Approximation to Boolean functions by neural networks with applications to thinning algorithms

Author

Shenshu, Xiong ; Zhaoying, Zhou ; Limin, Zhong ; Wendong, Zhang

Author_Institution

Dept. of Precision Instrum. & Mechanology, Tsinghua Univ., Beijing, China

Volume

2

fYear

2000

fDate

2000

Firstpage

1004

Abstract

In this paper, a theorem on approximation to Boolean functions by neural networks and its proof are proposed. A Boolean function, f:{0,1}n→{0,1} is proved to be approximated by a three layer neural network with 2ⁿ hidden nodes. With the theorem, a thinning algorithm using the neural network technique is concluded. A hard processor implementing the thinning algorithm is designed to raise the thinning efficiency, which can meet the practical needs better. This makes the algorithm suitable for real-time image processing

Keywords

Boolean functions; approximation theory; functional analysis; mathematics computing; neural nets; signal processing; Boolean functions; engineering applications; hidden nodes; neural networks; real-time image processing; thinning algorithms; thinning efficiency; three layer neural network; Algorithm design and analysis; Approximation algorithms; Boolean functions; Digital systems; Electronic mail; Image processing; Instruments; Mathematics; Neural networks; Piecewise linear approximation;

fLanguage

English

Publisher

ieee

Conference_Titel

Instrumentation and Measurement Technology Conference, 2000. IMTC 2000. Proceedings of the 17th IEEE

Conference_Location

Baltimore, MD

ISSN

1091-5281

Print_ISBN

0-7803-5890-2

Type

conf

DOI

10.1109/IMTC.2000.848892

Filename

848892