Newsgroups: sci.physics,alt.sci.physics.new-theories,alt.consciousness,sci.cognitive,comp.ai,sci.philosophy.tech,sci.skeptic
Path: cantaloupe.srv.cs.cmu.edu!rochester!udel!gatech!swrinde!pipex!uknet!newsfeed.ed.ac.uk!dcs.ed.ac.uk!newshost.dcs.ed.ac.uk!mxm
From: Mike Moran <mxm@dcs.ed.ac.uk>
Subject: Re: Review of Shadows of the Mind
In-Reply-To: sarfatti@ix.netcom.com's message of 20 Mar 1995 00:18:16 GMT
Message-ID: <MXM.95Mar21004051@dcs.ed.ac.uk>
Sender: cnews@dcs.ed.ac.uk (UseNet News Admin)
Organization: Department of Computer Science, Edinburgh University
References: <3kd36r$bh6@ixnews2.ix.netcom.com> <3kdtfn$7v2@fang.dsto.gov.au>
	<3kdtoq$7v2@fang.dsto.gov.au> <3kfn0a$npj@news.primenet.com>
	<3kihk8$ltl@ixnews4.ix.netcom.com>
Date: Tue, 21 Mar 1995 00:40:50 GMT
Lines: 29
Xref: glinda.oz.cs.cmu.edu sci.physics:114449 sci.cognitive:6899 comp.ai:28321 sci.philosophy.tech:17135 sci.skeptic:107469



Jack Sarfatti writes:
In article <3kihk8$ltl@ixnews4.ix.netcom.com> sarfatti@ix.netcom.com (Jack Sarfatti) writes:


sarfatti> In <3kfn0a$npj@news.primenet.com> english@primenet.com (Lawson English) 
sarfatti> writes: 
[ ... blah blah deleted ... ]
sarfatti> Also I thought that in all actual neural nets there must be some kind of
sarfatti> already existing programmer somehow setting the goals? Please correct 
sarfatti> me. What real evidence is there that an intelligent net will 
sarfatti> spontaneously arise under natural selection? Some kind of computer 
sarfatti> simulations. A comprehensive review tutorial on this by some pundit is 
sarfatti> in order.

	I'm no net pundit, but i can tell you that nets learning by
'tutoring' or 'teaching' of inputs and outputs are but one class of
neural nets. There are others that are simply given a clump of data,
and essentially make 'sense' of it; ie find some patterns in it. I
can't give many more details as i'm short on time, but in summary, the
type of neural net you cite above are not the only type of nets that
can be created, and learn. 

				Thanks,

					Mike


