Article: Convergence of discrete-time recurrent neural networks with variable delay

File Download
  • No File Attached
Links for fulltext
(May Require Subscription)
Supplementary
  • Basic View
  • Metadata View
  • XML View
TitleConvergence of discrete-time recurrent neural networks with variable delay
AuthorsLiang, J2
Cao, J2
Lam, J1
KeywordsComponentwise Exponential Stability
Discrete-Time
Global Exponential Stability
Lyapunov Functional
Recurrent Neural Networks (Rnns)
Variable Delay
Issue Date2005
PublisherWorld Scientific Publishing Co Pte Ltd. The Journal's web site is located at http://www.worldscinet.com/ijbc/ijbc.shtml
CitationInternational Journal Of Bifurcation And Chaos In Applied Sciences And Engineering, 2005, v. 15 n. 2, p. 581-595 [How to Cite?]
DOI: http://dx.doi.org/10.1142/S0218127405012235
AbstractIn this paper, some global exponential stability criteria for the equilibrium point of discrete-time recurrent neural networks with variable delay are presented by using the linear matrix inequality (LMI) approach. The neural networks considered are assumed to have asymmetric weighting matrices throughout this paper. On the other hand, by applying matrix decomposition, the model is embedded into a cooperative one, the latter possesses important order-preserving properties which are basic to our analysis. A sufficient condition is obtained ensuring the componentwise exponential stability of the system with specific performances such as decay rate and trajectory bounds. © World Scientific Publishing Company.
ISSN0218-1274
2011 Impact Factor: 0.755
2011 SCImago Journal Rankings: 0.058
DOIhttp://dx.doi.org/10.1142/S0218127405012235
ISI Accession Number IDWOS:000228906700012
ReferencesReferences in Scopus
DC Field
Value
dc.contributor.authorLiang, J
dc.contributor.authorCao, J
dc.contributor.authorLam, J
dc.date.accessioned2012-08-08T08:43:51Z
dc.date.available2012-08-08T08:43:51Z
dc.date.issued2005
dc.description.abstractIn this paper, some global exponential stability criteria for the equilibrium point of discrete-time recurrent neural networks with variable delay are presented by using the linear matrix inequality (LMI) approach. The neural networks considered are assumed to have asymmetric weighting matrices throughout this paper. On the other hand, by applying matrix decomposition, the model is embedded into a cooperative one, the latter possesses important order-preserving properties which are basic to our analysis. A sufficient condition is obtained ensuring the componentwise exponential stability of the system with specific performances such as decay rate and trajectory bounds. © World Scientific Publishing Company.
dc.description.natureLink_to_subscribed_fulltext
dc.identifier.citationInternational Journal Of Bifurcation And Chaos In Applied Sciences And Engineering, 2005, v. 15 n. 2, p. 581-595 [How to Cite?]
DOI: http://dx.doi.org/10.1142/S0218127405012235
dc.identifier.doihttp://dx.doi.org/10.1142/S0218127405012235
dc.identifier.epage595
dc.identifier.isiWOS:000228906700012
dc.identifier.issn0218-1274
2011 Impact Factor: 0.755
2011 SCImago Journal Rankings: 0.058
dc.identifier.issue2
dc.identifier.scopuseid_2-s2.0-18644377250
dc.identifier.spage581
dc.identifier.urihttp://hdl.handle.net/10722/156760
dc.identifier.volume15
dc.languageeng
dc.publisherWorld Scientific Publishing Co Pte Ltd. The Journal's web site is located at http://www.worldscinet.com/ijbc/ijbc.shtml
dc.publisher.placeSingapore
dc.relation.ispartofInternational Journal of Bifurcation and Chaos in Applied Sciences and Engineering
dc.relation.referencesReferences in Scopus
dc.subjectComponentwise Exponential Stability
dc.subjectDiscrete-Time
dc.subjectGlobal Exponential Stability
dc.subjectLyapunov Functional
dc.subjectRecurrent Neural Networks (Rnns)
dc.subjectVariable Delay
dc.titleConvergence of discrete-time recurrent neural networks with variable delay
dc.typeArticle
Author Affiliations
  1. The University of Hong Kong
  2. Southeast University