Path: utzoo!attcan!uunet!lll-winken!ames!oliveb!apple!bbn!bbn.com!aboulang
From: aboulang@bbn.com (Albert Boulanger)
Newsgroups: comp.ai.neural-nets
Subject: Re: Data Compression
Message-ID: <37416@bbn.COM>
Date: 18 Mar 89 15:56:47 GMT
References: <10199@nsc.nsc.com>
Sender: news@bbn.COM
Reply-To: aboulanger@bbn.com
Lines: 28
In-reply-to: andrew@nsc.nsc.com's message of 18 Mar 89 04:18:09 GMT


Here is another one from my collection since I am interested in this subject:

"Dimensionality-Reduction Using Connectionist Networks"
Eric Saud, MIT AI Memo 941 (January 1987)

Also the so-called "encoder" networks using backprop where the desired
output is set to be the input (dimensionality is reduced at the hidden
layer and the hidden layer activity can serve as the desired "real"
output) and Hinton's & McClelland's recirculating networks
generalization of encoder nets (see "Learning Representations by
Recirculation" Heoffrey Hinton & James McClelland, NIPS Proceedings
AIP Press 1988) can reduce dimensionality. In general the class of
learning algorithms called "unsupervised" learning can potentially
reduce dimensionality. There is however a spectrum of characteristics
among the different unsupervised learning procedures:

Do the reduced dimensions span the space?
Are the reduced dimensions orthogonal?

Terry Sanger's algorithm does both. It would be interesting to work
out what his learning rule does with sigmoid transfer functions for
the neurons.


Albert Boulanger
BBN Systems & Technologies Corporation
aboulanger@bbn.com