Generalization ability of universal learning network by using second order derivatives

M. Han, K. Hirasawa, Takayuki Furuzuki, J. Murata

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

4 Citations (Scopus)

Abstract

In this paper, it is studied how the generalization ability of modeling of the dynamic systems can be improved by taking advantages of the second order derivatives of the criterion function with respect to the external inputs. The proposed method is based on the regularization theory proposed by Poggio, but a main distinctive point in this paper is that extension to dynamic systems from static systems has been taken into account and actual second order derivatives of the Universal Learning Network have been used to train the parameters of the networks. The second order derivatives term of the criterion function may minimize the deviation caused by the external input changes. Simulation results show that the method is useful for improving the generalization ability of identifying nonlinear dynamic systems using neural networks.

Original languageEnglish
Title of host publicationProceedings of the IEEE International Conference on Systems, Man and Cybernetics
PublisherIEEE
Pages1818-1823
Number of pages6
Volume2
Publication statusPublished - 1998
Externally publishedYes
EventProceedings of the 1998 IEEE International Conference on Systems, Man, and Cybernetics. Part 2 (of 5) - San Diego, CA, USA
Duration: 1998 Oct 111998 Oct 14

Other

OtherProceedings of the 1998 IEEE International Conference on Systems, Man, and Cybernetics. Part 2 (of 5)
CitySan Diego, CA, USA
Period98/10/1198/10/14

Fingerprint

Dynamical systems
Derivatives
Neural networks

ASJC Scopus subject areas

  • Hardware and Architecture
  • Control and Systems Engineering

Cite this

Han, M., Hirasawa, K., Furuzuki, T., & Murata, J. (1998). Generalization ability of universal learning network by using second order derivatives. In Proceedings of the IEEE International Conference on Systems, Man and Cybernetics (Vol. 2, pp. 1818-1823). IEEE.

Generalization ability of universal learning network by using second order derivatives. / Han, M.; Hirasawa, K.; Furuzuki, Takayuki; Murata, J.

Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. Vol. 2 IEEE, 1998. p. 1818-1823.

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

Han, M, Hirasawa, K, Furuzuki, T & Murata, J 1998, Generalization ability of universal learning network by using second order derivatives. in Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. vol. 2, IEEE, pp. 1818-1823, Proceedings of the 1998 IEEE International Conference on Systems, Man, and Cybernetics. Part 2 (of 5), San Diego, CA, USA, 98/10/11.
Han M, Hirasawa K, Furuzuki T, Murata J. Generalization ability of universal learning network by using second order derivatives. In Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. Vol. 2. IEEE. 1998. p. 1818-1823
Han, M. ; Hirasawa, K. ; Furuzuki, Takayuki ; Murata, J. / Generalization ability of universal learning network by using second order derivatives. Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. Vol. 2 IEEE, 1998. pp. 1818-1823
@inproceedings{bcd0c918f6e24c09b952dc16648b6576,
title = "Generalization ability of universal learning network by using second order derivatives",
abstract = "In this paper, it is studied how the generalization ability of modeling of the dynamic systems can be improved by taking advantages of the second order derivatives of the criterion function with respect to the external inputs. The proposed method is based on the regularization theory proposed by Poggio, but a main distinctive point in this paper is that extension to dynamic systems from static systems has been taken into account and actual second order derivatives of the Universal Learning Network have been used to train the parameters of the networks. The second order derivatives term of the criterion function may minimize the deviation caused by the external input changes. Simulation results show that the method is useful for improving the generalization ability of identifying nonlinear dynamic systems using neural networks.",
author = "M. Han and K. Hirasawa and Takayuki Furuzuki and J. Murata",
year = "1998",
language = "English",
volume = "2",
pages = "1818--1823",
booktitle = "Proceedings of the IEEE International Conference on Systems, Man and Cybernetics",
publisher = "IEEE",

}

TY - GEN

T1 - Generalization ability of universal learning network by using second order derivatives

AU - Han, M.

AU - Hirasawa, K.

AU - Furuzuki, Takayuki

AU - Murata, J.

PY - 1998

Y1 - 1998

N2 - In this paper, it is studied how the generalization ability of modeling of the dynamic systems can be improved by taking advantages of the second order derivatives of the criterion function with respect to the external inputs. The proposed method is based on the regularization theory proposed by Poggio, but a main distinctive point in this paper is that extension to dynamic systems from static systems has been taken into account and actual second order derivatives of the Universal Learning Network have been used to train the parameters of the networks. The second order derivatives term of the criterion function may minimize the deviation caused by the external input changes. Simulation results show that the method is useful for improving the generalization ability of identifying nonlinear dynamic systems using neural networks.

AB - In this paper, it is studied how the generalization ability of modeling of the dynamic systems can be improved by taking advantages of the second order derivatives of the criterion function with respect to the external inputs. The proposed method is based on the regularization theory proposed by Poggio, but a main distinctive point in this paper is that extension to dynamic systems from static systems has been taken into account and actual second order derivatives of the Universal Learning Network have been used to train the parameters of the networks. The second order derivatives term of the criterion function may minimize the deviation caused by the external input changes. Simulation results show that the method is useful for improving the generalization ability of identifying nonlinear dynamic systems using neural networks.

UR - http://www.scopus.com/inward/record.url?scp=0032311985&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032311985&partnerID=8YFLogxK

M3 - Conference contribution

VL - 2

SP - 1818

EP - 1823

BT - Proceedings of the IEEE International Conference on Systems, Man and Cybernetics

PB - IEEE

ER -