Author: blass uri
Date: 05:33:27 11/20/99
Go up one level in this thread
On November 20, 1999 at 03:30:53, Dann Corbit wrote: <snipped> >From what we have seen so far, all programs in the top 8 or so are peers in >ability. In other words, within one single standard deviation of uncertainty >there is nothing to tell which is the stronger. The mean value may be slightly >higher for some programs, but unless you play a bazillion games, there really is >not enough to separate them with mathematical certainty. I believe that the standard deviation is based on wrong assumptions and the rating of chess programs and humans is also based on wrong assumption. I believe based on the result that tiger is clearly better than other programs but I have no mathematical way to prove it because I have not a good model of the chances to win in a chess game between computers. The fact that part of the players do not have a learning function,part of the players have a not aggresive learning function and part of the player have an aggresive learning function makes the rating dependent on the opponents of every program and on the number of games. Uri
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.