File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Stability analysis of discrete-time recurrent neural networks with stochastic delay

TitleStability analysis of discrete-time recurrent neural networks with stochastic delay
Authors
KeywordsDelay dependence
Discrete-time recurrent neural networks (RNNs)
Mean square stability
Stochastic time delay
Issue Date2009
PublisherIEEE.
Citation
Ieee Transactions On Neural Networks, 2009, v. 20 n. 8, p. 1330-1339 How to Cite?
AbstractThis paper is concerned with the stability analysis of discrete-time recurrent neural networks (RNNs) with time delays as random variables drawn from some probability distribution. By introducing the variation probability of the time delay, a common delayed discrete-time RNN system is transformed into one with stochastic parameters. Improved conditions for the mean square stability of these systems are obtained by employing new Lyapunov functions and novel techniques are used to achieve delay dependence. The merit of the proposed conditions lies in its reduced conservatism, which is made possible by considering not only the range of the time delays, but also the variation probability distribution. A numerical example is provided to show the advantages of the proposed conditions. © 2009 IEEE.
Persistent Identifierhttp://hdl.handle.net/10722/124891
ISSN
2011 Impact Factor: 2.952
ISI Accession Number ID
Funding AgencyGrant Number
National Natural Science Foundation of China60825303
60834003
973 Project2009CB320600
Heilongjiang Outstanding Youth Science FundJC200809
Research Grants CouncilHKU 7031/06P
Funding Information:

Manuscript received September 02, 2008; revised December 06, 2008 and March 01, 2009; accepted March 24, 2009. First published July 14, 2009; current version published August 05, 2009. This work was supported in part by the National Natural Science Foundation of China under Grants 60825303 and 60834003, by 973 Project (2009CB320600), by the Heilongjiang Outstanding Youth Science Fund (JC200809), and by the Research Grants Council under code HKU 7031/06P.

References
Grants

 

DC FieldValueLanguage
dc.contributor.authorZhao, Yen_HK
dc.contributor.authorGao, Hen_HK
dc.contributor.authorLam, Jen_HK
dc.contributor.authorChen, Ken_HK
dc.date.accessioned2010-10-31T10:59:50Z-
dc.date.available2010-10-31T10:59:50Z-
dc.date.issued2009en_HK
dc.identifier.citationIeee Transactions On Neural Networks, 2009, v. 20 n. 8, p. 1330-1339en_HK
dc.identifier.issn1045-9227en_HK
dc.identifier.urihttp://hdl.handle.net/10722/124891-
dc.description.abstractThis paper is concerned with the stability analysis of discrete-time recurrent neural networks (RNNs) with time delays as random variables drawn from some probability distribution. By introducing the variation probability of the time delay, a common delayed discrete-time RNN system is transformed into one with stochastic parameters. Improved conditions for the mean square stability of these systems are obtained by employing new Lyapunov functions and novel techniques are used to achieve delay dependence. The merit of the proposed conditions lies in its reduced conservatism, which is made possible by considering not only the range of the time delays, but also the variation probability distribution. A numerical example is provided to show the advantages of the proposed conditions. © 2009 IEEE.en_HK
dc.languageengen_HK
dc.publisherIEEE.-
dc.relation.ispartofIEEE Transactions on Neural Networksen_HK
dc.rightsIEEE Transactions on Neural Networks. Copyright © IEEE.-
dc.rightsCreative Commons: Attribution 3.0 Hong Kong License-
dc.rights©2009 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.-
dc.subjectDelay dependenceen_HK
dc.subjectDiscrete-time recurrent neural networks (RNNs)en_HK
dc.subjectMean square stabilityen_HK
dc.subjectStochastic time delayen_HK
dc.titleStability analysis of discrete-time recurrent neural networks with stochastic delayen_HK
dc.typeArticleen_HK
dc.identifier.openurlhttp://library.hku.hk:4550/resserv?sid=HKU:IR&issn=1045-9227&volume=20&issue=8&spage=1330&epage=1339&date=2009&atitle=Stability+analysis+of+discrete-time+recurrent+neural+networks+with+stochastic+delay-
dc.identifier.emailLam, J:james.lam@hku.hken_HK
dc.identifier.authorityLam, J=rp00133en_HK
dc.description.naturepublished_or_final_version-
dc.identifier.doi10.1109/TNN.2009.2023379en_HK
dc.identifier.scopuseid_2-s2.0-68949212851en_HK
dc.identifier.hkuros179595en_HK
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-68949212851&selection=ref&src=s&origin=recordpageen_HK
dc.identifier.volume20en_HK
dc.identifier.issue8en_HK
dc.identifier.spage1330en_HK
dc.identifier.epage1339en_HK
dc.identifier.isiWOS:000268756800010-
dc.publisher.placeUnited Statesen_HK
dc.relation.projectDecay rate estimation and synthesis of functional differential systems via semi-definite programming-
dc.identifier.scopusauthoridZhao, Y=7406634118en_HK
dc.identifier.scopusauthoridGao, H=7402971422en_HK
dc.identifier.scopusauthoridLam, J=7201973414en_HK
dc.identifier.scopusauthoridChen, K=7410240709en_HK

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats