Presentation 2003/11/15
Research of Generalization Ability for Local Lenearized Least Squares Algorithm
Masahiro YOSHIDA, Hiroshi NINOMIYA, Hideki ASAI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) A variety of studies on training method with the weight decay has been done in order to improve the generalization ability in feedforward neural networks. In this research, we introduce the local training with weight decay based on the recursive least squares. The proposed method can improve the training speed. In the simulation, the generalization ability is compared the proposed method to another methods with weight decay.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) feedforward neural networks / local training / weight decay / recursive least squares / generalization ability
Paper # NLP2003-123
Date of Issue

Conference Information
Committee NLP
Conference Date 2003/11/15(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Nonlinear Problems (NLP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Research of Generalization Ability for Local Lenearized Least Squares Algorithm
Sub Title (in English)
Keyword(1) feedforward neural networks
Keyword(2) local training
Keyword(3) weight decay
Keyword(4) recursive least squares
Keyword(5) generalization ability
1st Author's Name Masahiro YOSHIDA
1st Author's Affiliation Dept. of Systems Engineering, Shizuoka University()
2nd Author's Name Hiroshi NINOMIYA
2nd Author's Affiliation Dept. of Information Science, Shonan Institute of Technology
3rd Author's Name Hideki ASAI
3rd Author's Affiliation Dept. of Systems Engineering, Shizuoka University
Date 2003/11/15
Paper # NLP2003-123
Volume (vol) vol.103
Number (no) 464
Page pp.pp.-
#Pages 6
Date of Issue