深度学习阅读书目Word文件下载.docx

深度学习阅读书目Word文件下载.docx

《深度学习阅读书目Word文件下载.docx》由会员分享，可在线阅读，更多相关《深度学习阅读书目Word文件下载.docx（10页珍藏版）》请在冰点文库上搜索。

oGraves,A.（2012）. 

Supervisedsequencelabellingwithrecurrentneuralnetworks（Vol.385）.Springer.

oSchmidhuber,J.（2014）.DeepLearninginNeuralNetworks:

AnOverview.75pages,850+references, 

http:

//arxiv.org/abs/1404.7828,PDF&

LATEXsource&

completepublicBIBTEXfileunder 

//www.idsia.ch/~juergen/deep-learning-overview.html.

ReinforcementLearning

oMnih,Volodymyr,KorayKavukcuoglu,DavidSilver,AlexGraves,IoannisAntonoglou,DaanWierstra,andMartinRiedmiller.“PlayingAtariwithdeepreinforcementlearning.” 

arXivpreprintarXiv:

1312.5602 

（2013）.

oVolodymyrMnih,NicolasHeess,AlexGraves,KorayKavukcuoglu.“RecurrentModelsofVisualAttention”ArXive-print,2014.

ComputerVision

oImageNetClassificationwithDeepConvolutionalNeuralNetworks,AlexKrizhevsky,IlyaSutskever,GeoffreyEHinton,NIPS2012.

oGoingDeeperwithConvolutions,ChristianSzegedy,WeiLiu,YangqingJia,PierreSermanet,ScottReed,DragomirAnguelov,DumitruErhan,VincentVanhoucke,AndrewRabinovich,19-Sept-2014.

oLearningHierarchicalFeaturesforSceneLabeling,ClementFarabet,CamilleCouprie,LaurentNajmanandYannLeCun,IEEETransactionsonPatternAnalysisandMachineIntelligence,2013.

LearningConvolutionalFeatureHierachiesforVisualRecognition, 

KorayKavukcuoglu,PierreSermanet,Y-LanBoureau,KarolGregor,Michaë

lMathieuandYannLeCun,AdvancesinNeuralInformationProcessingSystems（NIPS2010）,23,2010.

oGraves,Alex,etal. 

“Anovelconnectionistsystemforunconstrainedhandwritingrecognition.” 

PatternAnalysisandMachineIntelligence,IEEETransactionson 

31.5（2009）:

855-868.

oCireşan,D.C.,Meier,U.,Gambardella,L.M.,&

Schmidhuber,J.（2010）. 

Deep,big,simpleneuralnetsforhandwrittendigitrecognition. 

Neuralcomputation, 

22（12）,3207-3220.

oCiresan,Dan,UeliMeier,andJü

rgenSchmidhuber. 

“Multi-columndeepneuralnetworksforimageclassification.” 

ComputerVisionandPatternRecognition（CVPR）,2012IEEEConferenceon.IEEE,2012.

oCiresan,D.,Meier,U.,Masci,J.,&

Schmidhuber,J.（2011,July）. 

Acommitteeofneuralnetworksfortrafficsignclassification. 

In 

NeuralNetworks（IJCNN）,The2011InternationalJointConferenceon 

（pp.1918-1921）.IEEE.

NLPandSpeech

oJointLearningofWordsandMeaningRepresentationsforOpen-TextSemanticParsing,AntoineBordes,XavierGlorot,JasonWestonandYoshuaBengio（2012）,in:

Proceedingsofthe15thInternationalConferenceonArtificialIntelligenceandStatistics（AISTATS）

oDynamicpoolingandunfoldingrecursiveautoencodersforparaphrasedetection.Socher,R.,Huang,E.H.,Pennington,J.,Ng,A.Y.,andManning,C.D.（2011a）. 

InNIPS’2011.

oSemi-supervisedrecursiveautoencodersforpredictingsentimentdistributions.Socher,R.,Pennington,J.,Huang,E.H.,Ng,A.Y.,andManning,C.D.（2011b）. 

InEMNLP’2011.

oMikolovTomá

š:

StatisticalLanguageModelsbasedonNeuralNetworks.PhDthesis,BrnoUniversityofTechnology,2012.

oGraves,Alex,andJü

rgenSchmidhuber.“FramewisephonemeclassificationwithbidirectionalLSTMandotherneuralnetworkarchitectures.” 

NeuralNetworks 

18.5（2005）:

602-610.

oMikolov,Tomas,IlyaSutskever,KaiChen,GregS.Corrado,andJeffDean. 

“Distributedrepresentationsofwordsandphrasesandtheircompositionality.”In 

AdvancesinNeuralInformationProcessingSystems,pp.3111-3119.2013.

oK.Cho,B.vanMerrienboer,C.Gulcehre,D.Bahdanau,F.Bougares,H.Schwenk,Y.Bengio. 

LearningPhraseRepresentationsusingRNNEncoder-DecoderforStatisticalMachineTranslation.EMNLP2014.

oSutskever,Ilya,OriolVinyals,andQuocVVLe.“Sequencetosequencelearningwithneuralnetworks.” 

AdvancesinNeuralInformationProcessingSystems.2014.

DisentanglingFactorsandVariationswithDepth

oGoodfellow,Ian,etal.“Measuringinvariancesindeepnetworks.” 

Advancesinneuralinformationprocessingsystems 

22（2009）:

646-654.

oBengio,Yoshua,etal.“BetterMixingviaDeepRepresentations.” 

1207.4404 

（2012）.

oXavierGlorot, 

AntoineBordes 

and 

YoshuaBengio, 

DomainAdaptationforLarge-ScaleSentimentClassification:

ADeepLearningApproach,in:

ProceedingsoftheTwenty-eightInternationalConferenceonMachineLearning（ICML’11）,pages97-110,2011.

TransferLearninganddomainadaptation

oRaina,Rajat,etal.“Self-taughtlearning:

transferlearningfromunlabeleddata.” 

Proceedingsofthe24thinternationalconferenceonMachinelearning.ACM,2007.

oR.Collobert,J.Weston,L.Bottou,M.Karlen,K.KavukcuogluandP.Kuksa. 

NaturalLanguageProcessing（Almost）fromScratch. 

JournalofMachineLearningResearch,12:

2493-2537,2011.

oMesnil,Gré

goire,etal.“Unsupervisedandtransferlearningchallenge:

adeeplearningapproach.” 

UnsupervisedandTransferLearningWorkshop,inconjunctionwithICML.2011.

oCiresan,D.C.,Meier,U.,&

Schmidhuber,J.（2012,June）. 

TransferlearningforLatinandChinesecharacterswithdeepneuralnetworks.In 

NeuralNetworks（IJCNN）,The2012InternationalJointConferenceon 

（pp.1-6）.IEEE.

oGoodfellow,Ian,AaronCourville,andYoshuaBengio.“Large-ScaleFeatureLearningWithSpike-and-SlabSparseCoding.” 

ICML2012.

PracticalTricksandGuides

o“Improvingneuralnetworksbypreventingco-adaptationoffeaturedetectors.” 

Hinton,GeoffreyE.,etal. 

arXivpreprintarXiv:

1207.0580（2012）.

oPracticalrecommendationsforgradient-basedtrainingofdeeparchitectures,YoshuaBengio,U.Montreal,arXivreport:

1206.5533,LectureNotesinComputerScienceVolume7700,NeuralNetworks:

TricksoftheTradeSecondEdition,Editors:

Gré

goireMontavon,Geneviè

veB.Orr,Klaus-RobertMü

ller,2012.

oApractical 

guide 

totrainingRestrictedBoltzmannMachines,byGeoffreyHinton.

SparseCoding

oEmergenceofsimple-cellreceptivefieldpropertiesbylearningasparsecodefornaturalimages,BrunoOlhausen,Nature1996.

oKavukcuoglu,Koray,Marc’AurelioRanzato,andYannLeCun.“Fastinferenceinsparsecodingalgorithmswithapplicationstoobjectrecognition.” 

1010.3467 

（2010）.

oEfficientsparsecodingalgorithms.HonglakLee,AlexisBattle,RainaRajatandAndrewY.Ng.In 

NIPS19,2007. 

pdf

o“Sparsecodingwithanovercompletebasisset:

AstrategyemployedbyVI?

.”.Olshausen,BrunoA.,andDavidJ.Field. 

Visionresearch 

37.23（1997）:

3311-3326.

FoundationTheoryandMotivation

oHinton,GeoffreyE.“DeterministicBoltzmannlearningperformssteepestdescentinweight-space.” 

Neuralcomputation 

1.1（1989）:

143-150.

oBengio,Yoshua,andSamyBengio.“Modelinghigh-dimensionaldiscretedatawithmulti-layerneuralnetworks.” 

AdvancesinNeuralInformationProcessingSystems 

12（2000）:

400-406.

oBengio,Yoshua,etal.“Greedylayer-wisetrainingofdeepnetworks.” 

19（2007）:

153.

oBengio,Yoshua,MartinMonperrus,andHugoLarochelle.“Nonlocalestimationofmanifoldstructure.” 

NeuralComputation 

18.10（2006）:

2509-2528.

oHinton,GeoffreyE.,andRuslanR.Salakhutdinov.“Reducingthedimensionalityofdatawithneuralnetworks.” 

Science 

313.5786（2006）:

504-507.

oMarc’AurelioRanzato,Y.,LanBoureau,andYannLeCun.“Sparsefeaturelearningfordeepbeliefnetworks.” 

20（2007）:

1185-1192.

oBengio,Yoshua,andYannLeCun.“ScalinglearningalgorithmstowardsAI.” 

Large-ScaleKernelMachines 

34（2007）.

oLeRoux,Nicolas,andYoshuaBengio.“Representationalpowerofrestrictedboltzmannmachinesanddeepbeliefnetworks.” 

20.6（2008）:

1631-1649.

oSutskever,Ilya,andGeoffreyHinton.“Temporal-KernelRecurrentNeuralNetworks.” 

23.2（2010）:

239-243.

oLeRoux,Nicolas,andYoshuaBengio.“Deepbeliefnetworksarecompactuniversalapproximators.” 

22.8（2010）:

2192-2207.

oBengio,Yoshua,andOlivierDelalleau.“Ontheexpressivepowerofdeeparchitectures.” 

AlgorithmicLearningTheory.SpringerBerlin/Heidelberg,2011.

oMontufar,GuidoF.,andJasonMorton.“WhenDoesaMixtureofProductsContainaProductofMixtures?

.” 

1206.0387 

oMontú

far,Guido,RazvanPascanu,KyunghyunCho,andYoshuaBengio.“OntheNumberofLinearRegionsofDeepNeuralNetworks.”arXivpreprintarXiv:

1402.1869（2014）.

SupervisedFeedfowardNeuralNetworks

oTheManifoldTangentClassifier,SalahRifai,YannDauphin,PascalVincent,YoshuaBengioandXavierMuller,in:

NIPS’2011.

o“DiscriminativeLearningofSum-ProductNetworks.“,Gens,Robert,andPedroDomingos,NIPS2012BestStudentPaper.

oGoodfellow,I.,Warde-Farley,D.,Mirza,M.,Courville,A.,andBengio,Y.（2013）. 

Maxoutnetworks.TechnicalReport,UniversitedeMontreal.

oHinton,GeoffreyE.,etal.“Improvingneuralnetworksbypreventingco-adaptation