Expressive1-LipschitzNeuralNetworksforRobustMultipleGraphLearningagainstAdversarialAttacksXinZhao1ZeruZhang1ZijieZhang1LingfeiWu2JiayinJin1YangZhou1RuomingJin3DejingDou45DaYan6Abstractment)(Zhang&T...
EquivariantNetworksforPixelizedSpheresMehranShakerinava12SiamakRavanbakhsh12AbstractFigure1.Wemodeltherotationalsymmetryofthespherebycom-biningtherotationalsymmetryofaPlatonicsolidandisometriesPixe...
EnhancingRobustnessofNeuralNetworksthroughFourierStabilizationNetanelRaviv1AidanKelley1MichaelGuo1YevgenyVorobeychik1Abstractevasionattacks(Grosseetal.,2016;Li&Vorobeychik,2018;Laskovetal.,2014;Xue...
E(n)EquivariantGraphNeuralNetworksVictorGarciaSatorras1EmielHoogeboom1MaxWelling1AbstractThispaperintroducesanewmodeltolearngraphneuralNetworksequivarianttorotations,transla-tions,reflectionsandper...
DirectionalGraphNetworksDominiqueBeaini1SaroPassaro2VincentLe´tourneau13WilliamL.Hamilton34GabrieleCorso2PietroLio`2Abstractnels(alsocalledisotropickernels)(Kipf&Welling,2016;Gilmeretal.,2017).The...
DiffusionSourceIdentificationonNetworkswithStatisticalConfidenceQuinlanDawkins1TianxiLi2HaifengXu1Abstractleakageproblems(Newmanetal.,2002;Halperin&Al-mogy,2002;Xu&Ren,2016).ThenegativeimpactsstemD...
DifferentiableSortingNetworksforScalableSortingandRankingSupervisionFelixPetersen1ChristianBorgelt2HildeKuehne34OliverDeussen1AbstractRecently,theideaofend-to-endtrainingofneuralNetworkswithsorting...
DeepContinuousNetworksNergisTomen1SilviaL.Pintea1JanC.vanGemert1Abstractcalcircuits(Schrimpfetal.,2018),andemployCNNsasmodelsofbiologicalvision(Zhuangetal.,2020a).Specif-CNNsandcomputationalmodelso...
BayesianAttentionBeliefNetworksShujianZhang1XinjieFan1BoChen2MingyuanZhou1AbstractoftheTransformerstructure,itbecomespossibletotrainunprecedentedlargemodelsonbigdatasets(Devlinetal.,Attention-based...
BackdoorScanningforDeepNeuralNetworksthroughK-ArmOptimizationGuangyuShen1YingqiLiu1GuanhongTao1ShengweiAn1QiulingXu1SiyuanCheng1ShiqingMa2XiangyuZhang1Abstractdoor)attackexploitstheuninterpretabili...
ActiveLearningofContinuous-timeBayesianNetworksthroughInterventionsDominikLinzner12HeinzKoeppl13Abstracttolearnthesedependencies.Thisisaproblemwhendataisacquiredunderlimitedresources,whichisthecase...
AReceptorSkeletonforCapsuleNeuralNetworksJintaiChen1HongyunYu1ChengdeQian2DannyZ.Chen3JianWu4AbstractSeniorRepresentationsInpreviousCapsuleNeuralNetworks(CapsNets),routingroutingalgorithmsoftenperf...
UnsupervisedTransferLearningforSpatiotemporalPredictiveNetworksZhiyuYao1YunboWang1MingshengLong1JianminWang1Abstractdeeprepresentationsfromtheconsequencesofcomplexvideoevents.Thestudiesofthespatiot...
TransformationofReLU-basedrecurrentneuralNetworksfromdiscrete-timetocontinuous-timeZahraMonfared1DanielDurstewitz12AbstractMorerecently,inthenaturalsciences,biologyandphysicsinparticular,RNNswereal...
TrainingNeuralNetworksforandbyInterpolationLeonardBerrada1AndrewZisserman2M.PawanKumar2Abstractdimensionalnon-convexfunctions.Inpractice,themainalgorithmsofchoiceareStochasticGradientDescent(SGD)In...
TrainingLinearNeuralNetworks:Non-LocalConvergenceandComplexityResultsArminEftekhari1AbstractbythelinearmapLinearNetworksprovidevaluableinsightsintoRdx→RdytheworkingsofneuralNetworksingeneral.Thisp...
TrainingBinaryNeuralNetworksusingtheBayesianLearningRuleXiangmingMeng1RomanBachmann2MohammadEmtiyazKhan1Abstractbyreplacingthemultiplicationandadditionoperationswiththebit-wisexnorandbitcountoperat...
TrainingBinaryNeuralNetworksthroughLearningwithNoisySupervisionKaiHan12YunheWang2YixingXu2ChunjingXu2EnhuaWu13ChangXu4AbstractFigure1.Frameworkoflearningbinaryneuronswithnoisysuper-vision.Anetworkf...
T-Basis:aCompactRepresentationforNeuralNetworksAntonObukhov1MaximRakhuba1StamatiosGeorgoulis1MenelaosKanakis1DengxinDai1LucVanGool12Abstractthatcontainmillionsoftrainableparametersandconsumelotsofm...