|
From: | Joseph Heled |
Subject: | Re: [Bug-gnubg] Two patch sets - one for Joseph Heled |
Date: | Tue, 12 Nov 2002 09:50:39 +1300 |
User-agent: | Mozilla/5.0 (X11; U; SunOS sun4u; en-US; rv:1.1) Gecko/20020829 |
Implemented. See EvaluateFromBase in lib/neuralnet.c -Joseph David Montgomery wrote:
I think there's a lot more performance to be gained, but it may be harder work - the biggest time consumers are the setting up of the neural net inputs and the evaluation of the net itself, neither of which are trivial to change.Here's one idea for speeding up network propagation. Since most evaluations are of a position very similar to the previous evaluation (e.g., for checker plays), the inputs are mostly similar as well. So it may be faster to just update the net with the *differences* in the inputs, rather than starting fresh each time. One could do this either by looking at the diffs between this position and the last evaluated, or the do all checker plays by looking at the diff from the starting position.If anyone wants to look into using this idea, let me know and I'll send you code that implements it for the raw board encoding.David _______________________________________________ Bug-gnubg mailing list address@hidden http://mail.gnu.org/mailman/listinfo/bug-gnubg
[Prev in Thread] | Current Thread | [Next in Thread] |