Uso del conocimiento estadístico de la señal para la mejora de la velocidad de convergencia de los algoritmos adaptativos de gradiente

Abstract

This work deals with the use of previous or colateral information to improve the behaviour of adaptive algorithms. The study is made on gradient-based methods due to the relatively simple and good performances that they use to exhibit. This paper shows that the complete knowledge of the data at the input of the adaptive filter (and in consequence of its autocorrelation matrix and its inverse) can be used to modify the classic L. M.S. algorithm leading to better expressions for the gradient and a new adaptive 'step size'. Finally, the description is completed with the comparison between the variation ranges and a natural generalization of 'step size' parameter is obtained.