Newsgroups: comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!fs7.ece.cmu.edu!hudson.lm.com!news.pop.psu.edu!news.cac.psu.edu!howland.reston.ans.net!cs.utexas.edu!utnut!wave.scar!93funkst
From: 93funkst@wave.scar.utoronto.ca (FUNK  STEVEN LESLIE,,Student Account)
Subject: Re: Training sets
Message-ID: <D0LzEF.B2@wave.scar.utoronto.ca>
Sender: usenet@wave.scar.utoronto.ca
Nntp-Posting-Host: wave.scar.utoronto.ca
Reply-To: 93funkst@wave.scar.utoronto.ca
Organization: University of Toronto - Scarborough College
References: <165@leopold.win-uk.net>
Date: Sat, 10 Dec 1994 18:59:03 GMT
Lines: 8

Hi,

	I've noticed the same problem from a cognitive point of view.  I see and read about a lot of people using multi-layered systems trained with backprop to model cognitive phenomena.  The problem is that a system like this learns the functions in the training set and emulates them.  Which tells you little or nothing about the underlying system at work in the human mind.  There is a greater envolvment of empirical verification in the cognitive arena.  But still the problems do persist.  I would also be intere
sted in hearing about any standardized tests for network performance.  Not just from a computational point of view, but from a cognitive one as well.

Steve Funk
93funkst@wave.scar.utoronto.ca

