A Real Time Complex EKF Learning Algorithm for Multilayered Neural Networks

摘要

The complex backpropagation (BP) algorithm to train the neural networks for complex signals is available in the literature. However, the convergence speed of complex BP is slow. Hence, in this paper, a real time complex extended Kalman filtering (EKF) algorithm which has faster convergence speed than the complex BP algorithm is obtained. An approach using a two step recursion procedure for updating the weights of the complex EKF algorithm has been suggested. Illustrative simulation results are promising and confirm the efficacy of the algorithm.