Author: Uri Blass
Date: 16:56:13 10/19/02
Go up one level in this thread
On October 19, 2002 at 19:45:39, Will Singleton wrote: >On October 19, 2002 at 19:16:04, Vincent Diepeveen wrote: > >>On October 19, 2002 at 17:59:05, Jesper Antonsson wrote: >> >>I am under the clear belief that Fritz eval is much >>better than that of deep blue. Of course it's not a fair >>compare. Fritz is made in 2002. Deep blue in 1996-1997. >> >>It is comparing an airplane from 1910 with an airplane 2010. >> > >I think you have gone a bit overboard here. First, we have almost zero data >with which to make a decision. Second, I don't see any reason to suspect that >evaluation of computer chess programs has changed in the last 5-6 years. Programmers add more knowledge to their evaluation > The >rules of chess have not changed. So what evidence do you have that the passage >of time would affect one's ability to program an eval? More time help to improve the evaluation. When you have strong opponents you can see more problems and it can help you to improve your evaluation. Deeper blue suffered from lack of strong computer opponents at the time of deep thought-deeper blue. They also had no time to tune their evaluation because the deep blue was completed only in the last minutes. Having the right weights may be more important than having a lot of weights in the evaluation. 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.