Multimodal pattern classifiers with feedback of class memberships

Kohei Indue; Kiichi Urahama

Multimodal pattern classifiers with feedback of class memberships

Kohei Indue
, Kiichi Urahama

研究成果: ジャーナルへの寄稿 › 学術誌 › 査読

抄録

SUMMARY Feedback of class memberships is incorporated into multimodal pattern classifiers and their unsupcrvised learning algorithm is presented. Classification decision at low levels is revised by the feedback information which also enables the reconstruction of patterns at low levels. The effects of the feedback are examined for the McGurk effect by using a simple model.

本文言語	英語
ページ（範囲）	712-716
ページ数	5
ジャーナル	IEICE Transactions on Information and Systems
巻	E82-D
号	3
出版ステータス	出版済み - 1999
外部発表	はい

!!!All Science Journal Classification (ASJC) codes

ソフトウェア
ハードウェアとアーキテクチャ
コンピュータビジョンおよびパターン認識
電子工学および電気工学
人工知能

他のファイルとリンク

引用スタイル

@article{922e2525b4e84408b962169d05b5bd24,

title = "Multimodal pattern classifiers with feedback of class memberships",

abstract = "SUMMARY Feedback of class memberships is incorporated into multimodal pattern classifiers and their unsupcrvised learning algorithm is presented. Classification decision at low levels is revised by the feedback information which also enables the reconstruction of patterns at low levels. The effects of the feedback are examined for the McGurk effect by using a simple model.",

author = "Kohei Indue and Kiichi Urahama",

year = "1999",

language = "English",

volume = "E82-D",

pages = "712--716",

journal = "IEICE Transactions on Information and Systems",

issn = "0916-8532",

publisher = "Institute of Electronics Information Communication Engineers",

number = "3",

}

TY - JOUR

T1 - Multimodal pattern classifiers with feedback of class memberships

AU - Indue, Kohei

AU - Urahama, Kiichi

PY - 1999

Y1 - 1999

N2 - SUMMARY Feedback of class memberships is incorporated into multimodal pattern classifiers and their unsupcrvised learning algorithm is presented. Classification decision at low levels is revised by the feedback information which also enables the reconstruction of patterns at low levels. The effects of the feedback are examined for the McGurk effect by using a simple model.

AB - SUMMARY Feedback of class memberships is incorporated into multimodal pattern classifiers and their unsupcrvised learning algorithm is presented. Classification decision at low levels is revised by the feedback information which also enables the reconstruction of patterns at low levels. The effects of the feedback are examined for the McGurk effect by using a simple model.

UR - https://www.scopus.com/pages/publications/0033322113

UR - https://www.scopus.com/pages/publications/0033322113#tab=citedBy

M3 - Article

AN - SCOPUS:0033322113

SN - 0916-8532

VL - E82-D

SP - 712

EP - 716

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

IS - 3

ER -

Multimodal pattern classifiers with feedback of class memberships

抄録

!!!All Science Journal Classification (ASJC) codes

他のファイルとリンク

フィンガープリント

引用スタイル