Complex discriminative learning Bayesian neural equalizer

Abstract

Traditional approaches to channel equalization are based on the inversion of the global (linear or nonlinear) channel response. However, in digital links the complete channel inversion is neither required nor desirable. Since transmitted symbols belong to a discrete alphabet, symbol demodulation can be e ectively recasted as a classiÿcation problem in the space of received symbols. In this paper a novel neural network for digital equalization is introduced and described. The proposed approach is based on a decision-feedback architecture trained with a complex-valued discriminative learning strategy for the minimization of the classiÿcation error. Main features of the resulting neural equalizer are the high rate of convergence with respect to classical neural equalizers and the low degree of complexity. Its e ectiveness has been demonstrated through computer simulations for several typical digital transmission channels. ? 2001 Elsevier Science B.V. All rights reserved.

Novel Algorithms for Nonlinear Channel Equalization Using Neural Vector Quantization

“…Supervised neural networks, such as MLP and RBF, motivated by their universal approximation property, have been successfully used as nonlinear tools for channel equalization [11]. It has been demonstrated that the performance of MLP-or RBF-based adaptive filters usually outperform traditional linear techniques in many common signal processing applications [12], [20], [25].…”