Path: utzoo!utgpu!utstat!jarvis.csri.toronto.edu!mailrus!cs.utexas.edu!hellgate.utah.edu!helios.ee.lbl.gov!ucsd!nprdc!wilkins
From: wilkins@nprdc.arpa (Charles Wilkins)
Newsgroups: comp.ai.neural-nets
Subject: Nettalk
Message-ID: <4616@arctic.nprdc.arpa>
Date: 16 Nov 89 23:57:00 GMT
Sender: news@nprdc.arpa
Reply-To: wilkins@nprdc.arpa (Charles Wilkins)
Lines: 20
Organization:

I don't want to get into a protracted argument about nettalk, but I would
like to point out the following.  One important point about nettalk, was
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.  
These models can be looked at in many different ways, but I stand by my
claim that the primary purpose these models are used by the 'PDP' group
(Sejnowski,Rumelhart,McClelland, etal) is to model (however successfully or 
unsuccessfully) human cognition, and if it leads to other uses (e.g.
statistical tool) then wonderful.
These are strictly my own opinion, but I think that the 2-volume set
'Parallel Distibuted Processing: Explorations in the microstructure of
cognition' bears me out.

-Chuck Wilkins