Technical Program

WA8b1: Deep Learning

Session Type: Poster
Time: Wednesday, November 6, 10:15 - 11:30
Location: Merrill
Session Chair: Maxime Guillaud, Huawei
 
WA8b1-1: COUNTING LATTICE POINTS IN THE SPHERE USING DEEP NEURAL NETWORKS
         Aymen Askri; Télécom ParisTech
         Ghaya Rekaya-Ben Othman; Télécom ParisTech
         Hadi Ghauch; Télécom ParisTech
 
WA8b1-2: DSP-INSPIRED DEEP LEARNING: A CASE STUDY USING RAMANUJAN SUBSPACES
         Srikanth Tenneti; Amazon Web Services
         P. P. Vaidyanathan; California Institute of Technology
 
WA8b1-3: MEDA: MULTI-OUTPUT ENCODER-DECODER FOR SPATIAL ATTENTION IN CONVOLUTIONAL NEURAL NETWORKS
         Huayu Li; Northern Arizona University
         Abolfazl Razi; Northern Arizona University
 
WA8b1-4: LOSS FUNCTIONS FORCING CLUSTER SEPARATIONS FOR MULTI-CLASS CLASSIFICATION USING DEEP NEURAL NETWORKS
         Li Li; George Washington University
         Milos Doroslovacki; George Washington University
         Murray Loew; George Washington University
 
WA8b1-5: LEARNING STRUCTURED SIGNALS USING GANS WITH APPLICATIONS IN DENOISING AND DEMIXING
         Mohammadreza Soltani; Iowa State university
         Swayambhoo Jain; Technicolor AI Labs
         Abhinav V. Sambasivan; University of Minnesota
         Chinmay Hegde; Iowa State University
 
WA8b1-7: WAVE EQUATION EXTRACTION FROM A VIDEO USING SPARSE MODELING
         Ruixian Liu; University of California, San Diego
         Michael Bianco; University of California, San Diego
         Peter Gerstoft; University of California, San Diego
 
WA8b1-8: THE AUTOENCODER-KALMAN FILTER: THEORY AND PRACTICE
         Matthew Weiss; Worcester Polytechnic Institute
         Joshua Uzarski; U.S. Army Combat Capabilities Development Command Soldier Center
         Randy Paffenroth; Worcester Polytechnic Institute