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
Volume1565
ISBN (Print)0819406937
StatePublished - 1991
EventAdaptive Signal Processing - San Diego, CA, USA
Duration: Jul 22 1991Jul 24 1991

Other

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

Fingerprint

learning
cycles

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Leen, T. K. (1991). Learning in linear feature-discovery networks. In S. Haykin (Ed.), Proceedings of SPIE - The International Society for Optical Engineering (Vol. 1565, pp. 472-481). Publ by Int Soc for Optical Engineering.

Learning in linear feature-discovery networks. / Leen, Todd K.

Proceedings of SPIE - The International Society for Optical Engineering. ed. / Simon Haykin. Vol. 1565 Publ by Int Soc for Optical Engineering, 1991. p. 472-481.

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

Leen, TK 1991, Learning in linear feature-discovery networks. in S Haykin (ed.), Proceedings of SPIE - The International Society for Optical Engineering. vol. 1565, Publ by Int Soc for Optical Engineering, pp. 472-481, Adaptive Signal Processing, San Diego, CA, USA, 7/22/91.
Leen TK. Learning in linear feature-discovery networks. In Haykin S, editor, Proceedings of SPIE - The International Society for Optical Engineering. Vol. 1565. Publ by Int Soc for Optical Engineering. 1991. p. 472-481
Leen, Todd K. / Learning in linear feature-discovery networks. Proceedings of SPIE - The International Society for Optical Engineering. editor / Simon Haykin. Vol. 1565 Publ by Int Soc for Optical Engineering, 1991. pp. 472-481
@inproceedings{98d644532a634e3c81983fba70bee87d,
title = "Learning in linear feature-discovery networks",
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.",
author = "Leen, {Todd K.}",
year = "1991",
language = "English (US)",
isbn = "0819406937",
volume = "1565",
pages = "472--481",
editor = "Simon Haykin",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "Publ by Int Soc for Optical Engineering",

}

TY - GEN

T1 - Learning in linear feature-discovery networks

AU - Leen, Todd K.

PY - 1991

Y1 - 1991

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=0026371655&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026371655&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0819406937

VL - 1565

SP - 472

EP - 481

BT - Proceedings of SPIE - The International Society for Optical Engineering

A2 - Haykin, Simon

PB - Publ by Int Soc for Optical Engineering

ER -