APPROXIMATION CAPABILITY TO FUNCTIONS OF SEVERAL VARIABLES, NONLINEAR FUNCTIONALS, AND OPERATORS BY RADIAL BASIS FUNCTION NEURAL NETWORKS

被引：300

作者：

CHEN, TP ^{[1
]}

CHEN, H ^{[1
]}

机构：

[1] SUN MICROSYST INC,MT VIEW,CA 95050

来源：

IEEE TRANSACTIONS ON NEURAL NETWORKS | 1995年 / 6卷 / 04期

基金：

中国国家自然科学基金;

关键词：

D O I：

10.1109/72.392252

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 [模式识别与智能系统]; 0812 [计算机科学与技术]; 0835 [软件工程]; 1405 [智能科学与技术];

摘要：

The purpose of this paper is to explore the representation capability of radial basis function (RBF) neural networks. The main results are: 1) the necessary and sufficient condition for a function of one variable to be qualified as an activation function in RBF network is that the function is not an even polynomial, and 2) the capability of approximation to nonlinear functionals and operators by RBF networks is revealed, using sample data either in frequency domain or in time domain, which can be used in system identification by neural networks.

引用

页码：904 / 910

页数：7

共 24 条

[1]

Carroll S M, 1989, P IJCNN P, P607

[2]

CHEN T, 1995, IEEE T NEURAL NETWOR, V6

[3]

CHEN T, 1990, COMPUTING SCI STATIS, P163

[4]

CHEN T, IN PRESS CHINESE ANN

[5]

CHEN T, 1993, IEEE T NEURAL NETWOR, V4

[6]

CHEN T, 1992, KEXUE TONGBAO

[7]

Cybenko G., 1989, Mathematics of Control, Signals, and Systems, V2, P303, DOI 10.1007/BF02551274

[8]

DIEDONNE J, 1969, F MODERN ANAL, P142

[9]

ON THE APPROXIMATE REALIZATION OF CONTINUOUS-MAPPINGS BY NEURAL NETWORKS [J].

FUNAHASHI, K .

NEURAL NETWORKS, 1989, 2 (03) :183-192

[10]

GIROSI F, 1989, MIT1164 ART INT LAB

← 1 2 3 →