1 December 1991 Learning in linear feature-discovery networks
Author Affiliations +
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.
© (1991) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Todd K. Leen, Todd K. Leen, } "Learning in linear feature-discovery networks", Proc. SPIE 1565, Adaptive Signal Processing, (1 December 1991); doi: 10.1117/12.49799; https://doi.org/10.1117/12.49799
PROCEEDINGS
10 PAGES


SHARE
Back to Top