幾類神經網絡的全局指數穩(wěn)定性——泛函微分方程在神經網絡中的應用.pdf

1、Y828552∞————一№⑧研究生學位論文幾類神經網絡的全局指數穩(wěn)定性——泛函微分方程在神經網絡中自蛙用㈨g割顯里揖目螄hg———二￡——J整—』址——————一q镕監(jiān)Ⅻ亟土々業(yè)名％基園塾雯蝴月M墊堡壘且墨目靴授干日1—一——中國海洋大學Theglobalexponentialstabilityofseveralkindsofneuralnetworkstheapplicationsoffunctionaldifferentialeq

2、uationinneuralnetworksAbstractDuetothebroadspectrumofapplicationsinoptimization，signalprocessing，imageprocessing，solvingnonlinearalgebraicequation，patternrecognition，associativememoriesandSOon，theartfficialneuralnetworks

3、(ANN)havebeenfullydevelopedBecausethefunctionsininformationprocessingisdeterminedbythedynamicqualityoftheartificialneuralnetworks，itisnecessarytoinvestigatedthedynamicqualitiessuchasstability，oscillation，bifurcationandch

4、aosandSOonEspecially，intheapplicationsofoptimization，neuralcontrol，signalprocessingandpatternrecognition，theglobalasymptoticstabifityhasbecomethecoreproblemintheresearchinordertoavoidthespuriousresponseorlocalminimaInthe

5、realizationofelectronicneuralnetworks，timedelaysarelikelytobepresentduetothefiniteswitchingspeedofamplifiers，whichwillaffectthestabilityandleadtotheoscillationandthereforeinfluencethefunctionoftheartificialneuralnetworks

6、So，thethedynamicbehaviorofthetwokindsofANNmodelswithdelaysandwithoutdelayshavebeeninvestigatedinthisthesisThefundamentalproblemsoftheANNdynamicmodelsarethefollowing：1theexistenceofequihbrium；2theattractivity；3thestabilit

7、yInthisthesisthefeasiblecriteriaofseveralANNstocriticizeexistenceoftheuniqueglobalexponentialstableequilibriumInthisthesis，therefor，anewmethodofanalyzingthegloballyexponentialstabilityofHopfieldNeuralNetworksispresentedi

8、nchapter1，andthecriteriumofthegloballyexponentialstabilityofBidirectionalAssociativeMemoryNeu—ralNetworkswithVaryingTimeDelaysisalsoacquiredinchapter2Besides，anewlemmaabouttheHaianayDifferentialInequalityisobtainedandane