简介:Houdini是SideEffect公司的拳头产品,最初运行在SGI平台上,叫做Prism,后来移植到WindowsNT上,改名为Houdini。“终结者2”中那些液体机器人的经典场面就是用Houdini制作的。Houdini将后期制作的过程融入到了三维制作中,设计理念极为独特,变形球的功能强大,渲染也很优秀。Houdini除了自己的hscript语言外,还可以使用世界上已经非常成熟的更好的语言,如TCL、JAvA、Python。不过,当前它在国内的用户十分稀少,所以知道的人不多。在这里,我们管中窥豹,对Houdini产品家族作一个简单的介绍,以下不同的Houdini产品都有它擅长的应用领域。
简介:Dynamicnodecreationandfastlearningalgorithmforahybridfeedforwardneuralnetwork.Flight-pathanglecontrolvianeuro-adaptiveBackstepping.Locallearningframeworkforhandwrittencharacterrecognition.Maximizingmarginsofmultilayerneuralnetworks.ModularnetworkSOMself-orgmlizingmapofasystemsgroupinfunctionspace.
简介:ApplicationoftheRTNNmodelforasystemidentification,predictionandcontrol;AssociativeMemoryUsingRatioRuleforMulti-valuedPatternAssociation;Batch-to-BatchModel-basedIterativeOptimisationControlforaBatchPolymerisationReactor;BehaviouralPlasticityinAutonomousAgents:AComparisonbetweenTwoTypesofController;ChannelEqualizationUsingComplex-ValuedRecurrentNeuralNetworks;Classificationofnaturallanguagesentencesusingneuralnetworks;Combiningarecurrentneuralnetworkandtheoutputregulationtheoryfornon-linearadaptivecontrol。
简介:ConfigurablemultilayerCNN-UMemulatoronFPGA;Cortically-inspiredVisualProcessingwithaFourLayerCellularNeuralNetwork;Effectofcouplingresistorsonsteadypatternsincoupledoscillatornetworks;Exponentialconvergenceestimatesforneuralnetworkswithmultipledelays;FEATUREEXTRACTIONINEPILEPSYUSINGACELLULARNEURALNETWORKBASEDDEVICEFIRSTRESULTS;FurtherResultsontheStabilityofDelayedCellularNeuralNetworks;Globalstabilityanalysisindelayedcellularneuralnetworks;ImageedgedetectionusingadaptivemorphologyMeyerWavelet-CNN。
简介:PredictionoftheDimensionalChangesduringSinteringusingBackpropagationAlgorithm,Predictionofthenextstockpriceusingneuralnetwork-extractionthefeaturetopredictnextstockpricebyfiltering,Pulsemodeneuronwithpiecewiselinearactivationfunction,Remarksonmultilayerneuralnetworksinvolvingchaosneurons……