Newsgroups: comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!bb3.andrew.cmu.edu!newsfeed.pitt.edu!gatech!news.mathworks.com!uunet!in1.uu.net!redstone.interpath.net!sas!mozart.unx.sas.com!saswss
From: saswss@hotellng.unx.sas.com (Warren Sarle)
Subject: Re: What IS a neural-net?
Originator: saswss@hotellng.unx.sas.com
Sender: news@unx.sas.com (Noter of Newsworthy Events)
Message-ID: <DnKKun.LrC@unx.sas.com>
Date: Fri, 1 Mar 1996 03:39:59 GMT
X-Nntp-Posting-Host: hotellng.unx.sas.com
References: <4env0k$i37@gensva.athena.livjm.ac.uk> <4eotuf$5lg@delphi.cs.ucla.edu>  <DMvrIJ.Iuo@unx.sas.com> <4gghaq$7u8@delphi.cs.ucla.edu> <4ghs6d$ntv@cantaloupe.srv.cs.cmu.edu> <4gm0g7$2sl@delphi.cs.ucla.edu>
Organization: SAS Institute Inc.
Lines: 33


In article <4gm0g7$2sl@delphi.cs.ucla.edu>, edwin@cs.ucla.edu (E. Robert Tisdale) writes:
|> ...
|> The fact is that almost no one even attempts to justify artificial neural
|> network architecture or learning algorithm design on biological grounds.
|> I doubt that even a tiny fraction of the subscribers to this newsgroup
|> have ever done so.  It is meaningless to claim that artificial neural
|> networks are inspired by natural neural networks.
|> 
|> The problem is that the answer to the frequently answered question
|> `What is a neural network?' seems to imply that an [artificial] neural
|> network is not a neural network unless the "design was motivated
|> by the design and functioning of human brains and components thereof."
|> And this is simply NOT TRUE!

The _DARPA Neural Network Study_ (1988), p. 17: "A neural network is a
computational structure modeled on biological processes."

Hertz, Krogh & Palmer (1991), _Introduction to the Theory of Neural
Computation_, chapter 1.1 is entitled, "Inspiration from Neuroscience."
On p. 1 they say that neural computation "is inspired by knowledge from
neuroscience, though it does not try to biologically realistic in detail."

Haykin (1994), _Neural Networks: A Comprehensive Foundation_, "...
a neural network is a machine that is designed to model the way in
which the brain performs a particular task or function of interest."


-- 

Warren S. Sarle       SAS Institute Inc.   The opinions expressed here
saswss@unx.sas.com    SAS Campus Drive     are mine and not necessarily
(919) 677-8000        Cary, NC 27513, USA  those of SAS Institute.
