Composite likelihood estimation for restricted Boltzmann machines

Muneki Yasuda, Shun Kataoka, Yuji Waizumi, Kazuyuki Tanaka

研究成果: Conference contribution

2 被引用数 (Scopus)

抄録

Generally, learning the parameters of graphical models by using the maximum likelihood estimation is difficult and requires an approximation. Maximum composite likelihood estimations are statistical approximations of the maximum likelihood estimation and are higher-order generalizations of the maximum pseudo-likelihood estimation. In this paper, we propose a composite likelihood method and investigate its properties. Furthermore, we apply this to restricted Boltzmann machines.

本文言語English
ホスト出版物のタイトルICPR 2012 - 21st International Conference on Pattern Recognition
ページ2234-2237
ページ数4
出版ステータスPublished - 2012 12 1
イベント21st International Conference on Pattern Recognition, ICPR 2012 - Tsukuba, Japan
継続期間: 2012 11 112012 11 15

出版物シリーズ

名前Proceedings - International Conference on Pattern Recognition
ISSN(印刷版)1051-4651

Other

Other21st International Conference on Pattern Recognition, ICPR 2012
国/地域Japan
CityTsukuba
Period12/11/1112/11/15

ASJC Scopus subject areas

  • コンピュータ ビジョンおよびパターン認識

フィンガープリント

「Composite likelihood estimation for restricted Boltzmann machines」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル