Author: Dann Corbit
Date: 13:41:45 01/11/01
Go up one level in this thread
On January 11, 2001 at 16:28:04, Dann Corbit wrote: >On January 11, 2001 at 16:06:10, James T. Walker wrote: > >>On January 11, 2001 at 16:01:16, Dann Corbit wrote: >> >>>On January 11, 2001 at 15:58:55, James T. Walker wrote: >>> >>>>On January 11, 2001 at 14:59:06, Dann Corbit wrote: >>>> >>>>>On January 11, 2001 at 14:46:01, Garry Evans wrote: >>>>> >>>>>>On January 11, 2001 at 13:39:03, Dann Corbit wrote: >>>>>> >>>>>>>On January 11, 2001 at 11:43:10, Drazen Marovic wrote: >>>>>>> >>>>>>>> The sad thing is, if rebel had lost by a measly half point countless here >>>>>>>>would still try to deny comps gm strength. >>>>>>> >>>>>>>There is not enough evidence to confirm or deny the assertion either way. >>>>>>> >>>>>>>The 1/2 point swing in the other direction (for the comp) is no different. But >>>>>>>in any case, there are certainly not enough games to make a logical statement. >>>>>>>Only an emotional one. >>>>>> >>>>>>Baloney! We have more than enough games, simply visit Chris Carson's chess page. >>>>> >>>>>Been there, done that. >>>>>Take the individual combinations of machine and program, and calculate the error >>>>>bars for ELO. They are close to infinity. >>>> >>>> >>>>Why do that? Why not assume that all computers are essentially equal and go >>>>from there? If only one is of GM strength then using all of them could only >>>>decrease the argument for GM strength. >>> >>>We can do anything we like and make any sort of assumptions that we choose. >>>Fortunately, we have mathematics to test our models afterwards. Without using >>>this tool, we are making emotional choices rather than logical ones. There is >>>nothing wrong with that, but (personally) I prefer a rational approach. >> >>Please explain, mathmatically if you like, what is wrong with my proposal. What >>part is irrational/emotional? > >Assume that all computers are essentially equal? >;-) > >OK. You get a Commodore 64 and I get the latest Cray. Ready for a game of >chess? I'm not altogether clear here, let me add to my remark. If we start by assuming something we know is not true (e.g. all computers are equal in ability) then we have added a false axiom to our system. The inclusion of a single false axiom means that every false statement can be proven to be true. Therefore, such a step is inadmissable. However, we can start with a similar statement: A program will not vary in strength by changing machines by more than 100 ELO. Now *this* hypothesis, on the other hand, is verifiable and testable. If this is demonstrated to be correct, we can use it as an assumption for all the systems on which we have demonstrated it. (BTW, I think it is probably false). Consider also: A computer program will have bugs. All of them do. Given enough games, GM's will find a blind side and exploit it (if they have the interest to do it). Even computers can do this. In fact, that is why (in my opinion) the strongest programs are _not_ at the top of the SSDF list. The programs which make the best chess decisions [Rebel, Chess Tiger -- and this is pure conjecture on my part I will admit] do not learn very well. Hence, learners will eventually start to thump them. But if we erase the learning files and start over, I think the tables would turn. Now, this *is* a defect in the programs that do not learn well. But as a measure of a programs ability to analyze a position, I think the result could be a faulty conclusion.
This page took 0.01 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.