- Analysis of the dynamical behavior of a feedback

- Analysis of the dynamical behavior of a feedback

ID:40254075

大小:2.41 MB

页数:9页

时间:2019-07-29

- Analysis of the dynamical behavior of a feedback_第1页
- Analysis of the dynamical behavior of a feedback_第2页
- Analysis of the dynamical behavior of a feedback_第3页
- Analysis of the dynamical behavior of a feedback_第4页
- Analysis of the dynamical behavior of a feedback_第5页
资源描述:

《- Analysis of the dynamical behavior of a feedback》由会员上传分享,免费在线阅读,更多相关内容在学术论文-天天文库

1、ARTICLEINPRESSNeurocomputing71(2008)486–494www.elsevier.com/locate/neucomAnalysisofthedynamicalbehaviorofafeedbackauto-associativememoryMahmoodAmiri,SohrabSaeb,MohammadJavadYazdanpanah,S.AliSeyyedsalehiFacultyofBiomedicalEngineering,AmirkabirUniversityofTechnology(TehranPolytechnic),424Ha

2、fezAve,Tehran15875-4413,IranAvailableonline9October2007AbstractThedynamicalbehaviorandthestabilitypropertiesoffixedpointsinafeedbackauto-associativememoryareinvestigated.Theproposedstructureencompassesamulti-layerperceptron(MLP)andafeedbackconnectionthatlinksinputandoutputlayersthroughdelay

3、elements.TheMLPisinitiallytrainedsothatitmapsthetrainingpatternsintothemselvesasanauto-associativememory.Thefeedbackconnectionisthenestablishedinordertomakethefeedbackauto-associativememory.Wederivesomeexplicitequationsbasedonthetheoryofdynamicalsystems,whichrelatethestabilitypropertiesoffi

4、xedpointstothenetworkparametervalues.Wethenperformsomecasestudiesforthepurposeofperformancecomparisonsbetweentheproposedmodelandaself-feedbackneuralnetwork(SFNN)asanassociativememory.Severalsimulationsareprovidedtoverifythatnotonlyourmodelneedsmuchfewerneuronstostorenumerousstablefixedpoint

5、s,butalsoitisabletolearnasymmetricarrangementoffixedpoints,whereastheSFNNmodelislimitedtoorthogonalarrangements.r2007ElsevierB.V.Allrightsreserved.Keywords:Feedbackauto-associativememory;Stabilityanalysis;Fixedpoints1.Introductionequilibriumpointofthenetwork.Furthermore,theequilibriacorresp

6、ondingtothememoryvectorshavetoUtilizedinawidespectrumofapplications,neuralbeasymptoticallystable,i.e.,theyshouldbeattractivenetworkshavebeenwidelystudiedinrecentyears[8,15,17].equilibriumpointsorattractors[3].IntheconventionalstructureofanartificialneuralAsNNsstoreasetofdesiredpatternsassta

7、blenetwork,aneuronreceivesitsinputeitherfromotherequilibriumpointssuchthatthestoredinformationcanneuronsorfromexternalinputs(inputvector).Aweightedberetrievedifsufficientdataisprovidedinaninputsumoftheseinputsconstitutestheargumentofafixedpattern.Inotherwords,As

当前文档最多预览五页,下载文档查看全文

此文档下载收益归作者所有

当前文档最多预览五页,下载文档查看全文
温馨提示:
1. 部分包含数学公式或PPT动画的文件,查看预览时可能会显示错乱或异常,文件下载后无此问题,请放心下载。
2. 本文档由用户上传,版权归属用户,天天文库负责整理代发布。如果您对本文档版权有争议请及时联系客服。
3. 下载前请仔细阅读文档内容,确认文档内容符合您的需求后进行下载,若出现内容与标题不符可向本站投诉处理。
4. 下载文档时可能由于网络波动等原因无法下载或下载错误,付费完成后未能成功下载的用户请联系客服处理。