[Top][All Lists]

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
## [Bug-gnubg] Gammon output setup

**From**: |
Mark Higgins |

**Subject**: |
[Bug-gnubg] Gammon output setup |

**Date**: |
Sat, 10 Dec 2011 22:45:25 -0500 |

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] Gammon output setup**,
*Mark Higgins* **<=**