MA1.L2: Advances in Neural Models
Mon, 28 Oct, 08:30 - 10:00 Gulf Standard Time (UTC +4)
Location: Capital Suite - 14
Session Type: Lecture
Session Chair: Eduardo Silva, Federal University of Rio de Janeiro, Rio de Janeiro, Brazil
Track: Multidimensional Signal Processing
Click the to view the manuscript on IEEE Xplore Open Preview
Mon, 28 Oct, 08:30 - 08:48 Gulf Standard Time (UTC +4)

MA1.L2.1: ENN: A NEURAL NETWORK WITH DCT ADAPTIVE ACTIVATION FUNCTIONS
Marc Martinez-Gost, CTTC - UPC, Spain; Ana Isabel Pérez Neira, CTTC, Space and Resilient Communications, Spain; Miguel Ángel Lagunas, UPC, Spain
Mon, 28 Oct, 08:48 - 09:06 Gulf Standard Time (UTC +4)
 

MA1.L2.2: PAON: A NEW NEURON MODEL USING PADE APPROXIMANTS
Onur Keleş, A. Murat Tekalp, Koç University, Türkiye
Mon, 28 Oct, 09:06 - 09:24 Gulf Standard Time (UTC +4)
 

MA1.L2.3: Non-Separable Wavelet Transform using Learnable Convolutional Lifting Steps
João Parracho, Federal University of Rio de Janeiro, Brazil; Eduardo Silva, Federal University of Rio de Janeiro, Rio de Janeiro, Brazil, Brazil; Lucas Thomaz, Luis Távora, Sergio Faria, Instituto de Telecomunicações / Polytechnic of Leiria, Brazil
Mon, 28 Oct, 09:24 - 09:42 Gulf Standard Time (UTC +4)

MA1.L2.4: Trainable Fractional Fourier Transform
Emirhan Koc, Tuna Alikasifoglu, Arda Can Aras, Aykut Koc, Bilkent University, Türkiye
Mon, 28 Oct, 09:42 - 10:00 Gulf Standard Time (UTC +4)
 

MA1.L2.5: Robustness of tensor decomposition-based neural network compression
Théo Rudkiewicz, Ecole Normale Supérieure Paris-Saclay, France; Mohamed Ouerfelli, Zakariya Chaouai, Riccardo Finotello, Mohamed Tamaazousti, Université Paris-Saclay, CEA, List, France