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

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