简介：模糊系统具有容易被人理解的表达能力,神经网络则具有极强的自适应学习能力。本文将模糊逻辑控制技术和神经网络技术相结合,给出了一种比单独模糊系统或单独的神经网络系统性能更好的基于模糊RBF神经网络自整定的拥塞控制方法。该方法根据路由器中队列长度的变化来调整数据包的丢弃概率,从而使路由器的队列长度稳定在一期望值附近。仿真结果表明,该算法具有较强的鲁棒性,更短的调节时间。

简介：为了提高使用精度，研究了某型号MEMS陀螺仪的随机漂移模型。采用游程检验法分析了该陀螺仪随机漂移数据的平稳性，并根据该漂移为均值非平稳、方差平稳的随机过程的结论，采用梯度径向基（RBF）神经网络对漂移数据进行了建模。实验结果表明：相比经典RBF网络模型而言，这种方法建立的模型能更好地描则EMs陀螺仪的漂移特；相对于季节时间序列模型而言，其补偿效果提高了大约15％。

简介：

简介：Dynamicnodecreationandfastlearningalgorithmforahybridfeedforwardneuralnetwork.Flight-pathanglecontrolvianeuro-adaptiveBackstepping.Locallearningframeworkforhandwrittencharacterrecognition.Maximizingmarginsofmultilayerneuralnetworks.ModularnetworkSOMself-orgmlizingmapofasystemsgroupinfunctionspace.

简介：

简介：

简介：ApplicationoftheRTNNmodelforasystemidentification,predictionandcontrol；AssociativeMemoryUsingRatioRuleforMulti-valuedPatternAssociation；Batch-to-BatchModel-basedIterativeOptimisationControlforaBatchPolymerisationReactor；BehaviouralPlasticityinAutonomousAgents:AComparisonbetweenTwoTypesofController；ChannelEqualizationUsingComplex-ValuedRecurrentNeuralNetworks；Classificationofnaturallanguagesentencesusingneuralnetworks；Combiningarecurrentneuralnetworkandtheoutputregulationtheoryfornon-linearadaptivecontrol。

简介：

简介：ConfigurablemultilayerCNN-UMemulatoronFPGA；Cortically-inspiredVisualProcessingwithaFourLayerCellularNeuralNetwork；Effectofcouplingresistorsonsteadypatternsincoupledoscillatornetworks；Exponentialconvergenceestimatesforneuralnetworkswithmultipledelays；FEATUREEXTRACTIONINEPILEPSYUSINGACELLULARNEURALNETWORKBASEDDEVICEFIRSTRESULTS；FurtherResultsontheStabilityofDelayedCellularNeuralNetworks；Globalstabilityanalysisindelayedcellularneuralnetworks；ImageedgedetectionusingadaptivemorphologyMeyerWavelet-CNN。

简介：

简介：PredictionoftheDimensionalChangesduringSinteringusingBackpropagationAlgorithm，Predictionofthenextstockpriceusingneuralnetwork-extractionthefeaturetopredictnextstockpricebyfiltering，Pulsemodeneuronwithpiecewiselinearactivationfunction，Remarksonmultilayerneuralnetworksinvolvingchaosneurons……

简介：

简介：人工神经网络是另外一种计算模式。冯·诺依曼机器是以．人类信息处理过程的处理/记忆的抽象为基础的，而神经网络是以动物大脑并行处理的体系结构为基础的。这是一种多处理器的计算机系统，由大量简单的处理单元高度互连，简单分级通信，以及在各单元之间进行适应性交互作用组成。

简介：

简介：

简介：AnewapproachtogenerateAself-organizingfuzzyneuralnetworkmodel.Anonlinearcombiningforecastmethodbasedonfuzzyneuralnetwork.Anovelclustermethodinfrizzyneuralnetworks.AnovelrobustPIDcontrollerdesignbyfuzzyneuralnetwork.Arecurrentfuzzyneuralnetwork:learningandapplication.Astudyofchatterpredictioninendmillingprocess(fuzzyneuralnetworkmodelwithinputsofcuttingconditionsandsound.Aweightedfuzzyreasoninganditscorrespondingneuralnetwork.

简介：

简介：

简介：PriorityorderedBPneuralnetworkandtheapplicationforspeakeridentification；ProbingmodificationofBPneuralnetworklearning-rate；Real-timeoptimalexcitationcontrollerusingneuralnetwork；ResearchonthemodelingoftheaxialloaddistributioncoefficientofcylindricalgearsingearCADbasedonANN；Short-termsystemmarginalpriceforecastingwithhybridmodule；StudyonautomaticcreatingmethodofpublictransportationdispatchingformbasedonBPneuralnetwork。

简介：HarmonicMinimizingNeuralNetworkSVCControllerforCompensatingUnbalancedFluctuatingLoads；ImplementationofanAdaptivePredictor-CorrectorNeuralControllerwithintheNASAIFCSF-15WVUSimulator；NeuralNetworkAdaptiveControlofaSpacePlatform-BasedDeployableManipulator；Neuralnetworkcontroldesignforarigid-linkelectricallydrivenrobot；Neuralnetworkcontrolfordynamicvoltagerestorer；NeuralNetworkControlofAir-to-FuelRatioinaBi-FuelEngine；Neuralnetworkcontrolofcoldflowcirculatingfluidizedbed；Neuralnetworkcontrolofmultlvariableprocesseswithafastoptimisationalgorithm。