testwithGaussian—RBFneuralnetworkandBPneuralnetwork,andtoboththeapproximationproperties,generalizationability,theconvergencerate,theerrorandotheraspectsofthecomparison,theresultsshowthattheGaussian—RBFneuralnetworknotonlydesigncomfortablyandhaveafastertrainingspeed,butalsocanachievebetterapproximationresults.
Finally,weconstructedamodelbasedonGaussian-RBFneuralnetworkandforecastChina’Sstockpriceusingthemodel.Andthroughthe300tradingdaysofdataoftheShanghaiCompositeIndexfortheexperimenttotrainandpredict,wefoundthatGaussian-RBFneuralnetworkstockpredictionmodelthantheBPneuralnetworkpredictionmodelcangetarelativelybetterpredictioneffect.TheoreticalanalysisandexperimentresultshowthatthemethodofstockpredictionusingGaussian.RBFneuralnetworkiSfeasibleande伍cient.Ithasfavorableapplicableforeground.
KEYWORDSRBFNeuralnetwork,Gaussian—RBFNeuralnetwork,BPNeuralnetwork,Functionapproximation,StockpricepredictionIV
搜索“diyifanwen.net”或“第一范文网”即可找到本站免费阅读全部范文。收藏本站方便下次阅读,第一范文网,提供最新资格考试认证基于Gaussian型RBF神经网络的函数逼近与应用(7)全文阅读和word下载服务。
相关推荐: