Re: [computer-go] taking advantage of board symmetriesinneuralnetworks

[frank-steinmann@xxxxxxxxxxx (Frank Steinmann)]

> > Well, I've got color reversal for free, but translation invariance, what
> > does this mean on a go board?
>
> Well, go would be translation invariant if it weren't for the board edges,
> so as long as you encode "off the board" as distinct from black, white, or
> empty intersections, you can use a translation-invariant pattern matcher.
> For a neural net, use something like
>
> black = (+1,0), white = (-1,0), empty = (0,+1), off the board = (0,-1)
>
> as input, and convolutions with weight kernels as your basic operation.
> Each hidden unit now turns into a layer of 9x9 (or 19x19) units, but
> they all share the same weights.  You end up with a translation-invariant
> network with many connections but (comparatively) few weight parameters.

I have now implemented my NN in the way I understood your explanations and
it works really good. It learns the evaluation function (which I described
earlier) easily with an average error < 4%.
Thanks! :-D
Now I'm going to use it for some TD-Learning...

Frank

_______________________________________________
computer-go mailing list
computer-go@xxxxxxxxxxxxxxxxx
http://computer-go.org/mailman/listinfo/computer-go