File Download
  • No File Attached
 
Links for fulltext
(May Require Subscription)
 
Supplementary

Article: Exponential stability of high-order bidirectional associative memory neural networks with time delays
  • Basic View
  • Metadata View
  • XML View
TitleExponential stability of high-order bidirectional associative memory neural networks with time delays
 
AuthorsCao, J2
Liang, J2
Lam, J1
 
KeywordsBidirectional Associative Memory (Bam)
Exponential Stability
High-Order Neural Networks
Linear Matrix Inequality
Lyapunov Functional
Time Delays
 
Issue Date2004
 
PublisherElsevier BV. The Journal's web site is located at http://www.elsevier.com/locate/physd
 
CitationPhysica D: Nonlinear Phenomena, 2004, v. 199 n. 3-4, p. 425-436 [How to Cite?]
DOI: http://dx.doi.org/10.1016/j.physd.2004.09.012
 
AbstractIn this paper, exponential stability is studied for a class of high-order bidirectional associative memory (BAM) neural networks with time delays. By employing the linear matrix inequality (LMI) and the Lyapunov functional methods, several sufficient conditions are obtained for ensuring the system to be globally exponentially stable. Two illustrative examples are also given in the end of this paper to show the effectiveness of our results. © 2004 Elsevier B.V. All rights reserved.
 
ISSN0167-2789
2012 Impact Factor: 1.669
2012 SCImago Journal Rankings: 0.976
 
DOIhttp://dx.doi.org/10.1016/j.physd.2004.09.012
 
ISI Accession Number IDWOS:000226128200008
 
ReferencesReferences in Scopus
 
DC FieldValue
dc.contributor.authorCao, J
 
dc.contributor.authorLiang, J
 
dc.contributor.authorLam, J
 
dc.date.accessioned2012-08-08T08:43:41Z
 
dc.date.available2012-08-08T08:43:41Z
 
dc.date.issued2004
 
dc.description.abstractIn this paper, exponential stability is studied for a class of high-order bidirectional associative memory (BAM) neural networks with time delays. By employing the linear matrix inequality (LMI) and the Lyapunov functional methods, several sufficient conditions are obtained for ensuring the system to be globally exponentially stable. Two illustrative examples are also given in the end of this paper to show the effectiveness of our results. © 2004 Elsevier B.V. All rights reserved.
 
dc.description.natureLink_to_subscribed_fulltext
 
dc.identifier.citationPhysica D: Nonlinear Phenomena, 2004, v. 199 n. 3-4, p. 425-436 [How to Cite?]
DOI: http://dx.doi.org/10.1016/j.physd.2004.09.012
 
dc.identifier.doihttp://dx.doi.org/10.1016/j.physd.2004.09.012
 
dc.identifier.epage436
 
dc.identifier.isiWOS:000226128200008
 
dc.identifier.issn0167-2789
2012 Impact Factor: 1.669
2012 SCImago Journal Rankings: 0.976
 
dc.identifier.issue3-4
 
dc.identifier.scopuseid_2-s2.0-10644236158
 
dc.identifier.spage425
 
dc.identifier.urihttp://hdl.handle.net/10722/156723
 
dc.identifier.volume199
 
dc.languageeng
 
dc.publisherElsevier BV. The Journal's web site is located at http://www.elsevier.com/locate/physd
 
dc.publisher.placeNetherlands
 
dc.relation.ispartofPhysica D: Nonlinear Phenomena
 
dc.relation.referencesReferences in Scopus
 
dc.subjectBidirectional Associative Memory (Bam)
 
dc.subjectExponential Stability
 
dc.subjectHigh-Order Neural Networks
 
dc.subjectLinear Matrix Inequality
 
dc.subjectLyapunov Functional
 
dc.subjectTime Delays
 
dc.titleExponential stability of high-order bidirectional associative memory neural networks with time delays
 
dc.typeArticle
 
<?xml encoding="utf-8" version="1.0"?>
<item><contributor.author>Cao, J</contributor.author>
<contributor.author>Liang, J</contributor.author>
<contributor.author>Lam, J</contributor.author>
<date.accessioned>2012-08-08T08:43:41Z</date.accessioned>
<date.available>2012-08-08T08:43:41Z</date.available>
<date.issued>2004</date.issued>
<identifier.citation>Physica D: Nonlinear Phenomena, 2004, v. 199 n. 3-4, p. 425-436</identifier.citation>
<identifier.issn>0167-2789</identifier.issn>
<identifier.uri>http://hdl.handle.net/10722/156723</identifier.uri>
<description.abstract>In this paper, exponential stability is studied for a class of high-order bidirectional associative memory (BAM) neural networks with time delays. By employing the linear matrix inequality (LMI) and the Lyapunov functional methods, several sufficient conditions are obtained for ensuring the system to be globally exponentially stable. Two illustrative examples are also given in the end of this paper to show the effectiveness of our results. &#169; 2004 Elsevier B.V. All rights reserved.</description.abstract>
<language>eng</language>
<publisher>Elsevier BV. The Journal&apos;s web site is located at http://www.elsevier.com/locate/physd</publisher>
<relation.ispartof>Physica D: Nonlinear Phenomena</relation.ispartof>
<subject>Bidirectional Associative Memory (Bam)</subject>
<subject>Exponential Stability</subject>
<subject>High-Order Neural Networks</subject>
<subject>Linear Matrix Inequality</subject>
<subject>Lyapunov Functional</subject>
<subject>Time Delays</subject>
<title>Exponential stability of high-order bidirectional associative memory neural networks with time delays</title>
<type>Article</type>
<description.nature>Link_to_subscribed_fulltext</description.nature>
<identifier.doi>10.1016/j.physd.2004.09.012</identifier.doi>
<identifier.scopus>eid_2-s2.0-10644236158</identifier.scopus>
<relation.references>http://www.scopus.com/mlt/select.url?eid=2-s2.0-10644236158&amp;selection=ref&amp;src=s&amp;origin=recordpage</relation.references>
<identifier.volume>199</identifier.volume>
<identifier.issue>3-4</identifier.issue>
<identifier.spage>425</identifier.spage>
<identifier.epage>436</identifier.epage>
<identifier.isi>WOS:000226128200008</identifier.isi>
<publisher.place>Netherlands</publisher.place>
</item>
Author Affiliations
  1. The University of Hong Kong
  2. Southeast University