简介:将分支前馈神经网络(BFNN)运用于数字字符的模式识别问题中,其某些性能优于标准反向传播(BP)网络。BFNN的隐层神经元与输出神经元之间为分组对应关系,采用的学习算法与标准BP算法类似。BFNN可以根据样本的可分性构建最适宜的网络结构。在对大规模、分类复杂的样本进行识别时,性能优于标准BP网络。
简介:[篇名]CFDmodellingforcontrolofachemicalwasterotarykilnincinerator,[篇名]ComfortablepowerassistcontrolmethodforwalkingaidbyHAL-3,[篇名]Controlofgasolinedirectinjectionenginesusingtorquefeedback:asimulationstudy,[篇名]DecentralizedcontrolofatowercraneforUp-and-downandrotationaldirectionsusinggain-scheduledcontrolconsideringvaryingioad-ropelength,[篇名]Delay-awarepredictionfordecouplingofmultivariablecontrolsystems,[篇名]Designofcomputercontrolledcombustionengines,[篇名]DisturbanceRejectionControlbasedonAdaptiveIdentificationofTransferCharacteristicsfromAccelerationSensorforHardDiskDriveSystem,[篇名]Drift-andparameter-compensatedfluxestimatorforpersistentzero-stator-frequencyoperationofsensorless-controlledinductionmotors。