Share Email Print

Proceedings Paper

Learning in linear feature-discovery networks
Author(s): Todd K. Leen
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

We describe the dynamics of learning in unsupervised linear feature-discovery networks that have recurrent lateral connections. Bifurcation theory provides a description of the location of multiple equilibria and limit cycles in the weight-space dynamics.

Paper Details

Date Published: 1 December 1991
PDF: 10 pages
Proc. SPIE 1565, Adaptive Signal Processing, (1 December 1991); doi: 10.1117/12.49799
Show Author Affiliations
Todd K. Leen, Oregon Graduate Institute of Science and Technology (United States)

Published in SPIE Proceedings Vol. 1565:
Adaptive Signal Processing
Simon Haykin, Editor(s)

© SPIE. Terms of Use
Back to Top