Newsgroups: comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!das-news2.harvard.edu!news2.near.net!howland.reston.ans.net!ix.netcom.com!netcom.com!komodo
From: komodo@netcom.com (Tom Johnson)
Subject: Trade for NN code in Basic
Message-ID: <komodoD31Ano.6II@netcom.com>
Organization: NETCOM On-line Communication Services (408 261-4700 guest)
X-Newsreader: TIN [version 1.2 PL1]
Date: Thu, 26 Jan 1995 22:33:24 GMT
Lines: 21

I have spent many years developing the strongest commercial backgammon 
program only to be surpassed by an uppity neural net algorithm. So trying 
to keep up with the state of the computer art, I have tried to learn 
'simple' NN algorithms. I have purchased several books and spent over one 
hundred unsuccessful hours trying to implement the XOR test program. I 
believe that I grok the concepts, but I am missing something in the back 
propagation part.

I have sample code in C and Pascal which I have tried to translate to Basic.
My math background is limited to high school algebra so the equations in 
the books are foreign to me.

I know, I know. I intend to learn the 'C" language and update my math 
background, but in the interim I would like to trade a copy of my 
program, Expert Backgammon for Macintosh (a $50 retail value) for some 
sample documented code in the Basic language that an idiot could follow. 
Please include code for momentum.

Thanks for helping a beginner out of the dark.

Tom Johnson
