The estimate for approximation error of neural networks: A constructive approach

被引：65

作者：

Cao, Feilong ^{[1
]}

Xie, Tingfan ^{[1
]}

Xu, Zongben ^{[2
]}

机构：

[1] China Jiliang Univ, Dept Informat & Math Sci, Hangzhou 310018, Peoples R China

[2] Xian Jiaotong Univ, Inst Informat & Syst Sci, Xian 710049, Peoples R China

来源：

NEUROCOMPUTING | 2008年 / 71卷 / 4-6期

基金：

中国国家自然科学基金;

关键词：

neural networks; approximation; estimate of error;

D O I：

10.1016/j.neucom.2007.07.024

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Neural networks are widely used in many applications including astronomical physics, image processing, recognition, robotics and automated target tracking, etc. Their ability to approximate arbitrary functions is the main reason for this popularity. The main result of this paper is a constructive proof of a formula for the upper bound of the approximation error by feedforward neural networks with one hidden layer of sigmoidal units and a linear output. The result can also be used to estimate complexity of the maximum error network. An example to demonstrate the theoretical result is given. (c) 2007 Elsevier B.V. All rights reserved.

引用

页码：626 / 630

页数：5

共 15 条

[1] UNIVERSAL APPROXIMATION BOUNDS FOR SUPERPOSITIONS OF A SIGMOIDAL FUNCTION [J].

BARRON, AR .

IEEE TRANSACTIONS ON INFORMATION THEORY, 1993, 39 (03) :930-945

[2] SOME ANALYTICAL SOLUTIONS TO THE GENERAL APPROXIMATION PROBLEM FOR FEEDFORWARD NEURAL NETWORKS [J].

BULSARI, A .

NEURAL NETWORKS, 1993, 6 (07) :991-996

[3]

Cao FL, 2005, LECT NOTES COMPUT SC, V3496, P39

[4] UNIVERSAL APPROXIMATION TO NONLINEAR OPERATORS BY NEURAL NETWORKS WITH ARBITRARY ACTIVATION FUNCTIONS AND ITS APPLICATION TO DYNAMICAL-SYSTEMS [J].

CHEN, TP ;

CHEN, H .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1995, 6 (04) :911-917

[5] APPROXIMATION BY RIDGE FUNCTIONS AND NEURAL NETWORKS WITH ONE HIDDEN LAYER [J].

CHUI, CK ;

LI, X .

JOURNAL OF APPROXIMATION THEORY, 1992, 70 (02) :131-141

[6]

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

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

FUNAHASHI, K .

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

[8] UNIVERSAL APPROXIMATION OF AN UNKNOWN MAPPING AND ITS DERIVATIVES USING MULTILAYER FEEDFORWARD NETWORKS [J].

HORNIK, K ;

STINCHCOMBE, M ;

WHITE, H .

NEURAL NETWORKS, 1990, 3 (05) :551-560

[9]

Jones L. K, 1992, ANN STAT, V20, P765

[10]

Korain P, 1993, NEURAL NETWORKS, V6, P649

← 1 2 →