Newsgroups: comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!das-news2.harvard.edu!news2.near.net!bloom-beacon.mit.edu!gatech!news.sprintlink.net!pipex!uknet!newsfeed.ed.ac.uk!ainews!thomasg
From: thomasg@aisb.ed.ac.uk (Thomas Grove)
Subject: Connectionist Vision
Message-ID: <D9rAJt.3n3@aisb.ed.ac.uk>
Sender: news@aisb.ed.ac.uk (Network News Administrator)
Organization: Dept AI, Edinburgh University, Scotland
X-Newsreader: TIN [version 1.2 PL2]
Date: Tue, 6 Jun 1995 14:50:16 GMT
Lines: 21

Hello all,

	I'm involved in an  Msc project concerned with 
connectionist approaches to vision. Of particular interest to
me at the moment would be anything concerning Neural net style
self-organising feature detectors. I've read papers on such things
in the past, but can't remember any of the titles and have been
unable to come up with anything in the library. I'd be thankful for
any help.

I would also love to here from anyone who has attempted/is attempting
to build a connectionist inspired vision system. By inspired, I mean that it 
does not necessarily have to consist of NNs and similar gubbins, but could
in theory be "compiled down" into a system of simple computing 
elements. That is, an approach that stresses local computation and 
parallelisation.

Many thanks,

Tom Grove

