简介:ProfessorKowk-faiSo,theeditor-in-chiefofNeuralRegenerationResearch,hasbeennamedaFellowoftheNationalAcademyofInventors(NAI)ProfessorKwok-faiSo,DepartmentofOphthalmology,LiKaShing,FacultyofMedicine,TheUniversityofHongKong(HKU),hasbeennamedaFellowoftheNationalAcademyofInventors(NAI).
简介:Thispaperproposesanewneuralfuzzyinferencesystemthatmainlyconsistsoffourparts.Thefirstpartisabouthowtouseneuralnetworktoexpresstherelationwithinafuzzyrule.Thesecondpartisthesimplificationofthefirstpart,andexperimentsshowthatthesesimplificationswork.Onthecontrarytothesecondpart,thethirdpartistheenhancementofthefirstpartanditcanbeusedwhenthefirstpartcannotworkverywellinthefuzzyinferencealgorithm,whichwouldbeintroducedinthefourthpart.Finally,thefourthpart"neuralfuzzyinferencealgorithm"isbeenintroduced.Itcaninferencethenewmembershipfunctionoftheoutputbasedonpreviousfuzzyrules.Theaccuracyofthefuzzyinferencealgorithmisdependentonneuralnetworkgeneralizationability.Evenifthegeneralizationabilityoftheneuralnetworkweusedisgood,westillgetinaccurateresultssincethenewcomingrulemaynotberelatedtoanyofthepreviousrules.Experimentsshowthisalgorithmissuccessfulinsituationswhichsatisfytheseconditions.
简介:ThetypicalBDI(beliefdesireintention)modelofagentisnotefficientlycomputableandthestrictlogicexpressionisnoteasilyapplicabletotheAUV(autonomousunderwatervehicle)domainwithuncertainties.Inthispaper,anAUVfuzzyneuralBDImodelisproposed.Themodelisafuzzyneuralnetworkcomposedoffivelayers:input(beliefsanddesires),fuzzification,commitment,fuzzyintention,anddefuzzificationlayer.Inthemodel,thefuzzycommitmentrulesandneuralnetworkarecombinedtoformintentionsfrombeliefsanddesires.ThemodelisdemonstratedbysolvingPEG(pursuit-evasiongame),andthesimulationresultissatisfactory.
简介:NETWORKTELECOMmagazine,commencedpublicationin1999,isthenetwork&telecommunicationsindust0?sleadingpublicationinChina.specializinginthefieldofopticfibercommunications,accessnetwork,mobilecommunications,CATVnetwork,cablingsystemanddatacommunications;andhasestablisheditsrepuionbyacombinationofauthoritativeeditorialcontent,targetingackcuatlonofhigho.ualitycoveringtheentireChinaregiom
简介:TheEuropeanGeoparksNetworkwasestablishedinJune2000byfourregionsofdifferentEuropeanCountries--France,Germany,SpainandGreece--withsimilarnaturalandsocioeconomiccharacteristics.Thesefourregionsareruralareas,withaparticulargeologicalheritage,naturalbeautyandhighculturalpotential,allfacingproblemsofsloweconomicdevelopment,
简介:NETWORKTELECOMmagazinecommencedpublicationin1999,isthenetwork
简介:NETWORKTELECOMmagazineisthenetwork&telecommunicationsindustry'sleadingpublicationinChina,specializinginthefieldofopticfibercommunications,accessnetwork,mobilecommunications,CATVnetwork,cablingsystemanddatacommunications;andhasestablisheditsreputationbyacombinationofauthoritativeeditorialcontent,targetingacirculationofhighqualitycoveringtheentireChinaregion.
简介:TheBIONISnetworkwassetupinspring2002byProf.GeorgeJeronimidis,Prof.JulianVincentandPhilSheppard.Membershipisnowover300,withmembersfromacademiaandindustryinmorethan40countries.ThemissionofthenetworkistopromotetheapplicationofBiomimeticsinproductsandservicesanditsuseineducationandtraining.ItiscurrentlysupportedbySwedishBiomimetics3000?andhostedbytheUniversityofReading.
简介:Inthispaper,weproposetwoweightedlearningmethodsfortheconstructionofsinglehiddenlayerfeedforwardneuralnetworks.Bothmethodsincorporateweightedleastsquares.Ourideaistoallowthetraininginstancesnearertothequerytoofferbiggercontributionstotheestimatedoutput.Byminimizingtheweightedmeansquareerrorfunction,optimalnetworkscanbeobtained.Theresultsofanumberofexperimentsdemonstratetheeffectivenessofourproposedmethods.
简介:Inthispaper,weintroduceatypeofapproximationoperatorsofneuralnetworkswithsigmodalfunctionsoncompactintervals,andobtainthepointwiseanduniformestimatesoftheapproximation.Toimprovetheapproximationrate,wefurtherintroduceatypeofcombinationsofneuralnetworks.Moreover,weshowthatthederivativesoffunctionscanalsobesimultaneouslyapproximatedbythederivativesofthecombinations.Wealsoapplyourmethodtoconstructapproximationoperatorsofneuralnetworkswithsigmodalfunctionsoninfiniteintervals.