Neural network with node gates and its application to nonlinear system control

Junichi Murata, Tomohide Kakihara, Masaki Fujimoto, Kotaro Hirasawa

Research output: Contribution to journalArticle

Abstract

Neural networks with node gates are proposed to solve complicated or large problems with `divide and conquer' approach. Each hidden node of the network has a node gate on its output channel which controls the flow of the output from the node. By opening and closing depending on situations, the node gates form a sub-network dynamically which gives the solution suited for the current situation. When the situation changes, the gate openings are also changed accordingly, and a different sub-network will emerge to give a new solution. In the paper, a mechanism that controls the gate opening is proposed as well as the learning method of the network weights and the parameters contained in the gates. The network is applied to nonlinear system control problem where a number of different situations occur and demand for different control strategies. The results show that the proposed network can deal with the change of the situations appropriately.

Original languageEnglish
Pages (from-to)243-248
Number of pages6
JournalResearch Reports on Information Science and Electrical Engineering of Kyushu University
Volume5
Issue number2
Publication statusPublished - Sep 2000

Fingerprint

Nonlinear control systems
Neural networks

All Science Journal Classification (ASJC) codes

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

Cite this

Neural network with node gates and its application to nonlinear system control. / Murata, Junichi; Kakihara, Tomohide; Fujimoto, Masaki; Hirasawa, Kotaro.

In: Research Reports on Information Science and Electrical Engineering of Kyushu University, Vol. 5, No. 2, 09.2000, p. 243-248.

Research output: Contribution to journalArticle

@article{57767555d52d44f7b78a3a502260b216,
title = "Neural network with node gates and its application to nonlinear system control",
abstract = "Neural networks with node gates are proposed to solve complicated or large problems with `divide and conquer' approach. Each hidden node of the network has a node gate on its output channel which controls the flow of the output from the node. By opening and closing depending on situations, the node gates form a sub-network dynamically which gives the solution suited for the current situation. When the situation changes, the gate openings are also changed accordingly, and a different sub-network will emerge to give a new solution. In the paper, a mechanism that controls the gate opening is proposed as well as the learning method of the network weights and the parameters contained in the gates. The network is applied to nonlinear system control problem where a number of different situations occur and demand for different control strategies. The results show that the proposed network can deal with the change of the situations appropriately.",
author = "Junichi Murata and Tomohide Kakihara and Masaki Fujimoto and Kotaro Hirasawa",
year = "2000",
month = "9",
language = "English",
volume = "5",
pages = "243--248",
journal = "Research Reports on Information Science and Electrical Engineering of Kyushu University",
issn = "1342-3819",
publisher = "Kyushu University, Faculty of Science",
number = "2",

}

TY - JOUR

T1 - Neural network with node gates and its application to nonlinear system control

AU - Murata, Junichi

AU - Kakihara, Tomohide

AU - Fujimoto, Masaki

AU - Hirasawa, Kotaro

PY - 2000/9

Y1 - 2000/9

N2 - Neural networks with node gates are proposed to solve complicated or large problems with `divide and conquer' approach. Each hidden node of the network has a node gate on its output channel which controls the flow of the output from the node. By opening and closing depending on situations, the node gates form a sub-network dynamically which gives the solution suited for the current situation. When the situation changes, the gate openings are also changed accordingly, and a different sub-network will emerge to give a new solution. In the paper, a mechanism that controls the gate opening is proposed as well as the learning method of the network weights and the parameters contained in the gates. The network is applied to nonlinear system control problem where a number of different situations occur and demand for different control strategies. The results show that the proposed network can deal with the change of the situations appropriately.

AB - Neural networks with node gates are proposed to solve complicated or large problems with `divide and conquer' approach. Each hidden node of the network has a node gate on its output channel which controls the flow of the output from the node. By opening and closing depending on situations, the node gates form a sub-network dynamically which gives the solution suited for the current situation. When the situation changes, the gate openings are also changed accordingly, and a different sub-network will emerge to give a new solution. In the paper, a mechanism that controls the gate opening is proposed as well as the learning method of the network weights and the parameters contained in the gates. The network is applied to nonlinear system control problem where a number of different situations occur and demand for different control strategies. The results show that the proposed network can deal with the change of the situations appropriately.

UR - http://www.scopus.com/inward/record.url?scp=0034267271&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034267271&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0034267271

VL - 5

SP - 243

EP - 248

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 - 2

ER -