I notice in gnubg and other neural networks the probability of gammon gets its 
own output node, alongside the probability of (any kind of) win.

Doesn't this sometimes mean that the estimated probability of gammon could be 
larger than the probability of win, since both sigmoid outputs run from 0 to 1?

I'm playing around with making the gammon node represent the probability of a 
gammon win conditioned on a win; then the unconditional probability of a gammon 
win = prob of win * conditional prob of gammon win. In that setup, both outputs 
are free to roam (0,1) without causing inconsistencies.

Is there something I'm missing here about why this is suboptimal? Is there some 
other way people tend to ensure that prob of gammon win <= prob of any kind of 
win?


_______________________________________________
Bug-gnubg mailing list
[email protected]
https://lists.gnu.org/mailman/listinfo/bug-gnubg

Reply via email to