Cover image for Blondie24 : playing at the edge of AI
Blondie24 : playing at the edge of AI
Fogel, David B.
Personal Author:
Publication Information:
San Francisco : Morgan Kaufmann Publishers, [2002]

Physical Description:
xvi, 404 pages : illustrations ; 18 cm
Format :


Call Number
Material Type
Home Location
Item Holds
Q335 .F595 2002 Adult Non-Fiction Central Closed Stacks

On Order



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.

Author Notes

David B. Fogel is the CEO of Natural Selection, Inc.

Reviews 1

Choice Review

This book reads like an exciting novel. If one is a fan of artificial intelligence (AI) or even just wants to take a good trip through the mind of a brilliant engineering progression of thought, this book will provide hours of entertainment. Blondie24 tells about the development of a computer program that taught itself to play checkers. Unlike most other AI attempts at playing checkers or chess, this try has at its foundation not a program that was designed to apply the best practices of the game, but one that could learn, through its mistakes and failures, how to apply a successful strategy. The evolutionary computational strategy illustrated here is truly remarkable and may very well pave the path to doing much more with artificial intelligence than could be possible using other more traditional brute force approaches, such as those applied in the Big Blue project. The book contains helpful illustrations and is very easy to read. Recommended reading to inspire the imaginations of computer science students and practitioners at all levels. General readers; lower-division undergraduates through professionals. F. H. Wild III University of Rhode Island

Table of Contents

Acknowledgmentsp. xi
Introductionp. xiii
1 Setting the Stage
1 Intelligent Machines: Imitating Lifep. 3
2 Deep Blue: A Triumph for AI?p. 19
3 Building an Artificial Brainp. 37
4 Evolutionary Computation: Putting Nature to Workp. 69
5 Blue Hawall: a Natural Selectionp. 85
6 Checkersp. 97
7 Chinook: the Man-Machine Checkers Championp. 113
8 Samuel's Learning Machinep. 129
9 The Samuel-Newell Challengep. 151
2 The Making of Blondie
10 Evolving in the Checkers Environmentp. 163
11 In the Zonep. 187
12 A Repeat Performancep. 213
13 A New Dimensionp. 233
14 Letting the Genie Out of the Bottlep. 257
15 Blondie24p. 273
Epilogue: the Future of Artificial Intelligencep. 299
Appendix Your Honor, I Object!p. 305
Notesp. 321
Indexp. 393
About the Authorp. 405