Multiuser detection using time-varying scaling-parameter transiently chaotic neural networks

A time-varying scaling-parameter transiently chaotic neural network (TSTCNN) is proposed for multiuser detection in DS/CDMA systems. The TSTCNN has rich dynamics which can prevent the network from being trapped at local minima. Simulation results show that the performance of the TSTCNN-based detector can closely approximate that of the optimum detector.