Path: utzoo!utgpu!watmath!iuvax!mailrus!uunet!dtgcube!ed
From: ed@uunet!dtgcube (Edward Jung)
Newsgroups: comp.ai.neural-nets
Subject: Re: Nettalk
Keywords: connectionist physiology contraversy
Message-ID: <1989Nov17.180845.1786@uunet!dtgcube>
Date: 17 Nov 89 18:08:45 GMT
References: <4616@arctic.nprdc.arpa>
Organization: The Deep Thought Group, L.P.
Lines: 36
In-Reply-To: wilkins@nprdc.arpa's message of 16 Nov 89 23:57:00 GMT

In article <4616@arctic.nprdc.arpa> wilkins@nprdc.arpa (Charles Wilkins) writes:

   the relationship of the mistakes it made compared to the mistakes children
   make as they are learning to talk.  Another PDP model by Rumelhart and 
   McClelland teaches a network to learn the past tense of verbs.  They use
   a training corpus consisting approximately of the first few hundred verbs
   that children learn.  They then show the network words it hasn't seen. The
   success of the model is not demonstrated by the network responding to 
   'take' as 'took', but rather as 'taked', the same sort of mistake a child
   would make.  

This claim was refuted by linguists; there was subsequently a bit of a "contraversy"
surrounding this claim (the similarity of errors to that found in children, and
the effects of artificial "lesions" on the system) in Science (a year or two ago).

David Rumelhart himself might be amused to hear that the PDP group is so united
in their search for the basis of human cognition, although undoubtedly the phrase
"neural network" would imply some relationship to cognition (or at least its
"microstructure".  Indeed, prior to the 1988 ICNN (while there was still some doubt
to the physiological relevance of the then-current connectionist model),
connectionists were attempting to determine a biological mechanism, or an update
to their own back-propagation mechanism, that would unify physiological and
theoretical neural networks (hence the flurry of interest in NMDA receptors, etc
in 1988-1989).  Backpropagation has little physiological relevance to real neural
networks.

This is a topic rich in contraversy, but that should not inhibit connectionist
research!  At this point in time, it is premature to judge approaches by anything
other than their performance.  Even most human behavioral studies are not backed
by anything else.

-- 
Edward Jung                             The Deep Thought Group, L.P.
BIX: ejung                                      3400 Swede Hill Road
NeXT or UNIX mail                                Clinton, WA.  98236
        UUCP: uunet!dtgcube!ed          Internet: ed@dtg.com