Proceedings of 1994 28th Asilomar Conference on Signals, Systems and Computers (1994)

Pacific Grove, CA, USA

Oct. 31, 1994 to Nov. 2, 1994

ISSN: 1058-6393

ISBN: 0-8186-6405-3

pp: 627-631

J.C.M. Bermudez , Dept. of Electr. Eng., Fed. Univ. of Santa Catarina, Florianopolis, Brazil

N.J. Bershad , Dept. of Electr. Eng., Fed. Univ. of Santa Catarina, Florianopolis, Brazil

ABSTRACT

This paper extends conditional moment techniques previously developed for the study of nonlinear versions of the LMS algorithm to the study of the effects of quantizers in the finite precision case. Deterministic nonlinear recursions are derived for the mean and second moment matrix of the weight vector about the Wiener weight for white Gaussian data models and small algorithm step sizes /spl mu/. These recursions are solved numerically and shown to be in very close agreement with Monte Carlo simulations. Simulation examples are presented which demonstrate the accuracy of the theory in predicting the transient behavior and cancellation performance in steady-state for the quantized LMS algorithm.<>

INDEX TERMS

least mean squares methods, quantisation (signal), data structures, convergence of numerical methods, method of moments, matrix algebra, transient analysis, adaptive signal processing, white noise, Gaussian noise

CITATION

J. Bermudez and N. Bershad, "Nonlinear quantization effects an the LMS algorithm-analytical models for the MSE transient and convergence behavior,"

*Proceedings of 1994 28th Asilomar Conference on Signals, Systems and Computers(ACSSC)*, Pacific Grove, CA, USA, 1995, pp. 627-631.

doi:10.1109/ACSSC.1994.471528

CITATIONS