[Top][All Lists]

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Bug-gnubg] race net: 0ply and 1ply

From: Joseph Heled
Subject: Re: [Bug-gnubg] race net: 0ply and 1ply
Date: Wed, 27 Nov 2002 10:45:52 +1300
User-agent: Mozilla/5.0 (X11; U; SunOS sun4u; en-US; rv:1.1) Gecko/20020829

Your concern is fully shared. That is why my benchmark is *totally independent* of the training.
This is not an illusory result, but a real one.


Gary Wong wrote:
On Wed, Nov 27, 2002 at 07:55:44AM +1300, Joseph Heled wrote:

Personally I would be at least a little bit suspicious of a net with
poor 1-ply performance (which is not to say that I wouldn't use it,
merely that I would be worried if I didn't have some sort of

For instance, poor 1-ply performance is what we would expect to see
from a net with poor generalisation (which might occur if the training
data set is too close to the comparison data set).  In that case, the
"good" 0-ply (and to a lesser extent, 2-ply) performance might be largely
illusory.  (If a net gives excellent 0-ply results right across the
universe of inputs, it can't possibly give bad 1-ply results.)

This (and similar problems) make me uneasy about poor 1-ply performance.


reply via email to

[Prev in Thread] Current Thread [Next in Thread]