Robust stability analysis of quaternion-valued neural networks with time delays and parameter uncertainties

This paper addresses the problem of robust stability for quaternion-valued neural networks (QVNNs) with leakage delay, discrete delay and parameter uncertainties. Based on Homeomorphic mapping theorem and Lyapunov theorem, via modulus inequality technique of quaternions, some sufficient conditions o...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Neural networks 2017-07, Vol.91, p.55-65
Hauptverfasser: Chen, Xiaofeng, Li, Zhongshan, Song, Qiankun, Hu, Jin, Tan, Yuanshun
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 65
container_issue
container_start_page 55
container_title Neural networks
container_volume 91
creator Chen, Xiaofeng
Li, Zhongshan
Song, Qiankun
Hu, Jin
Tan, Yuanshun
description This paper addresses the problem of robust stability for quaternion-valued neural networks (QVNNs) with leakage delay, discrete delay and parameter uncertainties. Based on Homeomorphic mapping theorem and Lyapunov theorem, via modulus inequality technique of quaternions, some sufficient conditions on the existence, uniqueness, and global robust stability of the equilibrium point are derived for the delayed QVNNs with parameter uncertainties. Furthermore, as direct applications of these results, several sufficient conditions are obtained for checking the global robust stability of QVNNs without leakage delay as well as complex-valued neural networks (CVNNs) with both leakage and discrete delays. Finally, two numerical examples are provided to substantiate the effectiveness of the proposed results.
doi_str_mv 10.1016/j.neunet.2017.04.006
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_1899117732</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0893608017300862</els_id><sourcerecordid>1899117732</sourcerecordid><originalsourceid>FETCH-LOGICAL-c362t-1b5c3730e4938cad1133820d1d12c99bbf07380638114bdb4c4edb9ec13790623</originalsourceid><addsrcrecordid>eNp9kE1LXDEUhoNUdLT9ByJZdnOvOUl6b7IRRNoqCIK065CPMzTj_RiTXGX-fTOMdtnVu3ne83IeQi6AtcCgu9q0Ey4TlpYz6FsmW8a6I7IC1euG94p_IiumtGg6ptgpOct5wyqhpDghp1xJLQVXK_L8NLslF5qLdXGIZUftZIddjpnOa_qy2IJpivPUvNphwUDrZrJDjfI2p-dM32L5Q0sckQYc7C7XeqBbm-yItUmXyWMqNk4lYv5Mjtd2yPjlPc_J7x_ff93eNQ-PP-9vbx4aLzpeGnDfvOgFQ6mF8jYACKE4CxCAe62dW7NeKNYJBSBdcNJLDE6jB9Fr1nFxTr4e7m7T_LJgLmaM2eMw2AnnJRtQWgP0vdij8oD6NOeccG22KY427Qwws9dsNuag2ew1GyZNlVhrl-8Lixsx_Ct9eK3A9QHA-udrxGSyj1hlhJjQFxPm-P-Fvx2MkmQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1899117732</pqid></control><display><type>article</type><title>Robust stability analysis of quaternion-valued neural networks with time delays and parameter uncertainties</title><source>MEDLINE</source><source>ScienceDirect Journals (5 years ago - present)</source><creator>Chen, Xiaofeng ; Li, Zhongshan ; Song, Qiankun ; Hu, Jin ; Tan, Yuanshun</creator><creatorcontrib>Chen, Xiaofeng ; Li, Zhongshan ; Song, Qiankun ; Hu, Jin ; Tan, Yuanshun</creatorcontrib><description>This paper addresses the problem of robust stability for quaternion-valued neural networks (QVNNs) with leakage delay, discrete delay and parameter uncertainties. Based on Homeomorphic mapping theorem and Lyapunov theorem, via modulus inequality technique of quaternions, some sufficient conditions on the existence, uniqueness, and global robust stability of the equilibrium point are derived for the delayed QVNNs with parameter uncertainties. Furthermore, as direct applications of these results, several sufficient conditions are obtained for checking the global robust stability of QVNNs without leakage delay as well as complex-valued neural networks (CVNNs) with both leakage and discrete delays. Finally, two numerical examples are provided to substantiate the effectiveness of the proposed results.</description><identifier>ISSN: 0893-6080</identifier><identifier>EISSN: 1879-2782</identifier><identifier>DOI: 10.1016/j.neunet.2017.04.006</identifier><identifier>PMID: 28494328</identifier><language>eng</language><publisher>United States: Elsevier Ltd</publisher><subject>Computer Simulation - standards ; Discrete delay ; Global robust stability ; Leakage delay ; Linear matrix inequality ; Modulus inequality technique ; Neural Networks (Computer) ; Quaternion-valued neural networks ; Time Factors ; Uncertainty</subject><ispartof>Neural networks, 2017-07, Vol.91, p.55-65</ispartof><rights>2017</rights><rights>Published by Elsevier Ltd.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c362t-1b5c3730e4938cad1133820d1d12c99bbf07380638114bdb4c4edb9ec13790623</citedby><cites>FETCH-LOGICAL-c362t-1b5c3730e4938cad1133820d1d12c99bbf07380638114bdb4c4edb9ec13790623</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://dx.doi.org/10.1016/j.neunet.2017.04.006$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>314,778,782,3539,27911,27912,45982</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/28494328$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Chen, Xiaofeng</creatorcontrib><creatorcontrib>Li, Zhongshan</creatorcontrib><creatorcontrib>Song, Qiankun</creatorcontrib><creatorcontrib>Hu, Jin</creatorcontrib><creatorcontrib>Tan, Yuanshun</creatorcontrib><title>Robust stability analysis of quaternion-valued neural networks with time delays and parameter uncertainties</title><title>Neural networks</title><addtitle>Neural Netw</addtitle><description>This paper addresses the problem of robust stability for quaternion-valued neural networks (QVNNs) with leakage delay, discrete delay and parameter uncertainties. Based on Homeomorphic mapping theorem and Lyapunov theorem, via modulus inequality technique of quaternions, some sufficient conditions on the existence, uniqueness, and global robust stability of the equilibrium point are derived for the delayed QVNNs with parameter uncertainties. Furthermore, as direct applications of these results, several sufficient conditions are obtained for checking the global robust stability of QVNNs without leakage delay as well as complex-valued neural networks (CVNNs) with both leakage and discrete delays. Finally, two numerical examples are provided to substantiate the effectiveness of the proposed results.</description><subject>Computer Simulation - standards</subject><subject>Discrete delay</subject><subject>Global robust stability</subject><subject>Leakage delay</subject><subject>Linear matrix inequality</subject><subject>Modulus inequality technique</subject><subject>Neural Networks (Computer)</subject><subject>Quaternion-valued neural networks</subject><subject>Time Factors</subject><subject>Uncertainty</subject><issn>0893-6080</issn><issn>1879-2782</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2017</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><recordid>eNp9kE1LXDEUhoNUdLT9ByJZdnOvOUl6b7IRRNoqCIK065CPMzTj_RiTXGX-fTOMdtnVu3ne83IeQi6AtcCgu9q0Ey4TlpYz6FsmW8a6I7IC1euG94p_IiumtGg6ptgpOct5wyqhpDghp1xJLQVXK_L8NLslF5qLdXGIZUftZIddjpnOa_qy2IJpivPUvNphwUDrZrJDjfI2p-dM32L5Q0sckQYc7C7XeqBbm-yItUmXyWMqNk4lYv5Mjtd2yPjlPc_J7x_ff93eNQ-PP-9vbx4aLzpeGnDfvOgFQ6mF8jYACKE4CxCAe62dW7NeKNYJBSBdcNJLDE6jB9Fr1nFxTr4e7m7T_LJgLmaM2eMw2AnnJRtQWgP0vdij8oD6NOeccG22KY427Qwws9dsNuag2ew1GyZNlVhrl-8Lixsx_Ct9eK3A9QHA-udrxGSyj1hlhJjQFxPm-P-Fvx2MkmQ</recordid><startdate>201707</startdate><enddate>201707</enddate><creator>Chen, Xiaofeng</creator><creator>Li, Zhongshan</creator><creator>Song, Qiankun</creator><creator>Hu, Jin</creator><creator>Tan, Yuanshun</creator><general>Elsevier Ltd</general><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope></search><sort><creationdate>201707</creationdate><title>Robust stability analysis of quaternion-valued neural networks with time delays and parameter uncertainties</title><author>Chen, Xiaofeng ; Li, Zhongshan ; Song, Qiankun ; Hu, Jin ; Tan, Yuanshun</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c362t-1b5c3730e4938cad1133820d1d12c99bbf07380638114bdb4c4edb9ec13790623</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2017</creationdate><topic>Computer Simulation - standards</topic><topic>Discrete delay</topic><topic>Global robust stability</topic><topic>Leakage delay</topic><topic>Linear matrix inequality</topic><topic>Modulus inequality technique</topic><topic>Neural Networks (Computer)</topic><topic>Quaternion-valued neural networks</topic><topic>Time Factors</topic><topic>Uncertainty</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Chen, Xiaofeng</creatorcontrib><creatorcontrib>Li, Zhongshan</creatorcontrib><creatorcontrib>Song, Qiankun</creatorcontrib><creatorcontrib>Hu, Jin</creatorcontrib><creatorcontrib>Tan, Yuanshun</creatorcontrib><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><jtitle>Neural networks</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Chen, Xiaofeng</au><au>Li, Zhongshan</au><au>Song, Qiankun</au><au>Hu, Jin</au><au>Tan, Yuanshun</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Robust stability analysis of quaternion-valued neural networks with time delays and parameter uncertainties</atitle><jtitle>Neural networks</jtitle><addtitle>Neural Netw</addtitle><date>2017-07</date><risdate>2017</risdate><volume>91</volume><spage>55</spage><epage>65</epage><pages>55-65</pages><issn>0893-6080</issn><eissn>1879-2782</eissn><abstract>This paper addresses the problem of robust stability for quaternion-valued neural networks (QVNNs) with leakage delay, discrete delay and parameter uncertainties. Based on Homeomorphic mapping theorem and Lyapunov theorem, via modulus inequality technique of quaternions, some sufficient conditions on the existence, uniqueness, and global robust stability of the equilibrium point are derived for the delayed QVNNs with parameter uncertainties. Furthermore, as direct applications of these results, several sufficient conditions are obtained for checking the global robust stability of QVNNs without leakage delay as well as complex-valued neural networks (CVNNs) with both leakage and discrete delays. Finally, two numerical examples are provided to substantiate the effectiveness of the proposed results.</abstract><cop>United States</cop><pub>Elsevier Ltd</pub><pmid>28494328</pmid><doi>10.1016/j.neunet.2017.04.006</doi><tpages>11</tpages></addata></record>
fulltext fulltext
identifier ISSN: 0893-6080
ispartof Neural networks, 2017-07, Vol.91, p.55-65
issn 0893-6080
1879-2782
language eng
recordid cdi_proquest_miscellaneous_1899117732
source MEDLINE; ScienceDirect Journals (5 years ago - present)
subjects Computer Simulation - standards
Discrete delay
Global robust stability
Leakage delay
Linear matrix inequality
Modulus inequality technique
Neural Networks (Computer)
Quaternion-valued neural networks
Time Factors
Uncertainty
title Robust stability analysis of quaternion-valued neural networks with time delays and parameter uncertainties
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-15T20%3A58%3A14IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Robust%20stability%20analysis%20of%20quaternion-valued%20neural%20networks%20with%20time%20delays%20and%20parameter%20uncertainties&rft.jtitle=Neural%20networks&rft.au=Chen,%20Xiaofeng&rft.date=2017-07&rft.volume=91&rft.spage=55&rft.epage=65&rft.pages=55-65&rft.issn=0893-6080&rft.eissn=1879-2782&rft_id=info:doi/10.1016/j.neunet.2017.04.006&rft_dat=%3Cproquest_cross%3E1899117732%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=1899117732&rft_id=info:pmid/28494328&rft_els_id=S0893608017300862&rfr_iscdi=true