An Approximate Minimum BER Approach to Channel Equalisation Using Recurrent Neural Networks

Rodrigo C. de Lamare, Raimundo Sampaio-Neto

DOI: 10.14209/its.2002.395

Evento: 2002 International Telecommunications Symposium (ITS2002)

Keywords:

Abstract

"In this paper we investigate the use of an approximate minimum bit error rate (MBER) approach to channel equalisation using recurrent neural networks (RNN). We examine a stochastic gradient adaptive algorithm for approximating the MBER from training data using RNN structures. A comparative analysis of linear equalisers and neural equalisers, employing minimum mean squared error (MMSE) and approximate MBER (AMBER) adaptive algorithms is carried out. Computer simulation experiments show that the neural equaliser operating with a criterion similar to the AMBER algorithm outperforms neural receivers using the MMSE criterion via gradient-type algorithms and linear receivers with MMSE and MBER techniques."

Download