TCB Publications - Abstract

Jeanne Rubner, Klaus Schulten, and Paul Tavan. A self-organizing network for complete feature extraction. In R. Eckmiller, G. Hartmann, and G. Hauske, editors, Parallel Processing in Neural Systems and Computers, pp. 365-368. Elsevier, Amsterdam, 1990.

RUBN90A We describe a two-layered network of linear neurons that organizes itself as to extract the maximal amount of information contained in a set of presented patterns. The weights between layers obey a Hebbian rule, whereas the lateral, hierarchically organized weights within the output layer follow an Anti-Hebbian rule. For a proper choice of the learning parameters, this rule forces the activities of the output units to become uncorrelated and the lateral weights to vanish. The weights between the two layers converge to the eigenvectors of the covariance matrix of input patterns, i.e. the network performs a principal component analysis of the input information. Consequently the output units become detectors of orthogonal features, similar to ones found in the brain of mammals.

Download Full Text

The manuscripts available on our site are provided for your personal use only and may not be retransmitted or redistributed without written permissions from the paper's publisher and author. You may not upload any of this site's material to any public server, on-line service, network, or bulletin board without prior written permission from the publisher and author. You may not make copies for any commercial purpose. Reproduction or storage of materials retrieved from this web site is subject to the U.S. Copyright Act of 1976, Title 17 U.S.C.

Download full text: PDF (263.7KB)