Neural networks for multiuser detection in code-division multiple-access communications

Two simple structures employing multilayer perceptrons are proposed for demodulation of spread-spectrum signals in both synchronous and asynchronous Gaussian channels. The optimum receiver is used to benchmark the performance of the proposed receiver; in particular, it is proved to be instrumental in identifying the decision regions for the neural networks. The neutral networks are trained for the demodulation of signals via backpropagation-type algorithms. A modified backpropagation-type algorithm is introduced for single-user and multiuser detection with near-optimum performance that could have applications in other classification and pattern recognition problems. A comparative performance analysis of the three receivers, optimum, conventional, and the one employing neural networks, is carried out via Monte Carlo simulations. An importance sampling technique is employed to reduce the number of simulations necessary to evaluate the performance of these receivers in a multiuser environment. In examples given, the receiver significantly outperforms the conventional receiver