深度学习阅读书目.docx

深度学习阅读书目.docx

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

深度学习阅读书目

FROM:

ReadingList

Listofreadinglistsandsurveypapers:

∙ Books

oDeepLearning,YoshuaBengio,IanGoodfellow,AaronCourville,MITPress,Inpreparation.

∙ ReviewPapers

o RepresentationLearning:

AReviewandNewPerspectives,YoshuaBengio,AaronCourville,PascalVincent,Arxiv,2012.

oThemonographorreviewpaper LearningDeepArchitecturesforAI （Foundations&TrendsinMachineLearning,2009）.

oDeepMachineLearning–ANewFrontierinArtificialIntelligenceResearch–a surveypaper byItamarArel,DerekC.Rose,andThomasP.Karnowski.

oGraves,A.（2012）. Supervisedsequencelabellingwithrecurrentneuralnetworks（Vol.385）.Springer.

oSchmidhuber,J.（2014）.DeepLearninginNeuralNetworks:

AnOverview.75pages,850+references, http:

//arxiv.org/abs/1404.7828,PDF&LATEXsource&completepublicBIBTEXfileunder http:

//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.

o LearningConvolutionalFeatureHierachiesforVisualRecognition, KorayKavukcuoglu,PierreSermanet,Y-LanBoureau,KarolGregor,MichaëlMathieuandYannLeCun,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,andJürgenSchmidhuber. “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.

oMikolovTomáš:

 StatisticalLanguageModelsbasedonNeuralNetworks.PhDthesis,BrnoUniversityofTechnology,2012.

oGraves,Alex,andJürgenSchmidhuber.“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.” arXivpreprintarXiv:

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.

oXavierGlorot, AntoineBordes and YoshuaBengio, DomainAdaptationforLarge-ScaleSentimentClassification:

ADeepLearningApproach,in:

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

oR.Collobert,J.Weston,L.Bottou,M.Karlen,K.KavukcuogluandP.Kuksa. NaturalLanguageProcessing（Almost）fromScratch. JournalofMachineLearningResearch,12:

2493-2537,2011.

oMesnil,Grégoire,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:

GrégoireMontavon,GenevièveB.Orr,Klaus-RobertMüller,2012.

oApractical guide totrainingRestrictedBoltzmannMachines,byGeoffreyHinton.

∙ SparseCoding

oEmergenceofsimple-cellreceptivefieldpropertiesbylearningasparsecodefornaturalimages,BrunoOlhausen,Nature1996.

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

1010.3467 （2010）.

oGoodfellow,Ian,AaronCourville,andYoshuaBengio.“Large-ScaleFeatureLearningWithSpike-and-SlabSparseCoding.” ICML2012.

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.” Advancesinneuralinformationprocessingsystems 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.” Advancesinneuralinformationprocessingsystems 20（2007）:

1185-1192.

oBengio,Yoshua,andYannLeCun.“ScalinglearningalgorithmstowardsAI.” Large-ScaleKernelMachines 34（2007）.

oLeRoux,Nicolas,andYoshuaBengio.“Representationalpowerofrestrictedboltzmannmachinesanddeepbeliefnetworks.” NeuralComputation 20.6（2008）:

1631-1649.

oSutskever,Ilya,andGeoffreyHinton.“Temporal-KernelRecurrentNeuralNetworks.” NeuralNetworks 23.2（2010）:

239-243.

oLeRoux,Nicolas,andYoshuaBengio.“Deepbeliefnetworksarecompactuniversalapproximators.” Neuralcomputation 22.8（2010）:

2192-2207.

oBengio,Yoshua,andOlivierDelalleau.“Ontheexpressivepowerofdeeparchitectures.” AlgorithmicLearningTheory.SpringerBerlin/Heidelberg,2011.

oMontufar,GuidoF.,andJasonMorton.“WhenDoesaMixtureofProductsContainaProductofMixtures?

.” arXivpreprintarXiv:

1206.0387 （2012）.

oMontúfar,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