OptimizationTheoryforReLUNeuralNetworksTrainedwithNormalizationLayersYonatanDukler1QuanquanGu2GuidoMontúfar134AbstractofadditionalnormalizationmethodsfollowedBN,notablyincludingLayerNormalization(...
UnderstandingandUtilizingDeepNeuralNetworksTrainedwithNoisyLabelsPengfeiChen12BenbenLiao2GuangyongChen2ShengyuZhang12AbstractbasedonwhichwecandesignspecificmethodstotrainDNNsrobustlyinpracticalappl...
Plug-and-PlayMethodsProvablyConvergewithProperlyTrainedDenoisersErnestK.Ryu1JialinLiu1SichengWang2XiaohanChen2ZhangyangWang2WotaoYin1Abstractmeasurementsoftheimage,isencodedinf(x).Sof(x)issmallifxa...
InterpretingAdversariallyTrainedConvolutionalNeuralNetworksTianyuanZhang1ZhanxingZhu234AbstractAlongthisline,somerecentworksshowedthatstandardCNNsTrainedonImageNetmaketheirpredictionsrelyonWeattemp...