Topological properties of least-squares error surfaces for adaptive IIR filters

Virginia L. Stonick

doi:10.1117/12.130948

30 November 1992 Topological properties of least-squares error surfaces for adaptive IIR filters

Virginia L. Stonick

Proceedings Volume 1770, Advanced Signal Processing Algorithms, Architectures, and Implementations III; (1992) https://doi.org/10.1117/12.130948
Event: San Diego '92, 1992, San Diego, CA, United States

Abstract

In this paper, a new framework for understanding the performance of adaptive IIR filters is proposed and shown to enhance the understanding of filter stability during adaptation in time- varying data environments. This new understanding arises from considering the error surface as defined by the data, rather than the statistics of the data, in a manner analogous to that used to develop recursive least squares (RLS) FIR adaptive filters. The stability of the filter is shown to be dependent on the problem formulation. Defining the time-varying error surface using frequency domain, rather than time domain, methods is shown to result in substantially better stability structure in the performance surface.

Citation Download Citation

Virginia L. Stonick "Topological properties of least-squares error surfaces for adaptive IIR filters", Proc. SPIE 1770, Advanced Signal Processing Algorithms, Architectures, and Implementations III, (30 November 1992); https://doi.org/10.1117/12.130948

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available