Author: Dann Corbit
Date: 16:26:23 11/23/05
Go up one level in this thread
On November 23, 2005 at 19:24:42, Horst Biewald wrote: >Good day Gentleman, just a quick question concerning the learning capabilities >of these computers today (junior, fritz, shredder,maybe a few more) does >every game it plays does it learn where if any, mistakes are made? If that's the >case then theoretically it should get stronger each game. Am i looking at this >learning capability the wrong way? Maybe a little brief explanation would be >greatly appreciated. Thank You! Horst There are many kinds of learning. The most prominent are book learning and position learning. After the engine gets a surprise (either in an opening book position or in a game play position) it makes a note of it. There is some fancy math that goes along with it, but that's the general idea.
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.