Mixed time scale recursive algorithms

Author

Bucklew, James A. ; Kurtz, Thomas G.

Author_Institution

Dept. of Electr. & Comput. Eng., Wisconsin Univ., Madison, WI, USA

Volume

49

Issue

8

fYear

2001

fDate

8/1/2001 12:00:00 AM

Firstpage

1824

Lastpage

1830

Abstract

We investigate the behavior of certain types of mixed time scale adaptive algorithms. These systems comprise a “fast” or quickly changing algorithm mutually coupled to a “slow” or slowly changing algorithm. They arise naturally in a variety of adaptive environments such as in IIR system identification, the training of recurrent neural networks, decision feedback equalization, and others. [These algorithms (despite their title) should not be confused with the mixed time scales of wavelet transforms or other algorithms associated with multiresolution signal processing]. We give conditions for when the system can be analyzed from the framework of a simpler “frozen state” system. This analysis extends some of the previous work of Solo (1995) and his coworkers

Keywords

IIR filters; adaptive signal processing; decision feedback equalisers; filtering theory; identification; learning (artificial intelligence); recurrent neural nets; recursive estimation; IIR filter; IIR system identification; Monte Carlo simulation; decision feedback equalization; frozen state system; limiting differential equation behavior; mixed time scale adaptive algorithms; mixed time scale recursive algorithms; quickly changing algorithm; recurrent neural networks training; slowly changing algorithm; Adaptive algorithm; Algorithm design and analysis; Books; Equations; Mutual coupling; Signal processing algorithms; Signal resolution; System identification; Wavelet analysis; Wavelet transforms;

fLanguage

English

Journal_Title

Signal Processing, IEEE Transactions on

Publisher

ieee

ISSN

1053-587X

Type

jour

DOI

10.1109/78.934153

Filename

934153