Chaos control on Universal Learning Network

Masaru Koga, Kotaro Hirasawa, Junichi Murata, Masanao Ohbayashi

Research output: Contribution to journalArticle

Abstract

A method is proposed for controlling chaotic phenomena on Universal Learning Network (U.L.N.). Generation and die-out of chaotic phenomena are realized by changing Lyapunov Number of U.L.N. to positive and negative value respectively, which is accomplished by adjusting U.L.N. parameters so as to minimize a criterion function that is the difference between the desired Lyapunov Number and its actual value. Both a gradient method utilizing second order derivatives of U.L.N. and a random search method are adopted to optimize the parameters.

Original languageEnglish
Pages (from-to)15-33
Number of pages19
JournalMemoirs of the Kyushu University, Faculty of Engineering
Volume56
Issue number1
Publication statusPublished - Mar 1 1996
Externally publishedYes

Fingerprint

Gradient methods
chaotic dynamics
Chaos theory
learning
Derivatives
Chaos control
Learning networks
method
parameter

All Science Journal Classification (ASJC) codes

  • Energy(all)
  • Atmospheric Science
  • Earth and Planetary Sciences(all)
  • Management of Technology and Innovation

Cite this

Chaos control on Universal Learning Network. / Koga, Masaru; Hirasawa, Kotaro; Murata, Junichi; Ohbayashi, Masanao.

In: Memoirs of the Kyushu University, Faculty of Engineering, Vol. 56, No. 1, 01.03.1996, p. 15-33.

Research output: Contribution to journalArticle

Koga, M, Hirasawa, K, Murata, J & Ohbayashi, M 1996, 'Chaos control on Universal Learning Network', Memoirs of the Kyushu University, Faculty of Engineering, vol. 56, no. 1, pp. 15-33.
Koga, Masaru ; Hirasawa, Kotaro ; Murata, Junichi ; Ohbayashi, Masanao. / Chaos control on Universal Learning Network. In: Memoirs of the Kyushu University, Faculty of Engineering. 1996 ; Vol. 56, No. 1. pp. 15-33.
@article{6c6340582de742f8ab950220374ea5c1,
title = "Chaos control on Universal Learning Network",
abstract = "A method is proposed for controlling chaotic phenomena on Universal Learning Network (U.L.N.). Generation and die-out of chaotic phenomena are realized by changing Lyapunov Number of U.L.N. to positive and negative value respectively, which is accomplished by adjusting U.L.N. parameters so as to minimize a criterion function that is the difference between the desired Lyapunov Number and its actual value. Both a gradient method utilizing second order derivatives of U.L.N. and a random search method are adopted to optimize the parameters.",
author = "Masaru Koga and Kotaro Hirasawa and Junichi Murata and Masanao Ohbayashi",
year = "1996",
month = "3",
day = "1",
language = "English",
volume = "56",
pages = "15--33",
journal = "Memoirs of the Faculty of Engineering, Kyushu University",
issn = "1345-868X",
publisher = "Kyushu University, Faculty of Science",
number = "1",

}

TY - JOUR

T1 - Chaos control on Universal Learning Network

AU - Koga, Masaru

AU - Hirasawa, Kotaro

AU - Murata, Junichi

AU - Ohbayashi, Masanao

PY - 1996/3/1

Y1 - 1996/3/1

N2 - A method is proposed for controlling chaotic phenomena on Universal Learning Network (U.L.N.). Generation and die-out of chaotic phenomena are realized by changing Lyapunov Number of U.L.N. to positive and negative value respectively, which is accomplished by adjusting U.L.N. parameters so as to minimize a criterion function that is the difference between the desired Lyapunov Number and its actual value. Both a gradient method utilizing second order derivatives of U.L.N. and a random search method are adopted to optimize the parameters.

AB - A method is proposed for controlling chaotic phenomena on Universal Learning Network (U.L.N.). Generation and die-out of chaotic phenomena are realized by changing Lyapunov Number of U.L.N. to positive and negative value respectively, which is accomplished by adjusting U.L.N. parameters so as to minimize a criterion function that is the difference between the desired Lyapunov Number and its actual value. Both a gradient method utilizing second order derivatives of U.L.N. and a random search method are adopted to optimize the parameters.

UR - http://www.scopus.com/inward/record.url?scp=0030102098&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030102098&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0030102098

VL - 56

SP - 15

EP - 33

JO - Memoirs of the Faculty of Engineering, Kyushu University

JF - Memoirs of the Faculty of Engineering, Kyushu University

SN - 1345-868X

IS - 1

ER -