Adaptive bound reduced-form genetic algorithms for B-spline neural network training

Wei Yen Wang, Chin Wang Tao, Chen Guan Chang

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

In this paper, an adaptive bound reduced-form genetic algorithm (ABRGA) to tune the control points of B-spline neural networks is proposed. It is developed not only to search for the optimal control points but also to adaptively tune the bounds of the control points of the B-spline neural networks by enlarging the search space of the control points. To improve the searching speed of the reduced-form genetic algorithm (RGA), the ABRGA is derived, in which better bounds of control points of B-spline neural networks are determined and paralleled with the optimal control points searched. It is shown that better efficiency is obtained if the bounds of control points are adjusted properly for the RGA-based B-spline neural networks.

Original languageEnglish
Pages (from-to)2479-2488
Number of pages10
JournalIEICE Transactions on Information and Systems
VolumeE87-D
Issue number11
Publication statusPublished - 2004 Nov

Fingerprint

Splines
Genetic algorithms
Neural networks

Keywords

  • Adaptive bounds
  • B-spline neural networks
  • Nonlinear function approximation
  • Reduced-form genetic algorithms

ASJC Scopus subject areas

  • Software
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering
  • Artificial Intelligence

Cite this

Adaptive bound reduced-form genetic algorithms for B-spline neural network training. / Wang, Wei Yen; Tao, Chin Wang; Chang, Chen Guan.

In: IEICE Transactions on Information and Systems, Vol. E87-D, No. 11, 11.2004, p. 2479-2488.

Research output: Contribution to journalArticle

@article{416b74ecba7941c68a8ad6fcfea29341,
title = "Adaptive bound reduced-form genetic algorithms for B-spline neural network training",
abstract = "In this paper, an adaptive bound reduced-form genetic algorithm (ABRGA) to tune the control points of B-spline neural networks is proposed. It is developed not only to search for the optimal control points but also to adaptively tune the bounds of the control points of the B-spline neural networks by enlarging the search space of the control points. To improve the searching speed of the reduced-form genetic algorithm (RGA), the ABRGA is derived, in which better bounds of control points of B-spline neural networks are determined and paralleled with the optimal control points searched. It is shown that better efficiency is obtained if the bounds of control points are adjusted properly for the RGA-based B-spline neural networks.",
keywords = "Adaptive bounds, B-spline neural networks, Nonlinear function approximation, Reduced-form genetic algorithms",
author = "Wang, {Wei Yen} and Tao, {Chin Wang} and Chang, {Chen Guan}",
year = "2004",
month = "11",
language = "English",
volume = "E87-D",
pages = "2479--2488",
journal = "IEICE Transactions on Information and Systems",
issn = "0916-8532",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "11",

}

TY - JOUR

T1 - Adaptive bound reduced-form genetic algorithms for B-spline neural network training

AU - Wang, Wei Yen

AU - Tao, Chin Wang

AU - Chang, Chen Guan

PY - 2004/11

Y1 - 2004/11

N2 - In this paper, an adaptive bound reduced-form genetic algorithm (ABRGA) to tune the control points of B-spline neural networks is proposed. It is developed not only to search for the optimal control points but also to adaptively tune the bounds of the control points of the B-spline neural networks by enlarging the search space of the control points. To improve the searching speed of the reduced-form genetic algorithm (RGA), the ABRGA is derived, in which better bounds of control points of B-spline neural networks are determined and paralleled with the optimal control points searched. It is shown that better efficiency is obtained if the bounds of control points are adjusted properly for the RGA-based B-spline neural networks.

AB - In this paper, an adaptive bound reduced-form genetic algorithm (ABRGA) to tune the control points of B-spline neural networks is proposed. It is developed not only to search for the optimal control points but also to adaptively tune the bounds of the control points of the B-spline neural networks by enlarging the search space of the control points. To improve the searching speed of the reduced-form genetic algorithm (RGA), the ABRGA is derived, in which better bounds of control points of B-spline neural networks are determined and paralleled with the optimal control points searched. It is shown that better efficiency is obtained if the bounds of control points are adjusted properly for the RGA-based B-spline neural networks.

KW - Adaptive bounds

KW - B-spline neural networks

KW - Nonlinear function approximation

KW - Reduced-form genetic algorithms

UR - http://www.scopus.com/inward/record.url?scp=10444221738&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=10444221738&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:10444221738

VL - E87-D

SP - 2479

EP - 2488

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

SN - 0916-8532

IS - 11

ER -