Robust learning control using universal learning network

Masanao Ohbayashi, Kotaro Hirasawa, Junichi Murata, Masaaki Harada

研究成果: 会議への寄与タイプ論文

13 引用 (Scopus)

抄録

Characteristics of control system design using Universal Learning Network(U.L.N.) are that a system to be controlled and a controller are both constructed by U.L.N. and that the controller is best tuned through learning. U.L.N. has the same generalization ability as N.N.. So the controller constructed by U.L.N. is able to control the system in a favorable way under the condition different from the condition of the control system at learning stage. But stability can not be realized sufficiently. In this paper, we propose a robust learning control method using U.L.N. and second order derivatives of U.L.N.. The proposed method can realize better performance and robustness than the commonly used Neural Network. Robust learning control considered here is defined as follows. Even though initial values of node outputs change from those at learning, the control system is able to reduce its influence to other node outputs and can control the system in a preferable way as in the case of no variation.

元の言語英語
ページ2208-2213
ページ数6
出版物ステータス出版済み - 1 1 1996
イベントProceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4) - Washington, DC, USA
継続期間: 6 3 19966 6 1996

その他

その他Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4)
Washington, DC, USA
期間6/3/966/6/96

Fingerprint

Control systems
Controllers
Systems analysis
Derivatives
Neural networks

All Science Journal Classification (ASJC) codes

  • Software

これを引用

Ohbayashi, M., Hirasawa, K., Murata, J., & Harada, M. (1996). Robust learning control using universal learning network. 2208-2213. 論文発表場所 Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4), Washington, DC, USA, .

Robust learning control using universal learning network. / Ohbayashi, Masanao; Hirasawa, Kotaro; Murata, Junichi; Harada, Masaaki.

1996. 2208-2213 論文発表場所 Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4), Washington, DC, USA, .

研究成果: 会議への寄与タイプ論文

Ohbayashi, M, Hirasawa, K, Murata, J & Harada, M 1996, 'Robust learning control using universal learning network' 論文発表場所 Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4), Washington, DC, USA, 6/3/96 - 6/6/96, pp. 2208-2213.
Ohbayashi M, Hirasawa K, Murata J, Harada M. Robust learning control using universal learning network. 1996. 論文発表場所 Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4), Washington, DC, USA, .
Ohbayashi, Masanao ; Hirasawa, Kotaro ; Murata, Junichi ; Harada, Masaaki. / Robust learning control using universal learning network. 論文発表場所 Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4), Washington, DC, USA, .6 p.
@conference{9539932fa57549f2a41a0ec8b3217787,
title = "Robust learning control using universal learning network",
abstract = "Characteristics of control system design using Universal Learning Network(U.L.N.) are that a system to be controlled and a controller are both constructed by U.L.N. and that the controller is best tuned through learning. U.L.N. has the same generalization ability as N.N.. So the controller constructed by U.L.N. is able to control the system in a favorable way under the condition different from the condition of the control system at learning stage. But stability can not be realized sufficiently. In this paper, we propose a robust learning control method using U.L.N. and second order derivatives of U.L.N.. The proposed method can realize better performance and robustness than the commonly used Neural Network. Robust learning control considered here is defined as follows. Even though initial values of node outputs change from those at learning, the control system is able to reduce its influence to other node outputs and can control the system in a preferable way as in the case of no variation.",
author = "Masanao Ohbayashi and Kotaro Hirasawa and Junichi Murata and Masaaki Harada",
year = "1996",
month = "1",
day = "1",
language = "English",
pages = "2208--2213",
note = "Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4) ; Conference date: 03-06-1996 Through 06-06-1996",

}

TY - CONF

T1 - Robust learning control using universal learning network

AU - Ohbayashi, Masanao

AU - Hirasawa, Kotaro

AU - Murata, Junichi

AU - Harada, Masaaki

PY - 1996/1/1

Y1 - 1996/1/1

N2 - Characteristics of control system design using Universal Learning Network(U.L.N.) are that a system to be controlled and a controller are both constructed by U.L.N. and that the controller is best tuned through learning. U.L.N. has the same generalization ability as N.N.. So the controller constructed by U.L.N. is able to control the system in a favorable way under the condition different from the condition of the control system at learning stage. But stability can not be realized sufficiently. In this paper, we propose a robust learning control method using U.L.N. and second order derivatives of U.L.N.. The proposed method can realize better performance and robustness than the commonly used Neural Network. Robust learning control considered here is defined as follows. Even though initial values of node outputs change from those at learning, the control system is able to reduce its influence to other node outputs and can control the system in a preferable way as in the case of no variation.

AB - Characteristics of control system design using Universal Learning Network(U.L.N.) are that a system to be controlled and a controller are both constructed by U.L.N. and that the controller is best tuned through learning. U.L.N. has the same generalization ability as N.N.. So the controller constructed by U.L.N. is able to control the system in a favorable way under the condition different from the condition of the control system at learning stage. But stability can not be realized sufficiently. In this paper, we propose a robust learning control method using U.L.N. and second order derivatives of U.L.N.. The proposed method can realize better performance and robustness than the commonly used Neural Network. Robust learning control considered here is defined as follows. Even though initial values of node outputs change from those at learning, the control system is able to reduce its influence to other node outputs and can control the system in a preferable way as in the case of no variation.

UR - http://www.scopus.com/inward/record.url?scp=0029728598&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029728598&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0029728598

SP - 2208

EP - 2213

ER -