Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP
Path: utzoo!mnetor!uunet!husc6!hao!boulder!mikek
From: mikek@boulder.Colorado.EDU (Mike Kranzdorf)
Newsgroups: comp.ai
Subject: Re: Neural Networks & Unaligned fields
Message-ID: <2102@sigi.Colorado.EDU>
Date: Thu, 3-Sep-87 11:41:53 EDT
Article-I.D.: sigi.2102
Posted: Thu Sep  3 11:41:53 1987
Date-Received: Sat, 5-Sep-87 10:39:10 EDT
References: <277@ndmath.UUCP>
Sender: news@sigi.Colorado.EDU
Reply-To: mikek@boulder.Colorado.EDU (Mike Kranzdorf)
Organization: University of Colorado, Boulder
Lines: 11
Keywords: PDP Neural Nets

I am not familiar with the net in Byte, but I assume it is a two layer net,
like the one that was posted.  If this is the case, shifted patterns will
not be recognized.  It takes at least three layers for a net to have an
internal representation of the structure of an input pattern.  A good 
overview paper describing these kinds of conditions can be found in the
IEEE ASSP (Acoustics, Speech, and Signal Processing) Magazine April 1987,
Volume 4, Number 2, "An Introduction to Computing with Neural Nets" by
Richard P. Lippmann.  The article focuses on catagorizers, but is 
informative about nets in general.  

--mike