Technical Program

ADL-O.1: Signal Processing for Accelerating Deep Learning I

Symposium: Symposium on Signal Processing for Accelerating Deep Learning

Session Type: Oral

Time: Wednesday, November 15, 11:00 - 12:30

Location: Lachine

Session Chair: Xiangyang Ji, Tsinghua University

11:00 - 11:18

ADL-O.1.1: PARALLEL COMPUTING HEURISTICS FOR LOW-RANK MATRIX COMPLETION

Charlie Hubbard; Iowa State University

Chinmay Hegde; Iowa State University

11:18 - 11:36

ADL-O.1.2: SENSITIVITY-BASED ACCELERATION AND COMPRESSION ALGORITHM FOR CONVOLUTION NEURAL NETWORK

Yue Niu; Northwestern Polytechnical University

Zhenyu Liu; Tsinghua University

Chunsheng Mei; Northwestern Polytechnical University

Xiangyang Ji; Tsinghua University

Wei Zhou; Northwestern Polytechnical University

Dongsheng Wang; Tsinghua University

11:36 - 11:54

ADL-O.1.3: FPGA ACCELERATION OF BAYESIAN MODEL BASED ANALYSIS FOR TIME-INDEPENDENT PROBLEMS

Humberto Trimino Mora; Max-Planck-Institut für Plasmaphysik

Sergey Bozhenkov; Max-Planck-Institut für Plasmaphysik

Jens Knauer; Max-Planck-Institut für Plasmaphysik

Petra Kornejew; Max-Planck-Institut für Plasmaphysik

Sehyun Kwak; Max-Planck-Institut für Plasmaphysik

Oliver Ford; Max-Planck-Institut für Plasmaphysik

Golo Fuchert; Max-Planck-Institut für Plasmaphysik

Ekkehard Pasch; Max-Planck-Institut für Plasmaphysik

Jakob Svensson; Max-Planck-Institut für Plasmaphysik

Andreas Werner; Max-Planck-Institut für Plasmaphysik

Robert Christian Wolf; Max-Planck-Institut für Plasmaphysik

Dirk Timmermann; Rostock University

11:54 - 12:12

ADL-O.1.4: A VIDEO DEHAZING SYSTEM BASED ON FAST AIRLIGHT ESTIMATION

Yongmin Park; Korea Aerospace University

Tae-Hwan Kim; Korea Aerospace University

12:12 - 12:30

ADL-O.1.5: A 200MHZ 202.4GFLOPS@10.8W VGG16 ACCELERATOR IN XILINX VX690T