Design of digital differentiators and Hilbert transformers by feedback neural networks

Author

Bhattacharya, D. ; Antoniou, A.

Author_Institution

Dept. of Electr. & Comput. Eng., Victoria Univ., BC, Canada

fYear

1995

fDate

17-19 May 1995

Firstpage

489

Lastpage

492

Abstract

A Hopfield-type neural network is proposed for the design of nonrecursive digital differentiators and Hilbert transformers. Given the amplitude response, the all-analog network computes the filter coefficients in real time. The network is simulated and a few examples are included to show that this is an efficient way of solving the approximation problem and has a high potential for implementation in analog VLSI

Keywords

FIR filters; Hilbert transforms; Hopfield neural nets; VLSI; analogue processing circuits; delay circuits; differentiating circuits; filtering theory; Hilbert transformers; Hopfield-type neural network; all-analog network; amplitude response; analog VLSI; approximation problem solution; digital differentiators design; feedback neural networks; filter coefficients; nonrecursive digital differentiators; Computer networks; Cost function; Finite impulse response filter; Frequency; Hopfield neural networks; Neural networks; Neurofeedback; Neurons; Transformers; Very large scale integration;

fLanguage

English

Publisher

ieee

Conference_Titel

Communications, Computers, and Signal Processing, 1995. Proceedings., IEEE Pacific Rim Conference on

Conference_Location

Victoria, BC

Print_ISBN

0-7803-2553-2

Type

conf

DOI

10.1109/PACRIM.1995.519576

Filename

519576