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
