Universal approximation of multiple nonlinear operators by neural networks

被引：19

作者：

Back, AD ^{[1
]}

Chen, TP

机构：

[1] Windale Technol, Brisbane, Qld 4075, Australia

[2] Fudan Univ, Dept Math, Shanghai 200433, Peoples R China

来源：

NEURAL COMPUTATION | 2002年 / 14卷 / 11期

关键词：

D O I：

10.1162/089976602760407964

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Recently, there has been interest in the observed capabilities of some classes of neural networks with fixed weights to model multiple nonlinear dynamical systems. While this property has been observed in simulations, open questions exist as to how this property can arise. In this article, we propose a theory that provides a possible mechanism by which this multiple modeling phenomenon can occur.

引用

页码：2561 / 2566

页数：6

共 19 条

[1]

BACK A, 1998, P 1997 INT C NEUR IN, V1, P326

[2]

BRANICKY M, 1996, STUDIES HYBRID SYSTE

[3]

BRANICKY MS, 1994, LIDSP223 DEP EL ENG

[4]

BROCKETT RW, 1993, PROG SYST C, V14, P29

[5] APPROXIMATIONS OF CONTINUOUS FUNCTIONALS BY NEURAL NETWORKS WITH APPLICATION TO DYNAMIC-SYSTEMS [J].

CHEN, TP ;

CHEN, H .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1993, 4 (06) :910-918

[6] 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

[7] Adaptive behavior from fixed weight networks [J].

Feldkamp, LA ;

Puskorius, GV ;

Moore, PC .

INFORMATION SCIENCES, 1997, 98 (1-4) :217-235

[8]

Hochreiter S, 1997, NEURAL COMPUT, V9, P1735, DOI [10.1162/neco.1997.9.1.1, 10.1007/978-3-642-24797-2]

[9]

Hochreiter S, 2001, LECT NOTES COMPUT SC, V2130, P87

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

HORNIK, K ;

STINCHCOMBE, M ;

WHITE, H .

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

← 1 2 →