Performance improvement of LMS algorithm using Hopfield modelnetwork

摘要

An algorithm that improves the adaptation rate of theleast-mean-square algorithm and is based on the dynamics of the networkin the Hopfield (neural network) model is discussed. The rate ofadaptation of the algorithm is shown to be n times as fast asthe system of the well-known LMS algorithm with the same control gain,n being the number of iterations for each data sample. Theconvergence is shown to depend on the gain constant, not on n.Simulations of the convergence behavior of the algorithm are presented