Identification and prediction of discrete chaotic maps applying a Chebyshev neural network

被引：24

作者：

Akritas, P

Antoniou, I

Ivanov, VV

机构：

[1] Int Solvay Inst Phys & Chem, B-1050 Brussels, Belgium

[2] Free Univ Brussels, Brussels, Belgium

[3] Joint Inst Nucl Res, Lab Comp Tech & Automat, Dubna 141980, Russia

来源：

CHAOS SOLITONS & FRACTALS | 2000年 / 11卷 / 1-3期

关键词：

Approximation theory - Feedforward neural networks - Learning systems - Multilayer neural networks - Polynomials;

D O I：

10.1016/S0960-0779(98)00302-6

中图分类号：

O1 [数学];

学科分类号：

0701 ; 070101 ;

摘要：

A new approach to reconstructing and predicting discrete chaotic maps is developed. It is based on the feed-forward neural network which decomposes the analyzed chaotic map in orthogonal Chebyshev polynomials. We show that the Chebyshev neural network (CNN) significantly exceeds the traditional multi-layer perceptron (MLP) in learning rate and in the accuracy of approximating an unknown map. (C) 1999 Elsevier Science Lid, All rights reserved.

引用

页码：337 / 344

页数：8

共 13 条

[1] ANTONIOU I, 1997, NONLINEAR WORLD, V4, P135
[2] A method for approximating one-dimensional functions
Basios, V
Bonushkina, AY
Ivanov, VV
[J]. COMPUTERS & MATHEMATICS WITH APPLICATIONS, 1997, 34 (7-8) : 687 - 693
[3] Berezin I.S., 1959, COMPUTING METHODS
[4] DENBY B, 1992, P 2 INT WORKSH SOFTW, P287
[5] IVANOV VV, 1995, NEW COMPUTING TECHNI, V4, P765
[6] Jackson E. A., 1989, Perspectives of Nonlinear Dynamics, V1
[7] JONES RD, 1990, FUNCTION APPROXIMATI, P90
[8] LAPEDES A, 1987, 872662 LAUR
[9] Lasota A., 1994, Applied Mathematical Sciences, V2nd
[10] PATTERN-RECOGNITION IN HIGH-ENERGY PHYSICS WITH ARTIFICIAL NEURAL NETWORKS - JETNET-2.0
LONNBLAD, L
PETERSON, C
ROGNVALDSSON, T
[J]. COMPUTER PHYSICS COMMUNICATIONS, 1992, 70 (01) : 167 - 182

← 1 2 →