Note: This content is accessible to all versions of every browser. However, this browser does not seem to support current Web standards, preventing the display of our site's design details.


On the Learning Mechanism of Adaptive Filters.

Adaptive filters are inherently nonlinear and time-variant devices that adjust themselves to an ever-changing environment; the structure of an adaptive system changes in such a way that its performance improves through a continuing interaction with its surroundings. The learning curve of an adaptive filter provides a reasonable measure of how fast and how well it reacts to its environment. This learning process has been extensively studied in the literature for slowly adapting systems. That is, for systems that employ infinitesimally small step-sizes. In this talk, we shall discuss several interesting phenomena that characterize the learning capabilities of adaptive filters when larger step-sizes are used. These phenomena actually occur even for slowly adapting systems but are less pronounced, which explains why they may have gone unnoticed. The phenomena however become significantly more pronounced for larger step-sizes and lead to several interesting observations. In particular, we shall show that an adaptive filter generally learns at a rate that is better than that predicted by least-mean-squares theory; that is, they seem to be smarter than we think. We shall also show that adaptive filters actually have two distinct rates of convergence; they learn at a slower rate initially and at a faster rate later (perhaps in a manner that mimics the human learning process). We shall also argue that special care is needed in interpreting learning curves. Several examples will be provided.

Type of Seminar:
Public Seminar
Assoc. Prof. Ali H. Sayed,
Rm 44-123-A Engr.IV Bldg Dept. Electrical Engineering , University of California Los Angeles, CA 90095-1594, USA
Sep 24, 1999   10:00

ETH-Zentrum, ETL K 25
Contact Person:

Prof. M. Morari
No downloadable files available.
Biographical Sketch:
Ali H. Sayed was born in Sao Paulo, Brazil. In 1981 he graduated in first place in the National Lebanese Baccalaureat, with the highest score in the history of the examination. In 1987 he received the degree of Engineer in Electrical Engineering from the University of Sao Paulo, Brazil, and was the first-place graduate of the School of Engineering. He was awarded the Institute of Engineering Prize (1987) and the Conde Armando Alvares Penteado Prize (1987). In 1989 he received, with distinction, the M.S. degree in Electrical Engineering from the University of São Paulo, Brazil, and in 1992 he received the Ph.D. degree in Electrical Engineering from Stanford University, Stanford, CA. In 1993 his Ph.D. thesis on structured algorithms in signal processing and mathematics received a special mention, among the three best Ph.D. thesis written during the period 1990-1992, for the Householder Prize in numerical algebra. From September 1992 to August 1993 he was a Research Associate with the Information Systems Laboratory at Stanford University, after which he joined, as an Assistant Professor, the Department of Electrical and Computer Engineering at the University of California, Santa Barbara, and was a member of the Center for Control Engineering and Computation (CCEC) and the Center for Information Processing Research (CIPR). Since July 1996 he has been an Associate Professor in the Department of Electrical Engineering at the University of California, Los Angeles. He is a member of the Signal Processing and Control fields of study. Dr. Sayed has over 80 publications., is a recipient of a 1994 NSF Research Initiation Award, and of the 1996 IEEE Donald G. Fink Prize Award. He is a member of IEEE, SIAM, and ILAS, and is an Associate Editor of the IEEE Transactions on Signal Processing. He is also working on several books and research monographs.