An embedded sigmoidal neural network for modeling of nonlinear systems

Takayuki Furuzuki, K. Hirasawa

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

This paper discusses the problem of applying sigmoidal neural network to prediction and control of nonlinear dynamical systems. Instead of directly using neural networks as nonlinear models, we first develop a shield based on application specific knowledge, and then embed sigmoidal neural network model in the shield. An embedded sigmoidal neural network model obtained in this way not only has a structure favorable for certain applications such as controller design, but also has useful interpretation on part of model parameters. Corresponding to the meaningful part and the meaningless part of model parameters, a hierarchical training algorithm consisting of two learning loops is introduced to train the model, which has good performance on solving local minimum problems. The usefulness of the proposed prediction model is demonstrated by applying it to prediction and control of a simulated nonlinear system.

Original languageEnglish
Title of host publicationProceedings of the International Joint Conference on Neural Networks
Pages1698-1703
Number of pages6
Volume3
Publication statusPublished - 2001
Externally publishedYes
EventInternational Joint Conference on Neural Networks (IJCNN'01) - Washington, DC
Duration: 2001 Jul 152001 Jul 19

Other

OtherInternational Joint Conference on Neural Networks (IJCNN'01)
CityWashington, DC
Period01/7/1501/7/19

Fingerprint

Nonlinear systems
Neural networks
Nonlinear dynamical systems
Controllers

ASJC Scopus subject areas

  • Software

Cite this

Furuzuki, T., & Hirasawa, K. (2001). An embedded sigmoidal neural network for modeling of nonlinear systems. In Proceedings of the International Joint Conference on Neural Networks (Vol. 3, pp. 1698-1703)

An embedded sigmoidal neural network for modeling of nonlinear systems. / Furuzuki, Takayuki; Hirasawa, K.

Proceedings of the International Joint Conference on Neural Networks. Vol. 3 2001. p. 1698-1703.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Furuzuki, T & Hirasawa, K 2001, An embedded sigmoidal neural network for modeling of nonlinear systems. in Proceedings of the International Joint Conference on Neural Networks. vol. 3, pp. 1698-1703, International Joint Conference on Neural Networks (IJCNN'01), Washington, DC, 01/7/15.
Furuzuki T, Hirasawa K. An embedded sigmoidal neural network for modeling of nonlinear systems. In Proceedings of the International Joint Conference on Neural Networks. Vol. 3. 2001. p. 1698-1703
Furuzuki, Takayuki ; Hirasawa, K. / An embedded sigmoidal neural network for modeling of nonlinear systems. Proceedings of the International Joint Conference on Neural Networks. Vol. 3 2001. pp. 1698-1703
@inproceedings{c2a31ef491044152b30be8b46e4b101c,
title = "An embedded sigmoidal neural network for modeling of nonlinear systems",
abstract = "This paper discusses the problem of applying sigmoidal neural network to prediction and control of nonlinear dynamical systems. Instead of directly using neural networks as nonlinear models, we first develop a shield based on application specific knowledge, and then embed sigmoidal neural network model in the shield. An embedded sigmoidal neural network model obtained in this way not only has a structure favorable for certain applications such as controller design, but also has useful interpretation on part of model parameters. Corresponding to the meaningful part and the meaningless part of model parameters, a hierarchical training algorithm consisting of two learning loops is introduced to train the model, which has good performance on solving local minimum problems. The usefulness of the proposed prediction model is demonstrated by applying it to prediction and control of a simulated nonlinear system.",
author = "Takayuki Furuzuki and K. Hirasawa",
year = "2001",
language = "English",
volume = "3",
pages = "1698--1703",
booktitle = "Proceedings of the International Joint Conference on Neural Networks",

}

TY - GEN

T1 - An embedded sigmoidal neural network for modeling of nonlinear systems

AU - Furuzuki, Takayuki

AU - Hirasawa, K.

PY - 2001

Y1 - 2001

N2 - This paper discusses the problem of applying sigmoidal neural network to prediction and control of nonlinear dynamical systems. Instead of directly using neural networks as nonlinear models, we first develop a shield based on application specific knowledge, and then embed sigmoidal neural network model in the shield. An embedded sigmoidal neural network model obtained in this way not only has a structure favorable for certain applications such as controller design, but also has useful interpretation on part of model parameters. Corresponding to the meaningful part and the meaningless part of model parameters, a hierarchical training algorithm consisting of two learning loops is introduced to train the model, which has good performance on solving local minimum problems. The usefulness of the proposed prediction model is demonstrated by applying it to prediction and control of a simulated nonlinear system.

AB - This paper discusses the problem of applying sigmoidal neural network to prediction and control of nonlinear dynamical systems. Instead of directly using neural networks as nonlinear models, we first develop a shield based on application specific knowledge, and then embed sigmoidal neural network model in the shield. An embedded sigmoidal neural network model obtained in this way not only has a structure favorable for certain applications such as controller design, but also has useful interpretation on part of model parameters. Corresponding to the meaningful part and the meaningless part of model parameters, a hierarchical training algorithm consisting of two learning loops is introduced to train the model, which has good performance on solving local minimum problems. The usefulness of the proposed prediction model is demonstrated by applying it to prediction and control of a simulated nonlinear system.

UR - http://www.scopus.com/inward/record.url?scp=0034870850&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034870850&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0034870850

VL - 3

SP - 1698

EP - 1703

BT - Proceedings of the International Joint Conference on Neural Networks

ER -