Effective training methods for function localization neural networks

Takafumi Sasakawa, Jinglu Hu, Katsunori Isono, Kotaro Hirasawa

研究成果: Conference contribution

1 引用 (Scopus)

抜粋

Inspired by Hebb's cell assembly theory about how the brain worked, we have developed a function localization neural network (FLNN). The main part of a FLNN is structurally the same as an ordinary feedforward neural network, but it is considered to consist of several overlapping modules, which are switched according to input patterns. A FLNN constructed in this way has been shown to have better representation ability than an ordinary neural network. However, BP training algorithm for such FLNN is very easy to get stuck at a local minimum. In this paper, we mainly discuss the methods for improving BP training of the FLNN by utilizing the structural property of the network. Two methods are proposed. Numerical simulations are used to show the effectiveness of the improved BP training methods.

元の言語English
ホスト出版物のタイトルInternational Joint Conference on Neural Networks 2006, IJCNN '06
出版者Institute of Electrical and Electronics Engineers Inc.
ページ4785-4790
ページ数6
ISBN(印刷物)0780394909, 9780780394902
DOI
出版物ステータスPublished - 2006 1 1
イベントInternational Joint Conference on Neural Networks 2006, IJCNN '06 - Vancouver, BC, Canada
継続期間: 2006 7 162006 7 21

出版物シリーズ

名前IEEE International Conference on Neural Networks - Conference Proceedings
ISSN(印刷物)1098-7576

Conference

ConferenceInternational Joint Conference on Neural Networks 2006, IJCNN '06
Canada
Vancouver, BC
期間06/7/1606/7/21

ASJC Scopus subject areas

  • Software

フィンガープリント Effective training methods for function localization neural networks' 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

    Sasakawa, T., Hu, J., Isono, K., & Hirasawa, K. (2006). Effective training methods for function localization neural networks. : International Joint Conference on Neural Networks 2006, IJCNN '06 (pp. 4785-4790). [1716764] (IEEE International Conference on Neural Networks - Conference Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ijcnn.2006.247154