Égalisation par prédiction Basée sur des réseaux de neurones et des fonctions objectifs obtenues à partir de la divergence de kullback-leibler et du constant modulus

Abstract

A nonlinear structure of filtering for blind equalization is presented. The neural network-based structure is used in order to provide nonlinearity on the filter structure while the learning strategy is divided in two stages. The Kullback-Leibler divergence is used as the base for the cost function of a self-organized rule and constant modulus criterion for the supervised one. Simulation results illustrate the performance of the strategy compared to classical ones for adaptive equalization. The results show that the proposed strategy outperforms even trained DFE for some cases of channels.