Universal Learning Network and its application systems

Kotaro Hirasawa, Masanao Ohbayashi, Junichi Murata

Research output: Contribution to journalArticle

Abstract

Universal Learning Network(ULN) and its application to control systems are discussed. In ULN, any kinds of nonlinearly operated nodes with a continuously differentiable function are connected to each other by multi-branches that may have arbitrary time delays including zero or minus ones. A generalized learning algorithm is proposed, which can be applied to any kinds of networks including static or dynamic networks, feedforward or recurrent networks, time delay neural networks and networks with multi-branches. One of the most important features of ULN is the use of the higher order derivatives. As for the application of ULN, control problems such as robust control and chaotic control are studied using second order derivatives and it is shown that the second order derivatives are effective tools to realize the sophisticated robust control and chaotic control in the nonlinear systems.

Original languageEnglish
Pages (from-to)14-29
Number of pages16
JournalResearch Reports on Information Science and Electrical Engineering of Kyushu University
Volume2
Issue number1
Publication statusPublished - Mar 1997
Externally publishedYes

Fingerprint

Robust control
Derivatives
Time delay
Learning algorithms
Nonlinear systems
Neural networks
Control systems

All Science Journal Classification (ASJC) codes

  • Hardware and Architecture
  • Engineering (miscellaneous)
  • Electrical and Electronic Engineering

Cite this

Universal Learning Network and its application systems. / Hirasawa, Kotaro; Ohbayashi, Masanao; Murata, Junichi.

In: Research Reports on Information Science and Electrical Engineering of Kyushu University, Vol. 2, No. 1, 03.1997, p. 14-29.

Research output: Contribution to journalArticle

@article{9dda658e33d34a34bc008fe2cb75118a,
title = "Universal Learning Network and its application systems",
abstract = "Universal Learning Network(ULN) and its application to control systems are discussed. In ULN, any kinds of nonlinearly operated nodes with a continuously differentiable function are connected to each other by multi-branches that may have arbitrary time delays including zero or minus ones. A generalized learning algorithm is proposed, which can be applied to any kinds of networks including static or dynamic networks, feedforward or recurrent networks, time delay neural networks and networks with multi-branches. One of the most important features of ULN is the use of the higher order derivatives. As for the application of ULN, control problems such as robust control and chaotic control are studied using second order derivatives and it is shown that the second order derivatives are effective tools to realize the sophisticated robust control and chaotic control in the nonlinear systems.",
author = "Kotaro Hirasawa and Masanao Ohbayashi and Junichi Murata",
year = "1997",
month = "3",
language = "English",
volume = "2",
pages = "14--29",
journal = "Research Reports on Information Science and Electrical Engineering of Kyushu University",
issn = "1342-3819",
publisher = "Kyushu University, Faculty of Science",
number = "1",

}

TY - JOUR

T1 - Universal Learning Network and its application systems

AU - Hirasawa, Kotaro

AU - Ohbayashi, Masanao

AU - Murata, Junichi

PY - 1997/3

Y1 - 1997/3

N2 - Universal Learning Network(ULN) and its application to control systems are discussed. In ULN, any kinds of nonlinearly operated nodes with a continuously differentiable function are connected to each other by multi-branches that may have arbitrary time delays including zero or minus ones. A generalized learning algorithm is proposed, which can be applied to any kinds of networks including static or dynamic networks, feedforward or recurrent networks, time delay neural networks and networks with multi-branches. One of the most important features of ULN is the use of the higher order derivatives. As for the application of ULN, control problems such as robust control and chaotic control are studied using second order derivatives and it is shown that the second order derivatives are effective tools to realize the sophisticated robust control and chaotic control in the nonlinear systems.

AB - Universal Learning Network(ULN) and its application to control systems are discussed. In ULN, any kinds of nonlinearly operated nodes with a continuously differentiable function are connected to each other by multi-branches that may have arbitrary time delays including zero or minus ones. A generalized learning algorithm is proposed, which can be applied to any kinds of networks including static or dynamic networks, feedforward or recurrent networks, time delay neural networks and networks with multi-branches. One of the most important features of ULN is the use of the higher order derivatives. As for the application of ULN, control problems such as robust control and chaotic control are studied using second order derivatives and it is shown that the second order derivatives are effective tools to realize the sophisticated robust control and chaotic control in the nonlinear systems.

UR - http://www.scopus.com/inward/record.url?scp=5844323456&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=5844323456&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:5844323456

VL - 2

SP - 14

EP - 29

JO - Research Reports on Information Science and Electrical Engineering of Kyushu University

JF - Research Reports on Information Science and Electrical Engineering of Kyushu University

SN - 1342-3819

IS - 1

ER -