A novel neural network-based approach for designing digital filters

Author

Zhao, Hui ; Yu, Juebang

Author_Institution

Univ. of Electron. Sci. & Technol. of China, Chengdu, China

Volume

4

fYear

1997

fDate

9-12 Jun 1997

Firstpage

2272

Abstract

A novel digital filter design approach based upon Neural Network Optimization (NNO) technique is proposed in the present paper. To demonstrate the feasibility of the NNO design approach; a Continuous Hopfield Neural Network (CHNN) model is chosen and the relation between the MSE criterion and the Lyapunov function is also established. The implementation of the NNO digital filter design is described together with some design guidelines. A few linear phase FIR filter design examples are given and the advantages of the NNO approach over conventional design techniques are illustrated

Keywords

FIR filters; Hopfield neural nets; Lyapunov methods; circuit CAD; delay circuits; digital filters; filtering theory; iterative methods; optimisation; MSE criterion; continuous Hopfield neural network model; digital filter design; neural network optimization technique; neural network-based approach; Design optimization; Digital filters; Finite impulse response filter; Frequency response; Hafnium; Hopfield neural networks; Multidimensional signal processing; Neural networks; Radar signal processing; Sampling methods;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 1997. ISCAS '97., Proceedings of 1997 IEEE International Symposium on

Print_ISBN

0-7803-3583-X

Type

conf

DOI

10.1109/ISCAS.1997.612775

Filename

612775