Enhancing the generalization ability of neural networks by using gram-schmidt orthogonalization algorithm

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

*この研究の対応する著者

研究成果査読

2 被引用数 (Scopus)

抄録

Generalization ability of neural networks is the most important criterion to determine whether one algorithm is powerful or not. Many new algorithms have been devised to enhance the generalization ability of neural networks[1][2]. In this paper a new algorithm using the Gram-Schmidt orthogonalization algorithm [3] to the outputs of nodes in the hidden layers is proposed with the aim to reduce the interference among the nodes in the hidden layers, which is much more efficient than the regularizers methods. Simulation results confirm the above assertion.

本文言語English
ページ1721-1726
ページ数6
出版ステータスPublished - 2001 1 1
外部発表はい
イベントInternational Joint Conference on Neural Networks (IJCNN'01) - Washington, DC, United States
継続期間: 2001 7 152001 7 19

Conference

ConferenceInternational Joint Conference on Neural Networks (IJCNN'01)
国/地域United States
CityWashington, DC
Period01/7/1501/7/19

ASJC Scopus subject areas

  • ソフトウェア
  • 人工知能

フィンガープリント

「Enhancing the generalization ability of neural networks by using gram-schmidt orthogonalization algorithm」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