Re: [computer-go] taking advantage of board symmetries inneuralnetworks

[frank-steinmann@xxxxxxxxxxx (Frank Steinmann)]

> Another idea is to symmetrize the training data by presenting each
> pattern under all reflections and rotations.  This might lead to a better
> evaluation function eventually, but primarily it slows down learning
> quite a bit.  We didn't look into it very much, but our hypothesis was
> that the symmetric data makes it much harder for the hidden units to
> break symmetry, something which they have to do in the learning process.

That is what I'm giving a trial right now.

> Overall we felt that dealing with reflections/rotations was not worth
> the effort, at least not at the level we were at.  (Disclaimer: all this
> was 10 years ago!)  We ended up using color reversal (negation, designed
> into the net) because it was easy to do, translation invariance because
> it helped *a lot*, and reflection/rotation (only on evaluation, not when
> learning) when we had enough cycles to spare (i.e., rarely :-).

Well, I've got color reversal for free, but translation invariance, what
does this mean on a go board?

To use reflection/rotation on evaluation seems to be a good idea.

Frank

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