Presentation 1997/2/7
Second-order Learning Algorithm with Squared Penalty Term
Kazumi Saito, Ryohei Nakano,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper compares three penalty terms with respect to the efficiency of supervised learning, by using first- and second-order learning algorithms. Our experiments,showed that for a reasonably adequate penalty factor, the combination of the squared penalty term and the second-order learning algorithm drastically improves the convergence performance more than 20 times over the other combinations, at the same time bringing about better generalization performance.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) penalty term / second-order learning algorithm / generalization performance / conver-gence performance.
Paper # NLP96-151,NC96-105
Date of Issue

Conference Information
Committee NC
Conference Date 1997/2/7(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 Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Second-order Learning Algorithm with Squared Penalty Term
Sub Title (in English)
Keyword(1) penalty term
Keyword(2) second-order learning algorithm
Keyword(3) generalization performance
Keyword(4) conver-gence performance.
1st Author's Name Kazumi Saito
1st Author's Affiliation NTT Communication Science Laboratories()
2nd Author's Name Ryohei Nakano
2nd Author's Affiliation NTT Communication Science Laboratories
Date 1997/2/7
Paper # NLP96-151,NC96-105
Volume (vol) vol.96
Number (no) 512
Page pp.pp.-
#Pages 8
Date of Issue