Linear neural network based blind equalization

This letter considers the problem of blind equalization in digital communic ations by using linear neural network. Unlike most adaptive blind equalizat ion methods which are based on matrix decomposition or the Hankel property of matrix, we give a stochastic approximate learning algorithm for the neur al network according to the property of the correlation matrices of the tra nsmitted symbols. The network outputs provide an estimation of the source s ymbols, while the weight matrix of network estimates the inverse of the cha nnel matrix. Simulation results demonstrate the performance and validity of the proposed approach for blind equalization. (C) 1999 Elsevier Science B. V. All rights reserved.