Computer Chess Club Archives




Subject: Re: chess and neural networks

Author: Vincent Diepeveen

Date: 17:50:54 07/02/03

Go up one level in this thread

On July 01, 2003 at 14:21:12, Tom Kerrigan wrote:

>On July 01, 2003 at 13:32:19, Ralph Stoesser wrote:
>>Hello *,
>>Why no top engine uses neural networks for positional evaluation in non-tactical
>>situations? Are there interesting publications about neural networks and chess
>Neural networks are for analyzing things that are
>"fuzzy"--voice/image/handwriting recognition, etc. Chess is a very exacting
>game. (It makes a big difference if your rook is on d1 vs. e1.) I doubt neural
>networks will ever be useful for chess.

Depending upon your own definition of fuzzy logics, chess for sure is a fuzzy
logics game in the wide perspective seen.

I can imagine that if you take computerchess as a serious science that you don't
want to get grouped together in the category of fuzzylogics where a lot of
idiots are around who at most can reinvent a random way to optimize a few
parameters though that can be done faster than with a random search :)

Yet in the true sense of the word, Chess can be very clearly seen as a form of
fuzzy logics. In fact all evaluations do not evaluate something binary, but in a
fuzzy logic way. Some scale of evaluations can get given. So the proof that
chess is a fuzzy logic game is just too simple to be true.

This page took 0.01 seconds to execute

Last modified: Thu, 07 Jul 11 08:48:38 -0700

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