File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Global robust exponential stability analysis for interval recurrent neural networks

TitleGlobal robust exponential stability analysis for interval recurrent neural networks
Authors
KeywordsGlobal Exponential Stability
Interval Systems
Linear Matrix Inequality
Recurrent Neural Networks
Issue Date2004
PublisherElsevier BV. The Journal's web site is located at http://www.elsevier.com/locate/physleta
Citation
Physics Letters, Section A: General, Atomic And Solid State Physics, 2004, v. 325 n. 2, p. 124-133 How to Cite?
AbstractThis Letter investigates the problem of robust global exponential stability analysis for interval recurrent neural networks (RNNs) via the linear matrix inequality (LMI) approach. The values of the time-invariant uncertain parameters are assumed to be bounded within given compact sets. An improved condition for the existence of a unique equilibrium point and its global exponential stability of RNNs with known parameters is proposed. Based on this, a sufficient condition for the global robust exponential stability for interval RNNs is obtained. Both of the conditions are expressed in terms of LMIs, which can be checked easily by various recently developed convex optimization algorithms. Examples are provided to demonstrate the reduced conservatism of the proposed exponential stability condition. © 2004 Elsevier B.V. All rights reserved.
Persistent Identifierhttp://hdl.handle.net/10722/156763
ISSN
2015 Impact Factor: 1.677
2015 SCImago Journal Rankings: 0.755
ISI Accession Number ID
References

 

DC FieldValueLanguage
dc.contributor.authorXu, Sen_US
dc.contributor.authorLam, Jen_US
dc.contributor.authorHo, DWCen_US
dc.contributor.authorZou, Yen_US
dc.date.accessioned2012-08-08T08:43:52Z-
dc.date.available2012-08-08T08:43:52Z-
dc.date.issued2004en_US
dc.identifier.citationPhysics Letters, Section A: General, Atomic And Solid State Physics, 2004, v. 325 n. 2, p. 124-133en_US
dc.identifier.issn0375-9601en_US
dc.identifier.urihttp://hdl.handle.net/10722/156763-
dc.description.abstractThis Letter investigates the problem of robust global exponential stability analysis for interval recurrent neural networks (RNNs) via the linear matrix inequality (LMI) approach. The values of the time-invariant uncertain parameters are assumed to be bounded within given compact sets. An improved condition for the existence of a unique equilibrium point and its global exponential stability of RNNs with known parameters is proposed. Based on this, a sufficient condition for the global robust exponential stability for interval RNNs is obtained. Both of the conditions are expressed in terms of LMIs, which can be checked easily by various recently developed convex optimization algorithms. Examples are provided to demonstrate the reduced conservatism of the proposed exponential stability condition. © 2004 Elsevier B.V. All rights reserved.en_US
dc.languageengen_US
dc.publisherElsevier BV. The Journal's web site is located at http://www.elsevier.com/locate/physletaen_US
dc.relation.ispartofPhysics Letters, Section A: General, Atomic and Solid State Physicsen_US
dc.subjectGlobal Exponential Stabilityen_US
dc.subjectInterval Systemsen_US
dc.subjectLinear Matrix Inequalityen_US
dc.subjectRecurrent Neural Networksen_US
dc.titleGlobal robust exponential stability analysis for interval recurrent neural networksen_US
dc.typeArticleen_US
dc.identifier.emailLam, J:james.lam@hku.hken_US
dc.identifier.authorityLam, J=rp00133en_US
dc.description.naturelink_to_subscribed_fulltexten_US
dc.identifier.doi10.1016/j.physleta.2004.03.038en_US
dc.identifier.scopuseid_2-s2.0-1942443174en_US
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-1942443174&selection=ref&src=s&origin=recordpageen_US
dc.identifier.volume325en_US
dc.identifier.issue2en_US
dc.identifier.spage124en_US
dc.identifier.epage133en_US
dc.identifier.isiWOS:000221210600006-
dc.publisher.placeNetherlandsen_US
dc.identifier.scopusauthoridXu, S=7404438591en_US
dc.identifier.scopusauthoridLam, J=7201973414en_US
dc.identifier.scopusauthoridHo, DWC=7402971938en_US
dc.identifier.scopusauthoridZou, Y=7402166773en_US

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats