Author: Enrique Irazoqui
Date: 09:51:10 10/12/98
Go up one level in this thread
On October 12, 1998 at 06:03:29, Moritz Berger wrote: >"Does not achieve this goal" is again somewhat uncompromising, given the purely >experimental nature of your falsification. Falsification? I posted results anyone can verify. Nothing "false" about them. >I am sorry if I sounded too harsh to you; but don't forget who is going to quote >you as "now also Enrique Irazoqui agrees that SSDF rating of Fritz 5 is >distorted" ... AND SO WHAT??? Moritz: I am simply trying to look at things without considering that by doing this I can give weapons to the enemy. I see no war around and I have no enemy. >I think that your observations are interesting enough to do a follow up on your >research; I started with having a match between Crafty 15.19 engine with >PowerBook (clean, learning enabled) on PII-400 vs. Hiarcs 6 on P233MMX at 60/5 >time controls: > >Overall score Crafty from 32 games +8 =15 -9 = 48% >games 1-10: 55% >games 11-20: 35% >games 21-30: 50% >[[games 31-32: 75%]] > >(to be continued, using exactly the same learning algorithm as Fritz 5 on the >very same PowerBook). > >At least in 30 Blitz games, so far the 1st 10 games were clearly the best ... > >Do you agree on this testing method? Will you accept my result after a few >hundred Blitz games? Maybe you want to join my experiment and play similar >matches on your machines? I wonder if it's worth it. Yesterday I would have been more receptive than now, after finding out about Shredder 2. I posted before the results of 22 matches played by Fritz 5. The pattern was clear: in the second half of these matches Fritz scored quite a bit better than in the first half. 22 matches are enough to discard random results, or are they not? To make sure, I looked in the same way at the SSDF matches played by Shredder 2. Since Shredder has no learner it shouldn't show this pattern. Result in 9 matches: Shredder 2 scored 66% in the first half and 71% in the second. Similar to Fritz 5. Meaning: so much for looking for patterns in this way. They don't seem to show anything worth mentioning. My mistake for rushing to conclusions... ((( Nothing special in Fritz matches aside from the fact that it did very well... Enrique >Moritz
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.