Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: Emulating Human Pattern-Recognition in Chess(temporal intelligence?)

Author: martin fierz

Date: 17:52:13 05/18/02

Go up one level in this thread


On May 18, 2002 at 04:14:31, Otello Gnaramori wrote:

>I recently read about a new approach in AI (from the newsgroup rgcc) named
>"temporal intelligence" (opposed to the classic AI).
>
>If you are interested the link is the following :
>http://home1.gte.net/res02khr/AI/Animal.htm
>
>Here is an excerpt:
>"Animal is a spiking neural network that learns to play chess. It is written in
>C++ for MS Windows® and DirectX®. I have only tested it with Windows 2000, so it
>may not work on other Windows platforms. Animal is not a typical chess program.
>There is no look-ahead tree searching algorithm and no position evaluation
>function. Animal does not generate millions of moves like IBM's Deep Blue
>supercomputer. It learns pretty much the same way a human being does, that is,
>by sensing and interacting with its environment through trial and error."
>
>You can also download the program a try it yourself...but I seriously doubt if
>it will eventually reach a decent level of play :)
>
>w.b.r.
>Otello

the approach with neural nets can be plugged into a standard alpha-beta search,
using the neural net as evaluation function. recently, david fogel and kumar
chellapilla used a genetic algorithm to evolve neural networks to evaluate
checkers positions. they made a bit much hype about it ("learned to play
checkers!" (only learned to evaluate - the search part also belongs to playing
checkers) "defeated a commercial program!" (yeah, one for kids...)), it is a
weak program, mainly because the neural net is very slow in evaluating. but it
plays a much better game than a program which only evaluates material and got
something like a 2000 rating on the MSN zone.
and on the whole, the approach is very interesting, because today's forms of
machine learning used by chess programs are rather poor.

if you want to read on the program:
http://www.natural-selection.com/NSIPublicationsOnline.htm
there is also a book by david fogel, it's a good read, but not very technical -
probably nothing for the average CCC member.

if you want to buy it:
http://www.digenetics.com/index2.html

aloha
  martin



This page took 0 seconds to execute

Last modified: Thu, 15 Apr 21 08:11:13 -0700

Current Computer Chess Club Forums at Talkchess. This site by Sean Mintz.