|
From: | Philippe Michel |
Subject: | [Bug-gnubg] Pruning nets and SSE |
Date: | Wed, 16 Feb 2011 22:50:21 +0100 (CET) |
User-agent: | Alpine 2.00 (BSF 1167 2008-08-23) |
It works and is a little faster than the current way, so I suppose it could be used as is. The cost for non-SSE processors looks very small and they could always use the current nets.
But then the obvious question is : how about using properly trained nets with 8 and 12 (or 16) hidden nodes ? Could it make a difference in overall playing strength ? Could it allow faster evaluations thanks to more aggressive pruning ?
Do you (especially Joseph) have insights about this ? Were other parameters tried than 5 and 10 hidden nodes / 10 moves selected ? How did they do ?
[Prev in Thread] | Current Thread | [Next in Thread] |