Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP
Path: utzoo!mnetor!seismo!lll-crg!nike!cit-vax!mangler
From: mangler@cit-vax.Caltech.Edu (System Mangler)
Newsgroups: net.arch
Subject: Re: Computing with Neural Circuits:
Message-ID: <894@cit-vax.Caltech.Edu>
Date: Wed, 13-Aug-86 02:41:07 EDT
Article-I.D.: cit-vax.894
Posted: Wed Aug 13 02:41:07 1986
Date-Received: Wed, 13-Aug-86 09:13:19 EDT
References: <1883@ecsvax.UUCP> <64300001@prism>
Organization: California Institute of Technology
Lines: 12
Summary: threshold logic

In article <64300001@prism>, brian@prism.UUCP writes:
> Perhaps I'm being overly simplistic, but doesn't this neural network
> stuff seem similar to ANALOG networks of non-linear devices?

(Being even more simplistic)  As near as I can tell, neural network
circuits are made of threshold logic.  When a 'neuron' has more
excitory inputs true than inhibitory inputs, it fires.	That's
threshold logic.  The stuff is described in all the old digital
switching theory books (such as Kohavi) but nobody seems to have
used it until Hopfield.  Doesn't look very analog to me.

Don Speck   speck@vlsi.caltech.edu  seismo!cit-vax!speck