By David B. Fogel

Blondie24 tells the tale of a working laptop or computer that taught itself to play checkers much better than its creators ever might by utilizing a software that emulated the fundamental ideas of Darwinian evolution--random version and ordinary selection-- to find by itself find out how to excel on the online game. in contrast to Deep Blue, the prestigious chess computing device that beat Garry Kasparov, the previous international champion chess participant, this evolutionary software did not have entry to thoughts hired by means of human grand masters, or to databases of strikes for the endgame strikes, or to different human services concerning the online game of chekers. With simply the main rudimentary info programmed into its "brain," Blondie24 (the program's net username) created its personal technique of comparing the advanced, altering styles of items that make up a checkers online game via evolving man made neural networks---mathematical versions that loosely describe how a mind works.It's becoming that Blondie24 should still seem in 2001, the 12 months after we take into account Arthur C. Clarke's prediction that sooner or later we'd achieve making a considering computer. during this compelling narrative, David Fogel, writer and co-creator of Blondie24, describes in convincing element how evolutionary computation will help to carry us toward Clarke's imaginative and prescient of HAL. alongside the way in which, he provides readers an inside of look at the attention-grabbing historical past of AI and poses provocative questions on its destiny. * Brings some of the most interesting parts of AI learn to lifestyles through following the tale of Blondie24's improvement within the lab via her evolution into an expert-rated checkers participant, in accordance with her remarkable good fortune in web competition.* Explains the rules of evolutionary computation, easily and clearly.* provides advanced fabric in an attractive type for readers with out history in laptop technology or synthetic intelligence.* Examines foundational concerns surrounding the construction of a considering machine.* Debates even if the recognized Turing try particularly assessments for intelligence.* demanding situations deeply entrenched myths concerning the successes and implication of a few recognized AI experiments * exhibits Blondie's strikes with checkerboard diagrams that readers can simply persist with.

Show description

Read or Download Blondie24: Playing at the Edge of AI PDF

Similar intelligence & semantics books

An Introduction to Computational Learning Theory

Emphasizing problems with computational potency, Michael Kearns and Umesh Vazirani introduce a few principal subject matters in computational studying thought for researchers and scholars in man made intelligence, neural networks, theoretical computing device technology, and statistics. Computational studying idea is a brand new and quickly increasing zone of study that examines formal types of induction with the ambitions of gaining knowledge of the typical tools underlying effective studying algorithms and settling on the computational impediments to studying.

Minimum Error Entropy Classification

This booklet explains the minimal errors entropy (MEE) notion utilized to info type machines. Theoretical effects at the internal workings of the MEE idea, in its software to fixing various type difficulties, are awarded within the wider realm of threat functionals. Researchers and practitioners additionally locate within the booklet a close presentation of useful facts classifiers utilizing MEE.

Artificial Intelligence for Humans, Volume 1: Fundamental Algorithms

An exceptional development calls for a robust origin. This publication teaches uncomplicated synthetic Intelligence algorithms comparable to dimensionality, distance metrics, clustering, errors calculation, hill mountain climbing, Nelder Mead, and linear regression. those aren't simply foundational algorithms for the remainder of the sequence, yet are very precious of their personal correct.

Advances in Personalized Web-Based Education

This booklet goals to supply very important information regarding adaptivity in computer-based and/or web-based academic structures. so one can make the coed modeling method transparent, a literature evaluation touching on scholar modeling innovations and techniques in past times decade is gifted in a unique bankruptcy.

Additional resources for Blondie24: Playing at the Edge of AI

Sample text

Chessboards in the same amount of time and therefore had an advantage over older, slower hardware. 11 Using faster hardware to process more boards in the same amount of time meant that chess programs could look farther ahead and anticipate a greater possible range of moves and countermoves. Fogel,Blondie24 8/28/01 9:32 AM Page 27 direct route to making better chess machines came from optimizing their hardware rather than their software. Deep Blue, the epitome of this optimization, emerged from the battle of two competing teams of computer experts at Carnegie Mellon University.

This top-down approach of searching for repeated patterns o¤ers a superior prospect for identifying causative factors. The pattern repeated in all natural learning systems is an evolutionary process of adaptation by variation and selection. Evolution, then, provides a simple yet complete prescription for programming a learning machine, a computer that can adapt its behavior to meet goals in a range of environments and to generate solutions to problems that we don’t yet know how to solve. HAL isn’t a mere collection of facts, but rather a learning machine.

7 to beat Machack more than 99 percent of the time. Yet, as we’ll discuss shortly, in a hypothetical game between Deep Blue and Belle, the odds against Belle would be almost eight to one. Just how did Deep Blue get to be so good? Hardware Makes It Happen The 1980s saw a rise in e¤orts to make application-specific hardware that could evaluate large numbers of possible chessboards very quickly. Every new generation of computer hardware could process more deep blue: a triumph for ai? You’d gain sixteen points if you defeated another player rated 1,500, but fewer than five points for defeating someone rated 1,100.

Download PDF sample

Download Blondie24: Playing at the Edge of AI by David B. Fogel PDF
Rated 4.98 of 5 – based on 8 votes