Constructive approximate interpolation by neural networks

被引：62

作者：

Llanas, B ^{[1
]}

Sainz, FJ ^{[1
]}

机构：

[1] Univ Politecn Madrid, Dept Matemat Aplicada, ETSI Caminos, E-28040 Madrid, Spain

来源：

JOURNAL OF COMPUTATIONAL AND APPLIED MATHEMATICS | 2006年 / 188卷 / 02期

关键词：

neural networks; approximate interpolation; uniform approximation;

D O I：

10.1016/j.cam.2005.04.019

中图分类号：

O29 [应用数学];

学科分类号：

070104 ;

摘要：

We present a. type of single-hidden layer feedforward neural networks with sigmoidal nondecreasing activation function. We call them ai-nets. They can approximately interpolate, with arbitrary precision, any set of distinct data in one or several dimensions. They can uniformly approximate any continuous function of one variable and can be used for constructing uniform approximants of continuous functions of several variables. All these capabilities are based on a closed expression of the networks. (c) 2005 Elsevier B.V. All rights reserved.

引用

页码：283 / 308

页数：26

共 26 条

[1]

Anthony M., 1999, Neural Network Learning: Theoretical Foundations, V9

[2]

ANTHONY M, 1994, MATH PREPRINT SERIES, V73

[3] Single-iteration training algorithm for multi-layer feed-forward neural networks [J].

Barhen, J ;

Cogswell, R ;

Protopopescu, V .

NEURAL PROCESSING LETTERS, 2000, 11 (02) :113-129

[4] APPROXIMATION OF A FUNCTION AND ITS DERIVATIVE WITH A NEURAL NETWORK [J].

CARDALIAGUET, P ;

EUVRARD, G .

NEURAL NETWORKS, 1992, 5 (02) :207-220

[5]

Chen D., 1993, Approximation Theory and its Applications, V9, P17, DOI DOI 10.1007/BF02836480

[6]

Chen JY, 2001, ACTA PHARMACOL SIN, V22, P163

[7] Limitations of the approximation capabilities of neural networks with one hidden layer [J].

Chui, CK ;

Li, X ;

Mhaskar, HN .

ADVANCES IN COMPUTATIONAL MATHEMATICS, 1996, 5 (2-3) :233-243

[8]

CHUI CK, 1994, MATH COMPUT, V63, P607, DOI 10.1090/S0025-5718-1994-1240656-2

[9]

Duch W., 1999, Neural Computing Surveys, V2

[10] MULTILAYER FEEDFORWARD NETWORKS ARE UNIVERSAL APPROXIMATORS [J].

HORNIK, K ;

STINCHCOMBE, M ;

WHITE, H .

NEURAL NETWORKS, 1989, 2 (05) :359-366

← 1 2 3 →