Multistability in recurrent neural networks

Chang Yuan Cheng*, Kuang H. Lin, Chih-Wen Shih

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

127 Scopus citations

Abstract

Stable stationary solutions correspond to memory capacity in the application of associative memory for neural networks. In this presentation, existence of multiple stable stationary solutions for Hopfield-type neural networks with delay and without delay is investigated. Basins of attraction for these stationary solutions are also estimated. Such a scenario of dynamics is established through formulating parameter conditions based on a geometrical setting. The present theory is demonstrated by two numerical simulations on the Hopfield neural networks with delays.

Original languageEnglish
Pages (from-to)1301-1320
Number of pages20
JournalSIAM Journal on Applied Mathematics
Volume66
Issue number4
DOIs
StatePublished - 21 Aug 2006

Keywords

  • Delay equations
  • Multistability
  • Neural network

Fingerprint Dive into the research topics of 'Multistability in recurrent neural networks'. Together they form a unique fingerprint.

Cite this