Adaptive processing with neural network controlled resonator-banks

Author

Sztipanovits, Janos

Author_Institution

Dept. of Electr. Eng., Vanderbilt Univ., Nashville, TN, USA

Volume

37

Issue

11

fYear

1990

fDate

11/1/1990 12:00:00 AM

Firstpage

1436

Lastpage

1440

Abstract

A structurally adaptive processing system that can dynamically change its transfer characteristics as a response to changes in the environment is described. The neural network controlled resonator-bank architecture consists of two main components, a resonator-bank filter structure and a neural network that controls the transfer characteristics of the filter. The architecture offers an attractive alternative for the approximation of time-variant nonlinear dynamics having a finite number of stable operating points with quasi-linear characteristics

Keywords

adaptive filters; digital filters; filtering and prediction theory; neural nets; resonators; signal processing; approximation; neural network controlled resonator-banks; quasi-linear characteristics; resonator-bank filter structure; stable operating points; structurally adaptive processing system; time-variant nonlinear dynamics; training methods; transfer characteristics; Adaptive control; Adaptive systems; Circuit theory; Circuits and systems; Control systems; Filters; Network synthesis; Neural networks; Programmable control; Reflection;

fLanguage

English

Journal_Title

Circuits and Systems, IEEE Transactions on

Publisher

ieee

ISSN

0098-4094

Type

jour

DOI

10.1109/31.62419

Filename

62419