RE: [Bug-gnubg] Some idle musings re. ratings

[David Montgomery]

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