Re: [Bug-gnubg] Pruning nets and SSE

[Joseph Heled]

I can't really remember. It is entirely reasonable to assume that with
the increase in CPU power we can have a better soft spot of prunning
net size and number of positions to prune.

-Joseph

On 17 February 2011 10:50, Philippe Michel <address@hidden> wrote:
> I have tried to use the patch to SSE code that Oystein posted here about one
> year ago to compute the pruning nets' outputs (using the current weights
> file padded with zeroes at the right places).
>
> 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 ?
>
>
> _______________________________________________
> Bug-gnubg mailing list
> address@hidden
> http://lists.gnu.org/mailman/listinfo/bug-gnubg
>