Author: ShaktiFire
Date: 18:19:09 07/15/00
Go up one level in this thread
On July 15, 2000 at 19:41:19, Dann Corbit wrote: >On July 15, 2000 at 19:35:34, ShaktiFire wrote: > >>On July 15, 2000 at 18:32:52, Mogens Larsen wrote: >> >>>On July 15, 2000 at 18:22:59, Ralf Elvsén wrote: >>> >>>>These are pretty harsh words, especially since I think Uri has a point. >>>>Even if it is not correct I wouldn't call it "nonsense" or "truth distortion". >>>>These judgements should be saved for more clear cases, and there has >>>>certainly been some on this board in the past... >>> >>>No, he doesn't have a point, since you can't determine GM strength by gathering >>>the results of several programs, reach GM strength within the bounds of >>>uncertainty and then conclude that one of the programs are GM strength. Because >>>you already know that none of programs alone are of GM strength with certainty >>>due to a large ELO uncertainty, otherwise it wouldn't be necessary to add them >>>together. So nonsense is the appropriate word, even though truth distortion was >>>unnecessary harsh. >>> >>>Best wishes... >>>Mogens >> >>Can we not make a category. Say, "commercial programs running on 500 Mhz or >>higher", take performance data, for that class, and then do statisical analyses >>that allow to make statements about that class. > >We can do anything we like, but what are we trying to model? > >With a large pool of data outliers are certain. > >Imagine a single trial by each program/machine combination. How much >information do the GM's have to pick the program/machines apart? The answer >(since there is only one game) is zero. > >Now, imagine a single machine and a single program that plays a million games >against a huge pool of GM's. Will they discover more flaws in the machine's >approach in this experiment or the one you designed? > >What will your conclusions be, mathematically? I think it would take a >supercomputer to model just how to interpret the data! That is a very good point you are trying to make. Given a single GM against a single program and machine, in the early sequence, the machine might do well, but in the 100 game sequence, the GM would learn the machine nuances and eventually dominate the machine, (assuming the machine isn't learning the nuances of the GM). So how can we say the combined program=machine combo is playing GM level, if it can not learn nuances of the GM. In a way, in order to call a program GM level it needs to adapt to an opponents style or learn about that style else it would do quite poorly in a many game matchup.
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.