1. The Secret of the Automaton
  2. pp. 1-8
  3. restricted access
    • View HTML View
    • Download PDF Download
  1. 2. Self-Driving Cars and the DARPA Grand Challenge
  2. pp. 9-22
  3. restricted access
    • View HTML View
    • Download PDF Download
  1. 3. Keeping within the Lanes: Perception in Self-Driving Cars
  2. pp. 23-36
  3. restricted access
    • View HTML View
    • Download PDF Download
  1. 4. Yielding at Intersections: The Brain of a Self-Driving Car
  2. pp. 37-56
  3. restricted access
    • View HTML View
    • Download PDF Download
  1. 5. Netflix and the Recommendation–Engine Challenge
  2. pp. 57-72
  3. restricted access
    • View HTML View
    • Download PDF Download
  1. 6. Ensembles of Teams: The Netflix Prize Winners
  2. pp. 73-88
  3. restricted access
    • View HTML View
    • Download PDF Download
  1. 7. Teaching Computers by Giving Them Treats
  2. pp. 89-106
  3. restricted access
    • View HTML View
    • Download PDF Download
  1. 8. How to Beat Atari Games by Using Neural Networks
  2. pp. 107-124
  3. restricted access
    • View HTML View
    • Download PDF Download
  1. 9. Artificial Neural Networks’ View of the World
  2. pp. 125-144
  3. restricted access
    • View HTML View
    • Download PDF Download
  1. 10. Looking Under the Hood of Deep Neural Networks
  2. pp. 145-156
  3. restricted access
    • View HTML View
    • Download PDF Download
  1. 11. Neural Networks that Can Hear, Speak, and Remember
  2. pp. 157-170
  3. restricted access
    • View HTML View
    • Download PDF Download
  1. 12. Understanding Natural Language (and Jeopardy! Questions)
  2. pp. 171-186
  3. restricted access
    • View HTML View
    • Download PDF Download
  1. 13. Mining the Best Jeopardy! Answer
  2. pp. 187-206
  3. restricted access
    • View HTML View
    • Download PDF Download
  1. 14. Brute-Force Search Your Way to a Good Strategy
  2. pp. 207-228
  3. restricted access
    • View HTML View
    • Download PDF Download
  1. 15. Expert-Level Play for the Game of Go
  2. pp. 229-248
  3. restricted access
    • View HTML View
    • Download PDF Download
  1. 16. Real-Time AI and Starcraft
  2. pp. 249-260
  3. restricted access
    • View HTML View
    • Download PDF Download
  1. 17. Five Decades (or More) from Now
  2. pp. 261-268
  3. restricted access
    • View HTML View
    • Download PDF Download
  1. Notes
  2. pp. 269-294
  3. restricted access
    • Download PDF Download
  1. Index
  2. pp. 295-298
  3. restricted access
    • View HTML View
    • Download PDF Download

This website uses cookies to ensure you get the best experience on our website. Without cookies your experience may not be seamless.