Multiresolution learning paradigm and signal prediction

Author

Liang, Yao ; Page, Edward W.

Author_Institution

Dept. of Comput. Sci., Clemson Univ., SC, USA

Volume

45

Issue

11

fYear

1997

fDate

11/1/1997 12:00:00 AM

Firstpage

2858

Lastpage

2864

Abstract

Current neural network learning processes, regardless of the learning algorithm and preprocessing used, are sometimes inadequate for difficult problems. We present a new learning concept and paradigm for neural networks, called multiresolution learning, based on multiresolution analysis in wavelet theory. The multiresolution learning paradigm can significantly improve the generalization performance of neural networks

Keywords

learning (artificial intelligence); neural nets; prediction theory; signal representation; signal resolution; sunspots; telecommunication traffic; time series; wavelet transforms; generalization performance; high-speed network traffic prediction; learning algorithm; multiresolution analysis; multiresolution learning paradigm; neural network learning; preprocessing; signal prediction; sunspot series; time series forecasting; wavelet representation; wavelet theory; AWGN; Adaptive equalizers; Biological neural networks; Digital communication; Digital magnetic recording; Intersymbol interference; Recurrent neural networks; Signal processing; Signal processing algorithms; Signal resolution;

fLanguage

English

Journal_Title

Signal Processing, IEEE Transactions on

Publisher

ieee

ISSN

1053-587X

Type

jour

DOI

10.1109/78.650113

Filename

650113