Author: Harald Faber
Date: 05:41:05 02/12/99
Go up one level in this thread
On February 11, 1999 at 15:41:25, Dann Corbit wrote: >Andreas Schwartmann asked an interesting question in r.g.c.c.: >"I wonder if anyone can enlighten me on how to use various test suites, like >LCT, LCT II and Covax. There are ceratin formulas on how to calculate the >playing strength according to these test suites, right?" > >Now, ignoring the fact that they are full of bugs and the measures are probably >bogus, how *does* one arrive at an ELO from a test suite evaluation? > >What is the actual mathematical basis for the calculations? Probably none. At least in BS there were formulas changed (!) after the results have come so that the formula gives a rating the authors SUPPOSE to be in the right order! Pesonally I have my own testsuite with positional stress but I wouldn't dare making a ranking or ELO-formula or calculation out of it. Ideal would be to have 3 kinds if testsets from which you can count all results together and SUPPOSE which program is best (but never try to make a formula out of it): 1) middlegame with positional important decisions: blockade or not, e5 or f5 in the Sicilian etc., best with advice by a GM with given reasons and no tactical whole in it 2) tactics with only 1 (!) PROVEN correct solution 3) endgames asking for endgame knowledge At the moment we have even not just one of them. (I also have to adjust my testsuite, there are some positions NO computer will ever SOLVE [if this is the right word]) It is certainly a lot of work, divided into 3 groups of chess interested people it should be possible to realize such a project within 3 months but I fear there won't be enough volunteers.
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.