Path: utzoo!attcan!uunet!wuarchive!usc!snorkelwacker!husc6!baker2
From: baker2@husc9.harvard.edu (James Baker)
Newsgroups: comp.theory.cell-automata
Subject: cellular automata and neural networks
Message-ID: <BAKER2.90Apr11140207@husc9.harvard.edu>
Date: 11 Apr 90 18:02:07 GMT
Sender: news@husc6.harvard.edu
Organization: /sc9a/cs163/baker2/.organization
Lines: 16


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

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

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

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

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.

-- Jim