Title :
A novel neural network-based approach for designing 2-D FIR filters
Author :
Zhao, Hui ; Yu, Juebang
Author_Institution :
Univ. of Electron. Sci. & Technol. of China, Chengdu, China
fDate :
11/1/1997 12:00:00 AM
Abstract :
A novel 2-D FIR filter design approach based on neural network optimization (NNO) technique is proposed in the present letter. To demonstrate the feasibility of the NNO design approach, a Tank-Hopfield neural network (THNN) model is chosen and the relation between the MSE (mean square error) criterion and the Lyapunov energy function is also established. The implementation of the approach is described together with some design guidelines. Two 2-D FIR filter design examples are given, and the advantages of the NNO approach over conventional methods are illustrated
Keywords :
FIR filters; Hopfield neural nets; Lyapunov methods; circuit optimisation; circuit stability; frequency response; low-pass filters; network synthesis; two-dimensional digital filters; 2-D FIR filter design; Lyapunov energy function; Tank-Hopfield neural network; design guidelines; frequency response; mean square error criterion; neural network optimization technique; square low-pass filter; Design methodology; Design optimization; Discrete Fourier transforms; Finite impulse response filter; Frequency response; Guidelines; Neural networks; Sampling methods; Signal design; Signal processing;
Journal_Title :
Circuits and Systems I: Fundamental Theory and Applications, IEEE Transactions on
