Presentation 2013-01-24
Study of quasi-Newton Training Algorithm on Parallel Distributed Environment
Makoto SAIKI, Yoshihiko SAKASHITA, Hiroshi NINOMIYA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper descnbes the feasibility of quasi-Newton method for training feedforward neural networks on the parallel distnbuted environment. Recently, we have to deal with large data in machine learning. Parallel distnbuted environment is one of the means to solve this problem. Most of the learning method with huge samples are based on the first order gradient algonthms. The quasi-Newton method is one of the most effective method to training feed forward neural networks. This study venfy practiced effectiveness method through computer simulations.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) neural networks / quasi-Newton method / back-propagation method / parallel distnbuted environment
Paper # NLP2012-111,NC2012-101
Date of Issue

Conference Information
Committee NLP
Conference Date 2013/1/17(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) Study of quasi-Newton Training Algorithm on Parallel Distributed Environment
Sub Title (in English)
Keyword(1) neural networks
Keyword(2) quasi-Newton method
Keyword(3) back-propagation method
Keyword(4) parallel distnbuted environment
1st Author's Name Makoto SAIKI
1st Author's Affiliation Department of information Science, Faculty of Engineering()
2nd Author's Name Yoshihiko SAKASHITA
2nd Author's Affiliation Department of information Science, Faculty of Engineering
3rd Author's Name Hiroshi NINOMIYA
3rd Author's Affiliation Department of information Science, Faculty of Engineering
Date 2013-01-24
Paper # NLP2012-111,NC2012-101
Volume (vol) vol.112
Number (no) 389
Page pp.pp.-
#Pages 6
Date of Issue