深度学习进展资料.ppt

HowdoesReducetheDimensionalityofDatawithDeepNeuralNetworks？2026/4/24

◆2012,ImageNetRecognitionChallenge,Hinton’steamwitha16%errorrateinclassifying1.2millionimages,againsta26%errorratebyitsclosestcompetitors.◆2006,HintonandSalakhutdinovproposeddeepneuralnetworkslearningmethod;Subsequently(June26,2012,news),researchersatGoogleandStanfordUniversitycreatedthelargestneuralnetworkswhichisadeepneuralnetworkwithnine-layerthatlearnedontheinternettolearnonitsown.Thesystemwasusedtosimulatehumanbrain,withonebi