Recent Advances in Convolutional Neural Networks

《Recent Advances in Convolutional Neural Networks》由会员上传分享，免费在线阅读，更多相关内容在学术论文-天天文库。

1、1RecentAdvancesinConvolutionalNeuralNetworksJiuxiangGu∗,ZhenhuaWang∗,JasonKuen,LianyangMa,AmirShahroudy,BingShuai,TingLiu,XingxingWang,andGangWang,Member,IEEEAbstract—Inthelastfewyears,deeplearninghasledtoverythem,fourrepresentativeworksareZFNet[7],VGGNet[8],goodperformanceonavarietyofproble

2、ms,suchasvisualGoogleNet[9]andResNet[10].Fromtheevolutionoftherecognition,speechrecognitionandnaturallanguageprocessing.architectures,atypicaltrendisthatthenetworksaregettingAmongdifferenttypesofdeepneuralnetworks,convolutionaldeeper,e.g.,ResNet,whichwonthechampionofILSVRCneuralnetworkshaveb

3、eenmostextensivelystudied.Duetothelackoftrainingdataandcomputingpowerinearlydays,itis2015,isabout20timesdeeperthanAlexNetand8timeshardtotrainalargehigh-capacityconvolutionalneuralnetworkdeeperthanVGGNet.Byincreasingdepth,thenetworkcanwithoutoverfitting.Aftertherapidgrowthintheamountofthebette

4、rapproximatethetargetfunctionwithincreasednon-annotateddataandtherecentimprovementsinthestrengthsoflinearityandgetbetterfeaturerepresentations.However,itgraphicsprocessorunits(GPUs),theresearchonconvolutionalalsoincreasesthecomplexityofthenetwork,whichmakesneuralnetworkshasbeenemergedswiftly

5、andachievedstate-of-the-artresultsonvarioustasks.Inthispaper,weprovideabroadthenetworkbemoredifficulttooptimizeandeasiertogetsurveyoftherecentadvancesinconvolutionalneuralnetworks.overfitting.Alongthisway,variousmethodsareproposedtoBesides,wealsointroducesomeapplicationsofconvolutionaldealwith

6、theseproblemsinvariousaspects.Inthispaper,weneuralnetworksincomputervision.trytogiveacomprehensivereviewofrecentadvancesandIndexTerms—ConvolutionalNeuralNetwork,Deeplearning.givesomethoroughdiscussions.Inthefollowingsections,weidentifybroadcategoriesofworksrelatedtoCNN.Wefirstgiveanoverviewof

7、thebasicI.INTRODUCTIONcomponentsofCNNinSectionII.Then,weintroducesomeONVOLUTIONALNeuralNetwork(CNN)isawell-recentimprovementsondifferentaspectsofCNNincludingCknowndeeplearningarchitectureinspiredbythenaturalconvolutionallayer,poolinglayer,activatio