From newshub.ccs.yorku.ca!ists!helios.physics.utoronto.ca!news-server.csri.toronto.edu!rpi!think.com!zaphod.mps.ohio-state.edu!wupost!psuvax1!rutgers!netnews.upenn.edu!jvnc.net!nuscc!hilbert!smoliar Mon Dec  9 10:47:41 EST 1991
Article 1826 of comp.ai.philosophy:
Path: newshub.ccs.yorku.ca!ists!helios.physics.utoronto.ca!news-server.csri.toronto.edu!rpi!think.com!zaphod.mps.ohio-state.edu!wupost!psuvax1!rutgers!netnews.upenn.edu!jvnc.net!nuscc!hilbert!smoliar
>From: smoliar@hilbert.iss.nus.sg (stephen smoliar)
Newsgroups: comp.ai.philosophy
Subject: Re: Dennett on Edelman--what a total loss
Message-ID: <1991Dec3.093313.14415@nuscc.nus.sg>
Date: 3 Dec 91 09:33:13 GMT
References: <57730@netnews.upenn.edu> <1991Nov29.050859.21552@bronze.ucs.indiana.edu> <57864@netnews.upenn.edu>
Sender: usenet@nuscc.nus.sg
Organization: Institute of Systems Science, NUS, Singapore
Lines: 44

In article <57864@netnews.upenn.edu> weemba@libra.wistar.upenn.edu (Matthew P
Wiener) writes:
>In article <1991Nov29.050859.21552@bronze.ucs.indiana.edu>, chalmers@bronze
>(David Chalmers) writes:
>>In article <57730@netnews.upenn.edu> weemba@libra.wistar.upenn.edu (Matthew P
>>Wiener) writes:
>
>>>Huh???  Edelman does not treat connectionism.  There is one reference
>>>to it in his trilogy, and he says the models lack the precise neuro-
>>>anatomical detail that he wants in a brain/mind model.  No more, no
>>>less.
>
>>See "Real Brains and Artificial Intelligence", in the 1988 special
>>issue of Daedalus on AI.  This paper identifies among the core tenets
>>of connectionism: [...] In other words, he has identified
>>connectionism entirely with the use of Hopfield nets and Boltzmann
>>machines, which in fact form a small and non-central subset of the
>>field.
>
>Considering that he avoids connectionism in his trilogy, but to
>point out it's non-anatomical detail, perhaps we can blame Reeke
>for the poor show here?  At the most, it's a side track.
>
I agree it's a side track, but I think that both Reeke and Edelman seem to do
only as much homework as they wish.  When I reviewed NEURAL DARWINISM for 
ARTIFICIAL INTELLIGENCE, I criticized the book for citing PERCEPTRONS but
not THE SOCIETY OF MIND.  My review of THE REMEMBERED PRESENT will be appearing
in ARTIFICIAL INTELLIGENCE relatively soon;  and, sure enough, that criticism
still stands.  Meanwhile, ARTIFICIAL INTELLIGENCE readers may have enjoyed
seeing Reeke go head-to-head against Marvin Minsky when we ran a joint review
of THE SOCIETY OF MIND.  Reeke made the mistake of accusing Minsky of having
a weak background in neurobiology, and Minsky did a reasonably good job of
taking him apart.

My thumb goes up with Weemba's, primarily because I think there are ways in
which we can learn from Edelman's progress thus far.  Nevertheless, I think
we have to read the stuff with some sense of where the warts are.  Some of
those warts seem to come from a selective approach to the literature which
is not always as scholarly as we would like.
-- 
Stephen W. Smoliar; Institute of Systems Science
National University of Singapore; Heng Mui Keng Terrace
Kent Ridge, SINGAPORE 0511
Internet:  smoliar@iss.nus.sg


