Path: utzoo!utgpu!watserv1!watmath!att!tut.cis.ohio-state.edu!cs.utexas.edu!usc!zaphod.mps.ohio-state.edu!wuarchive!mit-eddie!bloom-beacon!EE.ECN.PURDUE.EDU!tenorio
From: tenorio@EE.ECN.PURDUE.EDU (Manoel Fernando Tenorio)
Newsgroups: comp.theory.cell-automata
Subject: cellular automata and neural networks]
Message-ID: <9004121802.AA02795@ee.ecn.purdue.edu>
Date: 12 Apr 90 18:02:01 GMT
Sender: daemon@athena.mit.edu (Mr Background)
Distribution: inet
Organization: The Internet
Lines: 38


   From:  baker2@husc6.harvard.edu  (James Baker)
   Subject:  cellular automata and neural networks

   
   Has anyone constructed ``cellular automata'' that learn?

I think that before we can answer this question, it should be proceeded by a 
definition of what is and is not a CA. Certainly, learning has been done and
is possible on CA-like machines.

   There seems to be some good reasons to explore this possibility:

   1.  Arbitrary connections make analyzing neural networks difficult, if
   not just impossible.

I don't understand why that is so. We have published and algorithm to do that
in the IEEE Trans in NN. This is how the brain seems to form certain 
subcircuits, specially theone that are experienced based.

   2.  Cellular automata models are more readily simulated on hyper cube
   parallel architectures than conventional neural networks.

I don't understand why that is so. When I think of CA's, I have images of
highly regular structures, but that might not be necessary; but again the
same can be said about NN.

   Since one would train these models, they would not be cellular automata
   in the strict sense; for example, they might use some global reward
   signal or noise, in addition to receiving input and target data.

There have been a number of works on "local" learning rules for NN that can be 
applied here. You could take a look at CA-like machines in NIPS'87: 
Nondeterministic Adaptive Logic ELements by Windecker.

   -- Jim

------- End of Forwarded Message