System identification using neural network with parametric sigmoid function

M. Hasheminejad, J. Murata, K. Hirasawa

研究成果: Contribution to conferencePaper

抜粋

Nonlinear systems can be modeled by neural networks. However choice of suitable network architecture is the most important problem. And 'how to find the best activation function' is a persistent aspect of the architecture design. Here we have proposed a sigmoid function with one parameter which provides us not only the reduction of error bound but also the opportunity of obtaining better insight into the systems.

元の言語英語
ページ39-44
ページ数6
出版物ステータス出版済み - 12 1 1994
イベントProceedings of the Artificial Neural Networks in Engineering Conference (ANNIE'94) - St. Louis, MO, USA
継続期間: 11 13 199411 16 1994

会議

会議Proceedings of the Artificial Neural Networks in Engineering Conference (ANNIE'94)
St. Louis, MO, USA
期間11/13/9411/16/94

All Science Journal Classification (ASJC) codes

  • Engineering(all)

フィンガープリント System identification using neural network with parametric sigmoid function' の研究トピックを掘り下げます。これらはともに一意のフィンガープリントを構成します。

  • これを引用

    Hasheminejad, M., Murata, J., & Hirasawa, K. (1994). System identification using neural network with parametric sigmoid function. 39-44. 論文発表場所 Proceedings of the Artificial Neural Networks in Engineering Conference (ANNIE'94), St. Louis, MO, USA, .