Path: utzoo!utgpu!jarvis.csri.toronto.edu!mailrus!uflorida!gatech!gt-cmmsr!hms3!kirlik
From: kirlik@hms3 (Alex Kirlik)
Newsgroups: comp.ai.neural-nets
Subject: Thanks
Message-ID: <32131@gt-cmmsr.GATECH.EDU>
Date: 4 Mar 89 03:38:09 GMT
Sender: news@gt-cmmsr.GATECH.EDU
Reply-To: kirlik@hms3.gatech.edu (Alex Kirlik)
Distribution: usa
Organization: Center for Human-Machine Systems Research - Ga Tech
Lines: 45

This will be my final posting concerning my previous neural-net
question. (To thunderous applause)

Thanks for the many replies via email and the net; I have learned
from all - I guess that's the purpose of this forum.

I just want to conclude with two points. The two most frequent
criticisms of my comments were: 1. I have drastically overestimated
the degree to which nets have successfully mimicked human behavior;
and 2. I have drastically overestimated the degree to which any such
successes have been suggested to be the result of structural/
processing similarities between neural nets and the brain.

WRT point 1, I only want to suggest that some behavioral validity
demonstrations have been made, e.g. in _Parallel Distributed Processing_
Vol II, p. 266, Rumelhart and McClelland write "We have shown that our
simple learning model shows, to a remarkable degree, the characteristcs
of young children learning the morphology of the past tense in English."

My original posting was not concerned with defending the view that nets
are extremely successful in mimicking behavior (at whatever level), rather
I was concerned with examining the validity of arguments that suggest that
behavioral validity is due to structural/processing similarities between
our models and the brain (point 2).

WRT this point, the general reaction was that I was naive to think that
people take these models seriously at the level of units and neurons.
I AGREE that we shouldn't take these things seriously, that is
exactly the point I was trying to make by posing the question.

More specifically, my point is that the brain analogy cannot and should
not be used to explain any successes of these models until appropriate
referential relations that tie the model's constructs to the world can
be identified. I offered the "self-similarity" hypothesis as a possible
such relation, and recieved some interesting responses to it. 

But I have probably overestimated the degree to which explanations in
terms of unit-neuron relationships are still fashionable.

Thanks all,
Alex Kirlik

UUCP:	kirlik@chmsr.UUCP
        {backbones}!gatech!chmsr!kirlik
INTERNET:	kirlik@chmsr.gatech.edu