Author: jerry young
Date: 12:19:56 03/27/02
Go up one level in this thread
James, i have a clue, but that is all. They are based on statistics, and that can be faulty, as a bad line can often win. I research lines specifically, trying (futilely?) to create unbeatable trees. That is completely different than statistical learning, which is based solely (in my opinion)on program/cpu/time of game, pretty much as Uri suggests.
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.