Enhancing the Generalization Ability of Neural Networks by Using Gram-Schmidt Orthogonalization Algorithm

DOI Web Site
  • WAN Weishui
    Kyushu University
  • HIRASAWA Kotaro
    Graduate School of Information, Production and Systems, Waseda University
  • HU Jinglu
    Graduate School of Information, Production and Systems, Waseda University

抄録

In this paper a new algorithm applying Gram-Schmidt orthogonalization algorithm 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, therefore to enhance the generalization ability of neural networks, which is much more efficient than other regularizers methods. Simulation results confirm the above assertion.

収録刊行物

キーワード

詳細情報 詳細情報について

問題の指摘

ページトップへ