Export

Link to this page

Please use this URL for citations.

Search Other Services

Statistics

  • Access to this page：626 times

＜journal article＞
Semi-supervised logistic discrimination via graph-based regularization

Creator
Author PID
L002492
Creator Name
Kawano, Shuichi
川野, 秀一
カワノ, シュウイチ
Affiliation
Affiliation Name
Graduate School of Mathematics, Kyushu University
九州大学大学院数理学府
Creator Name
Misumi, Toshihiro
三角, 俊裕
ミスミ, トシヒロ
Affiliation
Affiliation Name
Graduate School of Mathematics, Kyushu University
九州大学大学院数理学府
Author PID
K000534
Creator Name
Konishi, Sadanori
小西, 貞則
コニシ, サダノリ
Affiliation
Affiliation Name
Faculty of Mathematics, Kyushu University
九州大学大学院数理学研究院
Language
English
Publisher
Springer
Date
2012-12
Source Title
Neural processing letters
Vol
36
Issue
3
Publication Type
Accepted Manuscript
Access Rights
open access
Rights
The original publication is available at www.springerlink.com
(C)Springer Science+Business Media, LLC. 2012
Related DOI
isIdenticalTo
https://doi.org/10.1007/s11063-012-9231-3
Related DOI
MI Preprint Series ; 2010-6
Related DOI
Neural processing letters || 36(3) || p203-216
http://www.math.kyushu-u.ac.jp/
Related URI
Neural processing letters || 36(3) || p203-216
http://www.math.kyushu-u.ac.jp/
Related URI
Related HDL
Relation
MI Preprint Series ; 2010-6
Neural processing letters || 36(3) || p203-216
http://www.math.kyushu-u.ac.jp/
Abstract We address the problem of constructing a nonlinear model based on both classified and unclassified data sets for classification. A semi-supervised logistic model with Gaussian basis expansions along w...ith technique of graph-based regularization method is presented. Crucial issues in our modeling procedure are the choices of tuning parameters included in the nonlinear logistic models. In order to select these adjusted parameters, we derive model selection criteria from the viewpoints of information theory and Bayesian approach. Some numerical examples are conducted to show the effectiveness of our proposed semi-supervised modeling strategies.show more

Hide fulltext details.

pdf MI2010-6 pdf 156 KB 328  

Details

Record ID
16260
Peer-Reviewed
Refereed
Subject Terms
Basis expansion
Logistic discrimination
Model selection
Regularization
Semi-supervised learning
ISSN
1573-773X
1370-4621
DOI
10.1007/s11063-012-9231-3
Notes
MI: Global COE Program Education-and-Research Hub for Mathematics-for-Industry
グローバルCOEプログラム「マス･フォア･インダストリ教育研究拠点」
Type
雑誌論文
Created Date 2013.03.04
Modified Date 2024.01.10