An embedded sigmoidal neural network for modeling of nonlinear systems

J. Hu*, K. Hirasawa

*この研究の対応する著者

研究成果: Paper査読

2 被引用数 (Scopus)

抄録

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.

本文言語English
ページ1698-1703
ページ数6
出版ステータスPublished - 2001 1 1
外部発表はい
イベントInternational Joint Conference on Neural Networks (IJCNN'01) - Washington, DC, United States
継続期間: 2001 7 152001 7 19

Conference

ConferenceInternational Joint Conference on Neural Networks (IJCNN'01)
国/地域United States
CityWashington, DC
Period01/7/1501/7/19

ASJC Scopus subject areas

  • ソフトウェア
  • 人工知能

フィンガープリント

「An embedded sigmoidal neural network for modeling of nonlinear systems」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル