Newsgroups: comp.ai.neural-nets
From: David@longley.demon.co.uk (David Longley)
Path: cantaloupe.srv.cs.cmu.edu!das-news2.harvard.edu!news2.near.net!news.mathworks.com!gatech!howland.reston.ans.net!news.sprintlink.net!demon!news.demon.co.uk!longley.demon.co.uk!David
Subject: Re: bias
References:  <1995Apr28.195623.7533@cm.cf.ac.uk> <D7t3E1.ECz@unx.sas.com>
Organization: Relational Technology
Reply-To: David@longley.demon.co.uk
X-Newsreader: Demon Internet Simple News v1.29
Lines: 30
X-Posting-Host: longley.demon.co.uk
Date: Sun, 30 Apr 1995 00:11:49 +0000
Message-ID: <799200709snz@longley.demon.co.uk>
Sender: usenet@demon.co.uk

In article <D7t3E1.ECz@unx.sas.com>
           saswss@hotellng.unx.sas.com "Warren Sarle" writes:

> If the network is trained to convergence by least squares and there is a
> "bias" (in the usual NN sense, "intercept" in statisticalese) in the
> outputs, then the residuals will indeed have a mean of zero. If you
> violate any of those conditions, the residuals may or may not have a
> mean of zero. The statisticians should realize that, if they understand
> that feedforward neural nets are nonlinear regression models.

This being so, why all the fuss about 'artificial neural networks'? 
Statisticians have been building better and better regression techniques 
over the years, and those techniques are based on clear *extensional* 
principles where the weights can be readily attributed to the independent
variables. I can't help but feel that all that artificial neural networks
do is model the somewhat daft, *intensional* way in which biological systems
model relations - ie 'overfitting', getting stuck in ruts and all the rest 
of the little pitfalls we tend to get ourselves into (Tversky & Kahneman 1974).

Surely AI wants to build *intelligent systems*, not artifical *human systems*.

(And before anyone says it....NO.....it isn't a product of distintly *human*
thinking and brain processing that has given us all we know and cherish...
that comes from *extensional* analysis, and Frege (1879) showed that to be
a purely mechanistic process which Turing and later Von Neumann showed to be
relaisable in terms of mathematical logic....

(see 'Fragments of Behaviour' 25/4/95 in sci.psychology etc for an elaboration)
-- 
David Longley
