幾類具變時(shí)滯的神經(jīng)網(wǎng)絡(luò)模型的動(dòng)力學(xué)研究.pdf

1、湖南大學(xué)碩士學(xué)位論文幾類具變時(shí)滯的神經(jīng)網(wǎng)絡(luò)模型的動(dòng)力學(xué)研究姓名：彭水軍申請(qǐng)學(xué)位級(jí)別：碩士專業(yè)：應(yīng)用數(shù)學(xué)指導(dǎo)教師：黃立宏2002.4.20AbstractThispaperiscomposedoffourchaptersInChapter1，weintroducethehistoricalbackgroundofproblemswhichwillbeinvestigatedandthemainworkofthispaperInChapte

2、r2，byusingMmatrixtheory，someanalysistechniquesandconstructingsuitableLyapunovfunctionals，weinvestigatetheconvergenceofsolutionsandtheexistenceanduniquenessofperiodicsolutionforsystem：P卜_@to卜掣小乃o“∥m叭”o’∞““以x(E)舊‘)一dJ(f)YA

3、‘)善6』f(‘)gj(而(‘))蚤9F(‘)gj(xi(t‘Yji(‘)))Jj(‘)，whereand垂arethepropagationalsignalfunctionsdefinedonRSeveralsufficientconditionsguaranteeingtheneuralexponentialstabilityaswellastheexistenceandstabilityofperiodicsolutionofth

4、eneuralnetworkareobtainedTheglobalasymptoticallystabilityofthecorrespondingneuralnetworkmodelswithconstantdelaysandcoefficientsisstudiedtooOurresultsimproveandgeneralizesomeknownresultsInChapter3，theperiodicoscillatoryso

5、lutionsandtheglobalstabilityarestudiedforaclassofcontinuousbi—directionalassociativememoryneuralnetworkmodelswithvariabledelays，andsomesimpleandnewsufficientconditionsaregivenensuringglobalexponentialstabilityandtheexist

6、enceofperiodicsolutionsoftheneuralneworkTheseresultshaveimportantleadingsignificanceinthedesignandapplicationsofglobalexponentialstableBAMnetworksandperiodicoscillatoryKeywords：neuralnetworks；bi—directionalassociativemem