[Top][All Lists]
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
RE: [Bug-gnubg] Two patch sets - one for Joseph Heled
From: |
David Montgomery |
Subject: |
RE: [Bug-gnubg] Two patch sets - one for Joseph Heled |
Date: |
Mon, 11 Nov 2002 11:53:27 -0800 |
> 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
Re: [Bug-gnubg] Two patch sets - one for Joseph Heled, Øystein O Johansen, 2002/11/11