Identification of nonlinear black-box systems based on Universal Learning Networks

Jinglu Hu, Kotaro Hirasawa, Junichi Murata, Masanao Ohbayashi, Kousuke Kumamaru

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

1 Citation (Scopus)

Abstract

This paper presents a modeling scheme for nonlinear black-box systems based on Universal Learning Networks (ULN). The ULN, a superset of all kinds of neural networks, consists of two kinds of elements: nodes and branches corresponding to equations and their relations in traditional description of dynamic systems. Following the idea of ULN, a nonlinear black-box system is first represented by a set of related unknown equations, and then treated as the ULN with nodes and branches. Each unknown node function in the ULN is re-parameterized by using an adaptive fuzzy model. One of distinctive features of the black-box model constructed in this way is that it can incorporate prior knowledge obtained from input-output data into its modeling and thus its parameters to be trained have explicit meanings useful for estimation and application.

Original languageEnglish
Title of host publicationIEEE World Congress on Computational Intelligence
Editors Anon
PublisherIEEE
Pages2465-2470
Number of pages6
Volume3
Publication statusPublished - 1998
EventProceedings of the 1998 IEEE International Joint Conference on Neural Networks. Part 1 (of 3) - Anchorage, AK, USA
Duration: May 4 1998May 9 1998

Other

OtherProceedings of the 1998 IEEE International Joint Conference on Neural Networks. Part 1 (of 3)
CityAnchorage, AK, USA
Period5/4/985/9/98

Fingerprint

Dynamical systems
Neural networks

All Science Journal Classification (ASJC) codes

  • Software

Cite this

Hu, J., Hirasawa, K., Murata, J., Ohbayashi, M., & Kumamaru, K. (1998). Identification of nonlinear black-box systems based on Universal Learning Networks. In Anon (Ed.), IEEE World Congress on Computational Intelligence (Vol. 3, pp. 2465-2470). IEEE.

Identification of nonlinear black-box systems based on Universal Learning Networks. / Hu, Jinglu; Hirasawa, Kotaro; Murata, Junichi; Ohbayashi, Masanao; Kumamaru, Kousuke.

IEEE World Congress on Computational Intelligence. ed. / Anon. Vol. 3 IEEE, 1998. p. 2465-2470.

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

Hu, J, Hirasawa, K, Murata, J, Ohbayashi, M & Kumamaru, K 1998, Identification of nonlinear black-box systems based on Universal Learning Networks. in Anon (ed.), IEEE World Congress on Computational Intelligence. vol. 3, IEEE, pp. 2465-2470, Proceedings of the 1998 IEEE International Joint Conference on Neural Networks. Part 1 (of 3), Anchorage, AK, USA, 5/4/98.
Hu J, Hirasawa K, Murata J, Ohbayashi M, Kumamaru K. Identification of nonlinear black-box systems based on Universal Learning Networks. In Anon, editor, IEEE World Congress on Computational Intelligence. Vol. 3. IEEE. 1998. p. 2465-2470
Hu, Jinglu ; Hirasawa, Kotaro ; Murata, Junichi ; Ohbayashi, Masanao ; Kumamaru, Kousuke. / Identification of nonlinear black-box systems based on Universal Learning Networks. IEEE World Congress on Computational Intelligence. editor / Anon. Vol. 3 IEEE, 1998. pp. 2465-2470
@inproceedings{a67968b7e49440a8b03e26d3a08ddcaf,
title = "Identification of nonlinear black-box systems based on Universal Learning Networks",
abstract = "This paper presents a modeling scheme for nonlinear black-box systems based on Universal Learning Networks (ULN). The ULN, a superset of all kinds of neural networks, consists of two kinds of elements: nodes and branches corresponding to equations and their relations in traditional description of dynamic systems. Following the idea of ULN, a nonlinear black-box system is first represented by a set of related unknown equations, and then treated as the ULN with nodes and branches. Each unknown node function in the ULN is re-parameterized by using an adaptive fuzzy model. One of distinctive features of the black-box model constructed in this way is that it can incorporate prior knowledge obtained from input-output data into its modeling and thus its parameters to be trained have explicit meanings useful for estimation and application.",
author = "Jinglu Hu and Kotaro Hirasawa and Junichi Murata and Masanao Ohbayashi and Kousuke Kumamaru",
year = "1998",
language = "English",
volume = "3",
pages = "2465--2470",
editor = "Anon",
booktitle = "IEEE World Congress on Computational Intelligence",
publisher = "IEEE",

}

TY - GEN

T1 - Identification of nonlinear black-box systems based on Universal Learning Networks

AU - Hu, Jinglu

AU - Hirasawa, Kotaro

AU - Murata, Junichi

AU - Ohbayashi, Masanao

AU - Kumamaru, Kousuke

PY - 1998

Y1 - 1998

N2 - This paper presents a modeling scheme for nonlinear black-box systems based on Universal Learning Networks (ULN). The ULN, a superset of all kinds of neural networks, consists of two kinds of elements: nodes and branches corresponding to equations and their relations in traditional description of dynamic systems. Following the idea of ULN, a nonlinear black-box system is first represented by a set of related unknown equations, and then treated as the ULN with nodes and branches. Each unknown node function in the ULN is re-parameterized by using an adaptive fuzzy model. One of distinctive features of the black-box model constructed in this way is that it can incorporate prior knowledge obtained from input-output data into its modeling and thus its parameters to be trained have explicit meanings useful for estimation and application.

AB - This paper presents a modeling scheme for nonlinear black-box systems based on Universal Learning Networks (ULN). The ULN, a superset of all kinds of neural networks, consists of two kinds of elements: nodes and branches corresponding to equations and their relations in traditional description of dynamic systems. Following the idea of ULN, a nonlinear black-box system is first represented by a set of related unknown equations, and then treated as the ULN with nodes and branches. Each unknown node function in the ULN is re-parameterized by using an adaptive fuzzy model. One of distinctive features of the black-box model constructed in this way is that it can incorporate prior knowledge obtained from input-output data into its modeling and thus its parameters to be trained have explicit meanings useful for estimation and application.

UR - http://www.scopus.com/inward/record.url?scp=0031632619&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031632619&partnerID=8YFLogxK

M3 - Conference contribution

VL - 3

SP - 2465

EP - 2470

BT - IEEE World Congress on Computational Intelligence

A2 - Anon, null

PB - IEEE

ER -