Technical Program

MLSP-L2: Deep Learning I

Session Type: Lecture
Time: Tuesday, May 14, 17:30 - 19:30
Location: Auditorium 2
Session Chair: Jie Ding, University of Minnesota
 
MLSP-L2.1: A TRAINING METHOD USING DNN-GUIDED LAYERWISE PRETRAINING FOR DEEP GAUSSIAN PROCESSES
Manuscript Link:  Click here to view manuscript on IEEE Xplore
         Tomoki Koriyama; Tokyo Institute of Technology
         Takao Kobayashi; Tokyo Institute of Technology
 
MLSP-L2.2: JOINTLY SPARSE CONVOLUTIONAL NEURAL NETWORKS IN DUAL SPATIAL-WINOGRAD DOMAINS
Manuscript Link:  Click here to view manuscript on IEEE Xplore
         Yoojin Choi; Samsung Semiconductor Inc.
         Mostafa El-Khamy; Samsung Semiconductor Inc.
         Jungwon Lee; Samsung Semiconductor Inc.
 
MLSP-L2.3: A PENALIZED AUTOENCODER APPROACH FOR NONLINEAR INDEPENDENT COMPONENT ANALYSIS
Manuscript Link:  Click here to view manuscript on IEEE Xplore
         Tianwen Wei; Xiaomi Inc.
         St├ęphane Chr├ętien; National Physical Laboratory
 
MLSP-L2.4: PRUNE YOUR NEURONS BLINDLY: NEURAL NETWORK COMPRESSION THROUGH STRUCTURED CLASS-BLIND PRUNING
Manuscript Link:  Click here to view manuscript on IEEE Xplore
         Abdullah Salama; SAP SE & Hamburg University of Technology
         Oleksiy Ostapenko; SAP SE & Humboldt University of Berlin
         Tassilo Klein; SAP SE
         Moin Nabi; SAP SE
 
MLSP-L2.5: DADA: DEEP ADVERSARIAL DATA AUGMENTATION FOR EXTREMELY LOW DATA REGIME CLASSIFICATION
Manuscript Link:  Click here to view manuscript on IEEE Xplore
         Xiaofeng Zhang; University of Science and Technology of China
         Zhangyang Wang; Texas A&M University
         Dong Liu; University of Science and Technology of China
         Qing Ling; Sun Yat-Sen University
 
MLSP-L2.6: UNDERSTANDING DEEP NEURAL NETWORKS THROUGH INPUT UNCERTAINTIES
Manuscript Link:  Click here to view manuscript on IEEE Xplore
         Jayaraman J. Thiagarajan; Lawrence Livermore National Laboratory
         Irene Kim; University of California, Davis
         Rushil Anirudh; Lawrence Livermore National Laboratory
         Peer-Timo Bremer; Lawrence Livermore National Laboratory