Path: utzoo!utgpu!jarvis.csri.toronto.edu!mailrus!uwm.edu!gem.mps.ohio-state.edu!wuarchive!udel!princeton!phoenix!eliot
From: eliot@phoenix.Princeton.EDU (Eliot Handelman)
Newsgroups: comp.ai.neural-nets
Subject: Re: NETtalk results
Message-ID: <11470@phoenix.Princeton.EDU>
Date: 12 Nov 89 06:32:52 GMT
References: <1690@cod.NOSC.MIL> <77404@linus.UUCP> <13659@orstcs.CS.ORST.EDU> <20676@mimsy.umd.edu> <6936@pt.cs.cmu.edu> <cZLCp3S00Xc5I6tElg@andrew.cmu.edu>
Reply-To: eliot@phoenix.Princeton.EDU (Eliot Handelman)
Distribution: usa
Organization: Princeton University, NJ
Lines: 16

In article <cZLCp3S00Xc5I6tElg@andrew.cmu.edu> nf0a+@andrew.cmu.edu (Nathan W. Fullerton) writes:
;
;	In response to the many messages that have been claiming conventional
;rule based methods get more accurate results than NETtalk, I would like
;to point out that a accuracy is not the only advantage NETtalk claims. 

What appears to be true is:

1. You get the EFFECT of coding rules without explicit rules
2. The net is a more compact piece of data than a rule base
3. It still works when you perform the neural net equivalent of a lobotomy

I may be wrong but I seem to recall that Rosenberg's work centered on 
point 3. They cut away areas of connections and it still worked reasonably
well. What is interesting is how the memory is distributed, not what the
thing can do.