Complete stability in multistable delayed neural networks

Chang Yuan Cheng*, Chih-Wen Shih

*Corresponding author for this work

Research output: Contribution to journalLetterpeer-review

32 Scopus citations

Abstract

We investigate the complete stability for multistable delayed neural networks. A new formulation modified from the previous studies on multistable networks is developed to derive componentwise dynamical property. An iteration argument is then constructed to conclude that every solution of the network converges to a single equilibrium as time tends to infinity. The existence of 3n equilibria and 2n positively invariant sets for the n-neuron system remains valid under the new formulation. The theory is demonstrated by a numerical illustration.

Original languageEnglish
Pages (from-to)719-740
Number of pages22
JournalNeural Computation
Volume21
Issue number3
DOIs
StatePublished - Mar 2009

Fingerprint

Dive into the research topics of 'Complete stability in multistable delayed neural networks'. Together they form a unique fingerprint.

Cite this