About the equivalence between complex-valued and real-valued fully connected neural networks -application to polinsar images - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

About the equivalence between complex-valued and real-valued fully connected neural networks -application to polinsar images

Résumé

In this paper we provide an exhaustive statistical comparison between Complex-Valued MultiLayer Perceptron (CV-MLP) and Real-Valued MultiLayer Perceptron (RV-MLP) on Oberpfaffenhofen Polarimetric and Interferometric Synthetic Aperture Radar (PolInSAR) database. In order to compare both networks in a fair manner, the need to define the equivalence between the models arises. A novel definition for an equivalent Real-Valued Neural Network (RVNN) is proposed in terms of its real-valued trainable parameters that maintain the aspect ratio and analyze its dynamics. We show that CV-MLP gets a slightly better statistical performance for classification on the PolInSAR image than a capacity equivalent RV-MLP.
Fichier principal
Vignette du fichier
DEMR21048.pdf (4.73 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03529898 , version 1 (17-01-2022)

Identifiants

Citer

Jose Barrachina, Chengfang Ren, Gilles Vieillard, Christele Morisseau, Jean-Philippe Ovarlez. About the equivalence between complex-valued and real-valued fully connected neural networks -application to polinsar images. IEEE International Workshop on Machine learning for signal processing, Oct 2021, Gold Coast, Queensland, Australia. ⟨10.1109/MLSP52302.2021.9596542⟩. ⟨hal-03529898⟩
31 Consultations
45 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More