Newsgroups: comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!rochester!rit!isc-newsserver!ultb!jmm7076
From: jmm7076@ultb.isc.rit.edu (J.M. Maurer)
Subject: Multiple patterns
Message-ID: <1995Feb23.191125.5275@ultb.isc.rit.edu>
Sender: news@ultb.isc.rit.edu (USENET News System)
Nntp-Posting-Host: ultb-gw.isc.rit.edu
Organization: Rochester Institute of Technology
Date: Thu, 23 Feb 1995 19:11:25 GMT
Lines: 15

NN Folks,
	I am currently working on a project that will need the ability
to recognize several patterns in an input image.  For example if you
train a net to recognize all the letters in the english alphabet and 
then you present it a word, the net will systematically/iteratively
identify all of the letters in the work.  The one structure that I 
know of is Fukushima's Neocognitron Selective Attention Model.

	If you know of any references for a model such as this please
let me know [email or post is ok].

Thanx in advance...

Jim Maurer

