Computer Chess Club Archives




Subject: Re: Chess and Neural Networks

Author: KarinsDad

Date: 08:53:31 01/27/99

Go up one level in this thread

On January 27, 1999 at 05:08:59, Frank Schubert wrote:

>Dear computerchess friends and program authors,
>last year the german academy for chess and sciences was founded at Karpov chess
>centre in Baden-Baden (D). As a co-ordinator for the topic 'Chess and Neural
>Networks' I just try to get an overall picture of interesting activities in this
>field. At the moment I only know the program ALEXS by van Tiggelen (NL) and the
>NeuroChess-project of Sebastian Thrun (Uni Pittsburgh). Who can give me more
>informations about chess (programs) and Neural Networks ?
>Additionally it would be nice if we can start a discussion here on CCC about
>possible applications of Neural Networks in chess programs. So does someone of
>the program authors plan to use NN's in his program ? What is your opinion about
>it ?

I considered using it, however, other people's results seemed to indicate that
it was not a promising area of study (at least not yet). I am reminded of the
neural net tank identification system that was 100% in the lab, but could not
identify tanks in the field. The reason, the images used in the lab had a
slightly different background color for friendly tanks and enemy tanks, and so
the neural net focused on the background color of the image and not on
characteristics of the tanks. Without the ability to work on problems of this
nature full time, the desired results would probably not be realized in a
reasonable amount of time.

I think that some elements of what neural nets really do, such as pattern
recognition, can currently be hardcoded into a program much faster. Just my


> What are your experiences in this field and what will be the future trends
>? Any contributions to this subject are welcome.

This page took 0.02 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.