Recurrent neural network techniques in multiuser detection

This paper explores the use of recurrent neural networks for sub-optimal detection in code division multiple access (CDMA) systems. The focus is to propose a Hopfeld-based neural network which overcomes the problem of local minima. We investigate past models that are based on the Hopfield neural network (HNN). We highlight the ability of stochastic algorithms to achieve global minimum solutions and propose a stochastic model based on probabilistic firing mechanisms