Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: Research idea? re: weight optimization

Author: James T. Walker

Date: 07:50:52 12/29/01

Go up one level in this thread


Back when Deep Blue was Deep Thought I think I read somewhere that it's eval was
automatically tuned by an algorythm that took 1000 GM games and adjusted the
eval to most closely play the GM moves.  Maybe I'm wrong and somebody (BOB) can
confirm/deny this.  By the way I never thought this was a good idea when I read
it.
Jim



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.