Relation between weight initialization of neural networks and pruning algorithms case study on Mackey-Glass time series

W. Wan, K. Hirasawa, J. Hu, Junichi Murata

研究成果: Contribution to conferencePaper

4 引用 (Scopus)

抜粋

The implementation of weight initialization is directly related to the convergence of learning algorithms. In this paper we made a case study on the famous Mackey-Glass time series problem in order to try to find some relations between weight initialization of neural networks and pruning algorithms. The pruning algorithm used in simulations is Laplace regularizer method, that is, the backpropagation algorithm with Laplace regularizer added to the criterion function. Simulation results show that different kinds of initialization weight matrices display almost the same generalization ability when using the pruning algorithm, at least for the Mackey-Glass time series.

元の言語英語
ページ1750-1755
ページ数6
出版物ステータス出版済み - 1 1 2001
イベントInternational Joint Conference on Neural Networks (IJCNN'01) - Washington, DC, 米国
継続期間: 7 15 20017 19 2001

その他

その他International Joint Conference on Neural Networks (IJCNN'01)
米国
Washington, DC
期間7/15/017/19/01

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence

フィンガープリント Relation between weight initialization of neural networks and pruning algorithms case study on Mackey-Glass time series' 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

    Wan, W., Hirasawa, K., Hu, J., & Murata, J. (2001). Relation between weight initialization of neural networks and pruning algorithms case study on Mackey-Glass time series. 1750-1755. 論文発表場所 International Joint Conference on Neural Networks (IJCNN'01), Washington, DC, 米国.