Learning in linear feature-discovery networks

Todd K. Leen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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.

Original languageEnglish (US)
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
EditorsSimon Haykin
PublisherPubl by Int Soc for Optical Engineering
Pages472-481
Number of pages10
ISBN (Print)0819406937
StatePublished - 1991
EventAdaptive Signal Processing - San Diego, CA, USA
Duration: Jul 22 1991Jul 24 1991

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume1565
ISSN (Print)0277-786X

Other

OtherAdaptive Signal Processing
CitySan Diego, CA, USA
Period7/22/917/24/91

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Learning in linear feature-discovery networks'. Together they form a unique fingerprint.

Cite this