Neural nets for adaptive filtering and adaptive pattern recognition

Author

Widrow, B. ; Winter, Robert

Author_Institution

Dept. of Electr. Eng., Stanford Univ., CA, USA

Volume

21

Issue

3

fYear

1988

fDate

3/1/1988 12:00:00 AM

Firstpage

25

Lastpage

39

Abstract

The adaptive linear combiner (ALC) is described, and practical applications of the ALC in signal processing and pattern recognition are presented. Six signal processing examples are given, which are system modeling, statistical prediction, noise canceling, echo canceling, universe modeling, and channel equalization. Adaptive pattern recognition using neural nets is then discussed. The concept involves the use of an invariance net followed by a trainable classifier. It makes use of a multilayer adaptation algorithm that descrambles output and reproduces original patterns.<>

Keywords

adaptive systems; artificial intelligence; filtering and prediction theory; learning systems; neural nets; pattern recognition; signal processing; adaptive filtering; adaptive linear combiner; adaptive pattern recognition; artificial intelligence; channel equalization; echo canceling; invariance net; neural nets; noise canceling; signal processing; statistical prediction; system modeling; trainable classifier; universe modeling; Adaptive filters; Adaptive signal processing; Automatic logic units; Modeling; Multi-layer neural network; Neural networks; Noise cancellation; Pattern recognition; Predictive models; Signal processing algorithms;

fLanguage

English

Journal_Title

Computer

Publisher

ieee

ISSN

0018-9162

Type

jour

DOI

10.1109/2.29

Filename

29