kirlik@hms3 (Alex Kirlik) (03/04/89)
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.edubloch@sequoya.ucsd.edu (Steve Bloch) (03/09/89)
In article <32131@gt-cmmsr.GATECH.EDU> kirlik@hms3.gatech.edu (Alex Kirlik) writes: >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. But it's quite predictable that the general public WILL read things that way when you name your discipline "neural nets" and announce results in areas generally considered as universal human behaviour. "The above opinions are my own. But that's just my opinion." Stephen Bloch
stu4@larry.mcrcim.mcgill.edu (01/26/91)
I just wanted to say a big thank you to all of you
who sent me their lists, comments and ideas on
NN books. It will be very helpful...
...........................................................................
Craig Jones ---> bnrmtl!stu4@larry.mcrcim.mcgill.edu
"There are no stupid questions, only stupid answers."
__________________________
\ Any opinions expressed /|
\ reflect the opinions/_L_________________________________
\_____________________|are my own and do not necessarily /
|of anyone I am affiliated with. /
|________________________________/
Bell Northern Research, Montreal Que.
...........................................................................