File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Stability analysis of static recurrent neural networks using delay-partitioning and projection

TitleStability analysis of static recurrent neural networks using delay-partitioning and projection
Authors
Issue Date2009
PublisherPergamon. The Journal's web site is located at http://www.elsevier.com/locate/neunet
Citation
Neural Networks, 2009, v. 22 n. 4, p. 343-347 How to Cite?
AbstractThis paper introduces an effective approach to studying the stability of recurrent neural networks with a time-invariant delay. By employing a new Lyapunov-Krasovskii functional form based on delay partitioning, novel delay-dependent stability criteria are established to guarantee the global asymptotic stability of static neural networks. These conditions are expressed in the framework of linear matrix inequalities, which can be verified easily by means of standard software. It is shown, by comparing with existing approaches, that the delay-partitioning projection approach can largely reduce the conservatism of the stability results. Finally, two examples are given to show the effectiveness of the theoretical results. © 2009 Elsevier Ltd. All rights reserved.
Persistent Identifierhttp://hdl.handle.net/10722/59127
ISSN
2015 Impact Factor: 3.216
2015 SCImago Journal Rankings: 1.629
ISI Accession Number ID
Funding AgencyGrant Number
RGC HKU 7031/06P
Funding Information:

The work in this paper was partially supported by RGC HKU 7031/06P.

References

 

DC FieldValueLanguage
dc.contributor.authorDu, Ben_HK
dc.contributor.authorLam, Jen_HK
dc.date.accessioned2010-05-31T03:43:20Z-
dc.date.available2010-05-31T03:43:20Z-
dc.date.issued2009en_HK
dc.identifier.citationNeural Networks, 2009, v. 22 n. 4, p. 343-347en_HK
dc.identifier.issn0893-6080en_HK
dc.identifier.urihttp://hdl.handle.net/10722/59127-
dc.description.abstractThis paper introduces an effective approach to studying the stability of recurrent neural networks with a time-invariant delay. By employing a new Lyapunov-Krasovskii functional form based on delay partitioning, novel delay-dependent stability criteria are established to guarantee the global asymptotic stability of static neural networks. These conditions are expressed in the framework of linear matrix inequalities, which can be verified easily by means of standard software. It is shown, by comparing with existing approaches, that the delay-partitioning projection approach can largely reduce the conservatism of the stability results. Finally, two examples are given to show the effectiveness of the theoretical results. © 2009 Elsevier Ltd. All rights reserved.en_HK
dc.languageengen_HK
dc.publisherPergamon. The Journal's web site is located at http://www.elsevier.com/locate/neuneten_HK
dc.relation.ispartofNeural Networksen_HK
dc.subject.meshAlgorithmsen_HK
dc.subject.meshArtificial Intelligenceen_HK
dc.subject.meshComputer Simulationen_HK
dc.subject.meshForecastingen_HK
dc.subject.meshLinear Modelsen_HK
dc.subject.meshMathematicsen_HK
dc.subject.meshNeural Networks (Computer)en_HK
dc.subject.meshPattern Recognition, Automateden_HK
dc.subject.meshSoftwareen_HK
dc.subject.meshTime Factorsen_HK
dc.titleStability analysis of static recurrent neural networks using delay-partitioning and projectionen_HK
dc.typeArticleen_HK
dc.identifier.openurlhttp://library.hku.hk:4550/resserv?sid=HKU:IR&issn=0893-6080&volume=22&issue=4&spage=343&epage=347&date=2009&atitle=Stability+analysis+of+static+recurrent+neural+networks+using+delay-partitioning+and+projectionen_HK
dc.identifier.emailLam, J:james.lam@hku.hken_HK
dc.identifier.authorityLam, J=rp00133en_HK
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1016/j.neunet.2009.03.005en_HK
dc.identifier.pmid19372029-
dc.identifier.scopuseid_2-s2.0-67349207087en_HK
dc.identifier.hkuros164266en_HK
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-67349207087&selection=ref&src=s&origin=recordpageen_HK
dc.identifier.volume22en_HK
dc.identifier.issue4en_HK
dc.identifier.spage343en_HK
dc.identifier.epage347en_HK
dc.identifier.isiWOS:000266998500003-
dc.publisher.placeUnited Kingdomen_HK
dc.identifier.scopusauthoridDu, B=25823711000en_HK
dc.identifier.scopusauthoridLam, J=7201973414en_HK
dc.identifier.citeulike4821800-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats