LMS algorithm with gradient descent filter length

Abstract

This letter presents a novel variable-length least mean square algorithm, whose filter length is adjusted dynamically along the negative gradient direction of the squared estimation error. Compared with other variable-length algorithms, the proposed algorithm has faster convergence and more robust performance in diverse environments.

3 Figures and Tables

Cite this paper

@article{Gu2004LMSAW, title={LMS algorithm with gradient descent filter length}, author={Yuantao Gu and Kun Tang and Huijuan Cui}, journal={IEEE Signal Processing Letters}, year={2004}, volume={11}, pages={305-307} }