From newshub.ccs.yorku.ca!ists!helios.physics.utoronto.ca!news-server.csri.toronto.edu!rpi!think.com!zaphod.mps.ohio-state.edu!qt.cs.utexas.edu!cs.utexas.edu!asuvax!gatech!darwin.sura.net!jvnc.net!netnews.upenn.edu!libra.wistar.upenn.edu Mon Dec  9 10:47:47 EST 1991
Article 1837 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!qt.cs.utexas.edu!cs.utexas.edu!asuvax!gatech!darwin.sura.net!jvnc.net!netnews.upenn.edu!libra.wistar.upenn.edu
>From: weemba@libra.wistar.upenn.edu (Matthew P Wiener)
Newsgroups: comp.ai.philosophy
Subject: Of course R&E missed out on backpropagation
Message-ID: <58158@netnews.upenn.edu>
Date: 4 Dec 91 01:09:32 GMT
References: <1991Nov29.050859.21552@bronze.ucs.indiana.edu>
Sender: news@netnews.upenn.edu
Reply-To: weemba@libra.wistar.upenn.edu (Matthew P Wiener)
Organization: The Wistar Institute of Anatomy and Biology
Lines: 45
Nntp-Posting-Host: libra.wistar.upenn.edu
In-reply-to: chalmers@bronze.ucs.indiana.edu (David Chalmers)

In article <1991Nov29.050859.21552@bronze.ucs.indiana.edu>, chalmers@bronze (David Chalmers) writes:
>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.  He appears not to have heard of backpropagation, for
>instance, which has been much more central to connectionist practice,
>and which fits none of the descriptions above.

You know, I just realized I've been swindled.  Good job!

Of course Reeke and Edelman missed out on backpropagation.  When
connectionism was rediscovered at the beginning of the '80s, the
first ones out of the gate were Hopfield nets, and the second out
were the Boltzmann machines.  It took a few years before backprop-
agation was part of the new wave.  And it naturally takes longer
before outsiders figure out that the center has moved.

So by book three, Edelman knew to just waffle over connectionism
and what it means for brainkind and to spell out his own work.

>The point is that Edelman has been far more concerned to distance
>himself from others than is necessary.

As I said, Edelman is not "just another guy".  He's a Nobel prize
winner in a far away enough discipline who gets into SCIENCE and
NATURE just by announcing that he's changing labs.  (Yeah yeah,
the fact that he's the second Big Name to jump ship from Rocke-
feller U after the slowly winding down Baltimore scandal is no
doubt part of the newsworthiness.)  Regardless of what distance
he maintains from the cognitive crowd, he will attract funding
and a goodly supply of interested junior faculty and grad students
who will run his model through the shakes.  He can afford to wait
for connectionism to discover that it's a brand of neural darwinism
and reentrant signaling, instead of the other way around.

In no way shape or form am I implying the above cynicism is the
weemba stamp of approval.  I am saying that it's perfectly natural
for Edelman to think that it's a waste of time to figure out whether
or not he's reinvented a johnny-come-lately wheel.  His first book
on these topics goes back to 1978, so he's been thinking along these
lines long before the new wave of connectionism.
-- 
-Matthew P Wiener (weemba@libra.wistar.upenn.edu)


