Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP
Path: utzoo!mnetor!seismo!rutgers!caip!clyde!cbatt!cwruecmp!hal!ncoast!btb
From: btb@ncoast.UUCP (Brad Banko)
Newsgroups: net.ai
Subject: Re: simulating a neural network
Message-ID: <1601@ncoast.UUCP>
Date: Wed, 22-Oct-86 18:15:32 EDT
Article-I.D.: ncoast.1601
Posted: Wed Oct 22 18:15:32 1986
Date-Received: Fri, 24-Oct-86 00:58:16 EDT
References: <223@eneevax.UUCP>
Reply-To: btb@ncoast.UUCP (Brad Banko)
Distribution: net
Organization: North Coast Computer Resources, Cleveland Public Access UNIX, Cleveland, OH
Lines: 19


Bill,
	Your program sounds very interesting... I have heard of related work
being done using matrices and transforms upon them to cause the "learning", but
your approach does something very interesting... it points out just what the
"missing" link is in the learning mode... getting the feedback in...
I suppose you have heard of these hardware devices that have been used recently
(Bell Labs, I think) based on a neural network model to find good solutions to
hard problems (travelling salesman...) fast... not the best solutions, but
fast good solutions...
	I would like to have a look at your source, if you would post it, or
send it to me...

					Brad Banko

				...!decvax!cwruecmp!ncoast!btb
		
-- 
Bradley T. Banko