2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

Technical Program

Click on the icon to view the manuscript on IEEE XPlore in the IEEE ICASSP 2021 Open Preview.

MLSP-3: Deep Learning Training Methods 3

Session Type: Poster
Time: Tuesday, 8 June, 13:00 - 13:45
Location: Gather.Town
Virtual Session: View on Virtual Platform
Session Chair: Jinyu Li, Microsoft
 
 MLSP-3.1: EVOLUTIONARY QUANTIZATION OF NEURAL NETWORKS WITH MIXED-PRECISION
         Zhenhua Liu; Peking University
         Xinfeng Zhang; University of Chinese Academy of Sciences
         Shanshe Wang; Peking University
         Siwei Ma; Peking University
         Wen Gao; Peking University
 
 MLSP-3.2: EVOLVING QUANTIZED NEURAL NETWORKS FOR IMAGE CLASSIFICATION USING A MULTI-OBJECTIVE GENETIC ALGORITHM
         Yong Wang; Central South University
         Xiaojing Wang; Central South University
         Xiaoyu He; Central South University
 
 MLSP-3.3: SPECTRAL DOMAIN CONVOLUTIONAL NEURAL NETWORK
         Bochen Guan; OPPO US Research Center
         Jinnian Zhang; University of Wisconsin-Madison
         William A. Sethares; University of Wisconsin-Madison
         Richard Kijowski; New York University
         Fang Liu; Harvard University
 
 MLSP-3.4: PARAMETRIC SPECTRAL FILTERS FOR FAST CONVERGING, SCALABLE CONVOLUTIONAL NEURAL NETWORKS
         Luke Wood; Google
         Eric Larson; Southern Methodist University
 
 MLSP-3.5: FEATURE REUSE FOR A RANDOMIZATION BASED NEURAL NETWORK
         Xinyue Liang; KTH Royal Institute of Technology
         Mikael Skoglund; KTH Royal Institute of Technology
         Saikat Chatterjee; KTH Royal Institute of Technology
 
 MLSP-3.6: A RELU DENSE LAYER TO IMPROVE THE PERFORMANCE OF NEURAL NETWORKS
         Alireza M. Javid; KTH Royal Institute of Technology
         Sandipan Das; KTH Royal Institute of Technology
         Mikael Skoglund; KTH Royal Institute of Technology
         Saikat Chatterjee; KTH Royal Institute of Technology