No subject

[Tom Shultz]

Subject: Abstract
Date: 21 June '94

FTP-host: archive.cis.ohio-state.edu
FTP-file: pub/neuroprose/shultz.cross.ps.Z

Please do not forward this announcement to other boards.  Thank you.

-------------------------------------------------------------

The following paper has been placed in the Neuroprose archive at 
Ohio State University: 

Analyzing Cross Connected Networks (8 pages)

Thomas R. Shultz 	
Department of Psychology & McGill Cognitive Science Centre		
McGill University
Montreal, Quebec, Canada H3A 1B1		
shultz at psych.mcgill.ca
	
and

Jeffrey L. Elman
Center for Research on Language
Department of Cognitive Science
University of California at San Diego
LaJolla, CA 92093-0126 
U.S.A.
elman at crl.ucsd.edu

Abstract
The non-linear complexities of neural networks make network 
solutions difficult to understand. Sanger's contribution analysis is 
here extended to the analysis of networks automatically generated 
by the cascade-correlation learning algorithm. Because such 
networks have cross connections that supersede hidden layers, 
standard analyses of hidden unit activation patterns are 
insufficient. A contribution is defined as the product of an output 
weight and the associated activation on the sending unit, whether 
that sending unit is an input or a hidden unit, multiplied by the sign 
of the output target for the current input pattern. Intercorrelations 
among contributions, as gleaned from the matrix of contributions x 
input patterns, can be subjected to principal components analysis 
(PCA) to extract the main features of variation in the contributions. 
Such an analysis is applied to three problems, continuous XOR, 
arithmetic comparison, and distinguishing between two interlocking 
spirals. In all three cases, this technique yields useful insights into 
network solutions that are consistent across several networks. 

The paper has been published in J. D. Cowan, G. Tesauro, & J. 
Alspector  (Eds.), Advances in Neural Information Processing 
Systems 6, pp. 1117-1124. San Francisco, CA: Morgan Kaufmannn.  

Instructions for ftp retrieval of this paper are given below.  If you 
are unable to retrieve and print it and therefore wish to receive a 
hardcopy, please send e-mail to shultz at psych.mcgill.ca

Please do not reply directly to this message.

FTP INSTRUCTIONS:

unix> ftp archive.cis.ohio-state.edu (or 128.146.8.52)
    Name: anonymous
    Password: <your e-mail address>
    ftp> cd pub/neuroprose
    ftp> binary
    ftp> get shultz.cross.ps.Z 
    ftp> quit
unix> uncompress shultz.cross.ps.Z 

Thanks to Jordan Pollack for maintaining this archive. 

Tom Shultz