Fast Converging Minimum Probability of Error Neural Network Receivers for DS-CDMA Communications

J.D. Matyjas, I.N. Psaromiligkos, S.N. Batalama, M.J. Medley
2004 IEEE Transactions on Neural Networks  
We consider a multilayer perceptron neural network (NN) receiver architecture for the recovery of the information bits of a direct-sequence code-division-multiple-access (DS-CDMA) user. We develop a fast converging adaptive training algorithm that minimizes the bit-error rate (BER) at the output of the receiver. The adaptive algorithm has three key features: i) it incorporates the BER, i.e., the ultimate performance evaluation measure, directly into the learning process, ii) it utilizes
more » ... nts that are derived from the properties of the optimum single-user decision boundary for additive white Gaussian noise (AWGN) multiple-access channels, and iii) it embeds importance sampling (IS) principles directly into the receiver optimization process. Simulation studies illustrate the BER performance of the proposed scheme. Index Terms-Accelerated convergence, approximation theory, direct-sequence code-division-multiple-access (DS-CDMA) systems, importance sampling (IS), minimum bit-error rate (BER), minimum probability of error, multilayer perceptron, neural networks (NNs), stochastic approximation, supervised learning algorithms.
doi:10.1109/tnn.2004.824409 pmid:15384536 fatcat:7rsybyrkl5fmvl3ufexu7yglee