Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!sun-barr!olivea!uunet!samsung!sol.ctr.columbia.edu!cunixf.cc.columbia.edu!cs.columbia.edu!fahn
From: fahn@cs.columbia.edu (Paul N. Fahn)
Newsgroups: comp.ai.neural-nets
Subject: Re: Postulates on the number of neurons
Summary: biological nets not optimal
Message-ID: <1990Dec11.174921.26838@cs.columbia.edu>
Date: 11 Dec 90 17:49:21 GMT
References: <1990Dec11.040646.20760@noose.ecn.purdue.edu>
Sender: news@cs.columbia.edu (The Daily News)
Reply-To: fahn@hudson.columbia.edu (Paul Fahn)
Followup-To: comp.ai.neural-nets
Organization: Columbia University Department of Computer Science
Lines: 19

In article <1990Dec11.040646.20760@noose.ecn.purdue.edu> muttiah@welsh.ecn.purdue.edu (Ranjan S Muttiah) writes:
>
>What do researches think about why there are so many _individual_ neurons  
>in the human brain (something like 10^19) ?  Is there some critical number
>needed for "intelligent behaviour" ?
>

It seems to me that (computer-based) neural net researchers too often
presume that biological organization is somehow optimal. It may be that
the brain represents an enormous waste of resources, and that 
"intelligent behavior" can be achieved with far fewer neurons, if only
they were organized more "intelligently". (or, equivalently, that higher
intelligence could be achieved with the same number of neurons.)

We should definitely look at biological nets for ideas, but in a very
critical way, and be prepared to reject anything found in the biological
realm.

.Paul.