Author: Matthew Hull
Date: 08:54:16 05/12/05
Go up one level in this thread
On May 12, 2005 at 11:47:54, Steven Edwards wrote: >On May 12, 2005 at 09:17:16, Matthew Hull wrote: >>On May 12, 2005 at 01:57:19, Steven Edwards wrote: > >>>After 101 cycles, a new champion organism was produced that matched nine of the >>>Bloss problems. After 285 cycles a ten matcher was found. And on cycle 411 an >>>organism was found that matched eleven. A twelve of fourteen matcher was >>>produced on cycle 453, and a thirteen match organism appeared on habitat cycle >>>1297. > >>The process sounds alot like neural network training. > >It's simpler in that an organism doesn't have a complex topography as does an >NN. It's more complex it that there are multple organisms in a persistent >breeding pool. How long did it take to complete the 1297 cycles? I suppose the cycle length depends upon the number of problems in the test, too?
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.