Blondie24: Playing at the Edge of AI

ISBN-13: 9781558607835 / Angielski / Miękka / 2001 / 406 str.

David B. Fogel

Opis

Blondie24 tells the story of a computer that taught itself to play checkers far better than its creators ever could by using a program that emulated the basic principles of Darwinian evolution--random variation and natural selection-- to discover on its own how to excel at the game. Unlike Deep Blue, the celebrated chess machine that beat Garry Kasparov, the former world champion chess player, this evolutionary program didn't have access to strategies employed by human grand masters, or to databases of moves for the endgame moves, or to other human expertise about the game of chekers. With only the most rudimentary information programmed into its "brain," Blondie24 (the program's Internet username) created its own means of evaluating the complex, changing patterns of pieces that make up a checkers game by evolving artificial neural networks---mathematical models that loosely describe how a brain works. It's fitting that Blondie24 should appear in 2001, the year when we remember Arthur C. Clarke's prediction that one day we would succeed in creating a thinking machine. In this compelling narrative, David Fogel, author and co-creator of Blondie24, describes in convincing detail how evolutionary computation may help to bring us closer to Clarke's vision of HAL. Along the way, he gives readers an inside look into the fascinating history of AI and poses provocative questions about its future.

• Brings one of the most exciting areas of AI research to life by following the story of Blondie24's development in the lab through her evolution into an expert-rated checkers player, based on her impressive success in Internet competition.
• Explains the foundations of evolutionary computation, simply and clearly.
• Presents complex material in an engaging style for readers with no background in computer science or artificial intelligence.
• Examines foundational issues surrounding the creation of a thinking machine.
• Debates whether the famous Turing Test really tests for intelligence.
• Challenges deeply entrenched myths about the successes and implication of some well-known AI experiments.
• Shows Blondie's moves with checkerboard diagrams that readers can easily follow.

Recenzje

"Meet Blondie. She's a 24-year old graduate student in mathematics at the University of California at San Diego. She skis and surfs, and is an ace at math. But her real claim to fame is her amazing ability to play checkers. She's really good--not good enough to defeat a grand master, but she did earn a spot in the top 500 of an international checkers tournament. Considering that she taught herself how to play without reading books, taking classes, or getting tips from experienced players--that's impressive. And considering that Blondie is only a computer program, and the rest of her persona is just a product my imagination, you might say that's really impressive!" --from the Introduction

Spis treści

Part 1 - Setting the Stage Chapter 1 - Intelligent Machines: Imitating Life Chapter 2 - Deep Blue: A Triumph of AI? Chapter 3 - Building An Artificial Brain Chapter 4 - Evolutionary Computation: Putting Nature to Work Chapter 5 - Blue Hawaii: Natural Selection Chapter 6 - Checkers Chapter 7 - Chinook: The Man-machine Checkers Champion Chapter 8 - Samuel's Learning Machine Chapter 9 - The Samuel-Newell ChallengePart 2 - The Making of Blondie Chapter 10 - Evolving in the Checkers Environment Chapter 11 - In The Zone Chapter 12 - A Repeat Performance Chapter 13 - A New Dimension Chapter 14 - Letting the Genie Out of the Bottle Chapter 15 - Blondie24 Epilogue: The Future of Artificial Intelligence Appendix: Your Honor, I Object! Notes Index About the Author

O autorze

David B. Fogel is the CEO of Natural Selection, Inc., a company which addresses complex, real-world problems in the areas of industry, medicine, and defense by applying the techniques of evolutionary computation, neural networks, fuzzy systems, knowledge-based systems, and stochastic processes, among other technologies. Dr. Fogel was the founding president of the Evolutionary Programming Society and was elected a Fellow of the IEEE in 1999. He is the founding editor-in-chief of the IEEE Transactions on Evolutionary Computation and serves on the editorial boards of several journals including BioSystems, Fuzzy Sets and Systems, and Journal of Scheduling.