Generalization Ability of Dynamic System by Using Second Order Derivatives of Universal Learning Network

DOI Web Site Web Site 参考文献19件

書誌事項

タイトル別名
  • Generalization Ability of Dynamic Systems by Using Second Order Derivatives of Universal Learning Network

この論文をさがす

抄録

This paper studies how the generalization ability of modeling of the dynamic systems can be improved by taking advantages of second order derivatives of the criterion function with respect to the external inputs that can be considered as a direct implementation of the well-known regularization technique. Computation of second order derivatives of Universal Learning Network for a dynamic network are discussed. Simulation studies of a nonlinear dynamic system and a real robot system are carried out to demonstrate the effectiveness of the proposed method. Simulation results show that the proposed method can improve the generalization ability of neural networks sufficiently by selecting an appropriate regularization parameter.

収録刊行物

参考文献 (19)*注記

もっと見る

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