No, we effectively ignored the symmetries, taking no advantage of them. On Wednesday, October 29, 2003, at 06:40 PM, Weimin Xiao wrote:
Thanks, Peter.
For the second question, I mean when your system is learning, do you also
learn other symmetrical positions, or remove symmetrical positions to reduce
the size of the generalized neural network?
Weimin
----- Original Message -----
From: "Peter Drake" <drake@xxxxxxxxxxxxxxxxx>
To: "computer-go" <computer-go@xxxxxxxxxxxxxxxxx>
Sent: Wednesday, October 29, 2003 6:11 PM
Subject: Re: [computer-go] Poster available
On Wednesday, October 29, 2003, at 03:55 PM, Weimin Xiao wrote:
Peter, Would you like to talk a little bit more on, 1. How do you set input parameters to your generalized neural network? E.g., is one parameter for one position such as Black = 1, Empty = 0, and White = -1; or two parameters for one position as Black = {0, 1}, Empty = {0, 0}, and White = {0, 1}.The latter.2. How do you deal with symmetric as a GO board always has 8 symmetrical configuration?We always inverted the board so that it was white's turn to move. I had some code for rotation and reflection, but it was causing trouble so I commented it out. I think Jim Levenick had a little more luck with this. Peter Drake Assistant Professor of Computer Science Lewis & Clark College http://www.lclark.edu/~drake/ _______________________________________________ computer-go mailing list computer-go@xxxxxxxxxxxxxxxxx http://computer-go.org/mailman/listinfo/computer-go
Peter Drake Assistant Professor of Computer Science Lewis & Clark College http://www.lclark.edu/~drake/ _______________________________________________ computer-go mailing list computer-go@xxxxxxxxxxxxxxxxx http://computer-go.org/mailman/listinfo/computer-go