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

[frank-steinmann@xxxxxxxxxxx (Frank Steinmann)]

> It sounds like your modification of the backprop algorithm might be the
> culprit. I don't completely understand what you mean by taking the
> average error of similar nodes, but if you're doing something like
> averaging the error of your network at each of the four corners, that's
> going to mess stuff up. 

Yes, that's what I did.

> One alternative way to take advantage of board symmetries might be to
> use each board position to generate four training cases per board
> position (one for each board rotation). This doesn't use the inherent
> structure of the network per se, but it should help the network learn
> more rapidly from fewer board positions. 

I generate eight training cases per board (using rotations and reflexions).

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