[Top][All Lists]
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
RE: [Bug-gnubg] Some idle musings re. ratings
From: |
David Montgomery |
Subject: |
RE: [Bug-gnubg] Some idle musings re. ratings |
Date: |
Thu, 11 Sep 2003 11:22:52 -0700 |
Kees wrote:
> I understand the noise is injected in the outputs of the NN. I always
> have had the feeling that it would be a better model of human error to
> inject the noise into the WEIGHTS of the NN. Now that I think about it I
> think this might also introduce clumping effects, like when the position
> moves into a region whose processing has been damaged a lot by the
> partial lobotomy.
>
> I guess I could just externally disturb the weights file to create a
> number of braindamaged bots and experiment with those. Any pointers to
> where I can find the file format for the wieghts files? Or is this a
> stupid idea anyways?
I think this is an interesting idea.
Here's a third, which might be easier to implement: apply the noise
directly to the inputs.
David
- [Bug-gnubg] Some idle musings re. ratings, Jim Segrave, 2003/09/10
- Re: [Bug-gnubg] Some idle musings re. ratings, Joern Thyssen, 2003/09/11
- Re: [Bug-gnubg] Some idle musings re. ratings, kvandoel, 2003/09/11
- RE: [Bug-gnubg] Some idle musings re. ratings,
David Montgomery <=
- Re: [Bug-gnubg] Some idle musings re. ratings, Jim Segrave, 2003/09/11
- Re: [Bug-gnubg] Some idle musings re. ratings, Joseph Heled, 2003/09/11
- Re: [Bug-gnubg] Some idle musings re. ratings, kvandoel, 2003/09/11
- Re: [Bug-gnubg] Some idle musings re. ratings, kvandoel, 2003/09/11
- Re: [Bug-gnubg] Some idle musings re. ratings, Joern Thyssen, 2003/09/12
- Re: [Bug-gnubg] Some idle musings re. ratings, kvandoel, 2003/09/12
- Re: [Bug-gnubg] Some idle musings re. ratings, Nardy Pillads, 2003/09/15