Generalization ability of universal learning network by using second order derivatives

M. Han*, K. Hirasawa, J. Hu, J. Murata

*この研究の対応する著者

研究成果: Conference article査読

4 被引用数 (Scopus)

抄録

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.

本文言語English
ページ(範囲)1818-1823
ページ数6
ジャーナルProceedings of the IEEE International Conference on Systems, Man and Cybernetics
2
出版ステータスPublished - 1998
外部発表はい
イベントProceedings of the 1998 IEEE International Conference on Systems, Man, and Cybernetics. Part 2 (of 5) - San Diego, CA, USA
継続期間: 1998 10 111998 10 14

ASJC Scopus subject areas

  • 制御およびシステム工学
  • ハードウェアとアーキテクチャ

フィンガープリント

「Generalization ability of universal learning network by using second order derivatives」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