Newsgroups: comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!rochester!cornellcs!newsstand.cit.cornell.edu!news.kei.com!newsfeed.internetmci.com!in2.uu.net!winternet.com!news.minn.net!skypoint.com!umn.edu!peschko
From: peschko@cs.umn.edu (Edward S. Peschko)
Subject: unsupervised learning
Message-ID: <peschko.817580034@cs.umn.edu>
Sender: news@news.cis.umn.edu (Usenet News Administration)
Nntp-Posting-Host: femto.cs.umn.edu
Organization: University of Minnesota, Twin Cities
Date: Tue, 28 Nov 1995 17:33:54 GMT
Lines: 15

hey all --

I had some very basic questions about unsupervised learning.. 

What are the principles behind this? It seems very unintuitive to me that 
a neural net could pick up more than simple patterns in data, but weirder 
things could happen..

Also, is unsupervised learning good for anything other than extremely simple
problems? And if it *has* been used on complicated domains, could someone
point to me where... (surprised to see that this is not a FAQ..)

Ed


