Universal learning network and its application to chaos control

Kotaro Hirasawa, Xiaofeng Wang, Junichi Murata, Takayuki Furuzuki, Chunzhi Jin

Research output: Contribution to journalArticle

55 Citations (Scopus)

Abstract

Universal Learning Networks (ULNs) are proposed and their application to chaos control is discussed. ULNs provide a generalized framework to model and control complex systems. They consist of a number of inter-connected nodes where the nodes may have any continuously differentiable nonlinear functions in them and each pair of nodes can be connected by multiple branches with arbitrary time delays. Therefore, physical systems, which can be described by differential or difference equations and also their controllers, can be modeled in a unified way, and so ULNs may form a super set of neural networks and fuzzy neural networks. In order to optimize the ULNs, a generalized learning algorithm is derived, in which both the first order derivatives (gradients) and the higher order derivatives are incorporated. The derivatives are calculated by using forward or backward propagation schemes. These algorithms for calculating the derivatives are extended versions of Back Propagation Through Time (BPTT) and Real Time Recurrent Learning (RTRL) of Williams in the sense that generalized node functions, generalized network connections with multi-branch of arbitrary time delays, generalized criterion functions and higher order derivatives can be deal with. As an application of ULNs, a chaos control method using maximum Lyapunov exponent of ULNs is proposed. Maximum Lyapunov exponent of ULNs can be formulated by using higher order derivatives of ULNs, and the parameters of ULNs can be adjusted so that the maximum Lyapunov exponent approaches the target value. From the simulation results, it has been shown that a fully connected ULN with three nodes is able to display chaotic behaviors. Copyright (C) 2000 Elsevier Science Ltd.

Original languageEnglish
Pages (from-to)239-253
Number of pages15
JournalNeural Networks
Volume13
Issue number2
DOIs
Publication statusPublished - 2000 Mar
Externally publishedYes

Fingerprint

Chaos theory
Learning
Derivatives
Time delay
Fuzzy neural networks
Difference equations
Backpropagation
Learning algorithms
Large scale systems
Differential equations
Neural networks
Controllers

Keywords

  • Chaos
  • Higher order derivatives calculation
  • Lyapunov exponent
  • Neural networks
  • Universal learning networks

ASJC Scopus subject areas

  • Artificial Intelligence
  • Neuroscience(all)

Cite this

Universal learning network and its application to chaos control. / Hirasawa, Kotaro; Wang, Xiaofeng; Murata, Junichi; Furuzuki, Takayuki; Jin, Chunzhi.

In: Neural Networks, Vol. 13, No. 2, 03.2000, p. 239-253.

Research output: Contribution to journalArticle

Hirasawa, Kotaro ; Wang, Xiaofeng ; Murata, Junichi ; Furuzuki, Takayuki ; Jin, Chunzhi. / Universal learning network and its application to chaos control. In: Neural Networks. 2000 ; Vol. 13, No. 2. pp. 239-253.
@article{37b1745f2bee4077a8ce507cf56b6dc6,
title = "Universal learning network and its application to chaos control",
abstract = "Universal Learning Networks (ULNs) are proposed and their application to chaos control is discussed. ULNs provide a generalized framework to model and control complex systems. They consist of a number of inter-connected nodes where the nodes may have any continuously differentiable nonlinear functions in them and each pair of nodes can be connected by multiple branches with arbitrary time delays. Therefore, physical systems, which can be described by differential or difference equations and also their controllers, can be modeled in a unified way, and so ULNs may form a super set of neural networks and fuzzy neural networks. In order to optimize the ULNs, a generalized learning algorithm is derived, in which both the first order derivatives (gradients) and the higher order derivatives are incorporated. The derivatives are calculated by using forward or backward propagation schemes. These algorithms for calculating the derivatives are extended versions of Back Propagation Through Time (BPTT) and Real Time Recurrent Learning (RTRL) of Williams in the sense that generalized node functions, generalized network connections with multi-branch of arbitrary time delays, generalized criterion functions and higher order derivatives can be deal with. As an application of ULNs, a chaos control method using maximum Lyapunov exponent of ULNs is proposed. Maximum Lyapunov exponent of ULNs can be formulated by using higher order derivatives of ULNs, and the parameters of ULNs can be adjusted so that the maximum Lyapunov exponent approaches the target value. From the simulation results, it has been shown that a fully connected ULN with three nodes is able to display chaotic behaviors. Copyright (C) 2000 Elsevier Science Ltd.",
keywords = "Chaos, Higher order derivatives calculation, Lyapunov exponent, Neural networks, Universal learning networks",
author = "Kotaro Hirasawa and Xiaofeng Wang and Junichi Murata and Takayuki Furuzuki and Chunzhi Jin",
year = "2000",
month = "3",
doi = "10.1016/S0893-6080(99)00100-8",
language = "English",
volume = "13",
pages = "239--253",
journal = "Neural Networks",
issn = "0893-6080",
publisher = "Elsevier Limited",
number = "2",

}

TY - JOUR

T1 - Universal learning network and its application to chaos control

AU - Hirasawa, Kotaro

AU - Wang, Xiaofeng

AU - Murata, Junichi

AU - Furuzuki, Takayuki

AU - Jin, Chunzhi

PY - 2000/3

Y1 - 2000/3

N2 - Universal Learning Networks (ULNs) are proposed and their application to chaos control is discussed. ULNs provide a generalized framework to model and control complex systems. They consist of a number of inter-connected nodes where the nodes may have any continuously differentiable nonlinear functions in them and each pair of nodes can be connected by multiple branches with arbitrary time delays. Therefore, physical systems, which can be described by differential or difference equations and also their controllers, can be modeled in a unified way, and so ULNs may form a super set of neural networks and fuzzy neural networks. In order to optimize the ULNs, a generalized learning algorithm is derived, in which both the first order derivatives (gradients) and the higher order derivatives are incorporated. The derivatives are calculated by using forward or backward propagation schemes. These algorithms for calculating the derivatives are extended versions of Back Propagation Through Time (BPTT) and Real Time Recurrent Learning (RTRL) of Williams in the sense that generalized node functions, generalized network connections with multi-branch of arbitrary time delays, generalized criterion functions and higher order derivatives can be deal with. As an application of ULNs, a chaos control method using maximum Lyapunov exponent of ULNs is proposed. Maximum Lyapunov exponent of ULNs can be formulated by using higher order derivatives of ULNs, and the parameters of ULNs can be adjusted so that the maximum Lyapunov exponent approaches the target value. From the simulation results, it has been shown that a fully connected ULN with three nodes is able to display chaotic behaviors. Copyright (C) 2000 Elsevier Science Ltd.

AB - Universal Learning Networks (ULNs) are proposed and their application to chaos control is discussed. ULNs provide a generalized framework to model and control complex systems. They consist of a number of inter-connected nodes where the nodes may have any continuously differentiable nonlinear functions in them and each pair of nodes can be connected by multiple branches with arbitrary time delays. Therefore, physical systems, which can be described by differential or difference equations and also their controllers, can be modeled in a unified way, and so ULNs may form a super set of neural networks and fuzzy neural networks. In order to optimize the ULNs, a generalized learning algorithm is derived, in which both the first order derivatives (gradients) and the higher order derivatives are incorporated. The derivatives are calculated by using forward or backward propagation schemes. These algorithms for calculating the derivatives are extended versions of Back Propagation Through Time (BPTT) and Real Time Recurrent Learning (RTRL) of Williams in the sense that generalized node functions, generalized network connections with multi-branch of arbitrary time delays, generalized criterion functions and higher order derivatives can be deal with. As an application of ULNs, a chaos control method using maximum Lyapunov exponent of ULNs is proposed. Maximum Lyapunov exponent of ULNs can be formulated by using higher order derivatives of ULNs, and the parameters of ULNs can be adjusted so that the maximum Lyapunov exponent approaches the target value. From the simulation results, it has been shown that a fully connected ULN with three nodes is able to display chaotic behaviors. Copyright (C) 2000 Elsevier Science Ltd.

KW - Chaos

KW - Higher order derivatives calculation

KW - Lyapunov exponent

KW - Neural networks

KW - Universal learning networks

UR - http://www.scopus.com/inward/record.url?scp=0034000787&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034000787&partnerID=8YFLogxK

U2 - 10.1016/S0893-6080(99)00100-8

DO - 10.1016/S0893-6080(99)00100-8

M3 - Article

C2 - 10935763

AN - SCOPUS:0034000787

VL - 13

SP - 239

EP - 253

JO - Neural Networks

JF - Neural Networks

SN - 0893-6080

IS - 2

ER -