IEICE TRANSACTIONS on Information
Multimodal Pattern Classifiers with Feedback of Class Memberships
Summary :
Feedback of class memberships is incorporated into multimodal pattern classifiers and their unsupervised 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.
- Publication
- IEICE TRANSACTIONS on Information Vol.E82-D No.3 pp.712-716
- Publication Date
- 1999/03/25
- Publicized
- Online ISSN
- DOI
- Type of Manuscript
- LETTER
- Category
- Bio-Cybernetics and Neurocomputing
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Kohei INOUE, Kiichi URAHAMA, "Multimodal Pattern Classifiers with Feedback of Class Memberships" in IEICE TRANSACTIONS on Information,
vol. E82-D, no. 3, pp. 712-716, March 1999, doi: .
Abstract: Feedback of class memberships is incorporated into multimodal pattern classifiers and their unsupervised 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.
URL: https://global.ieice.org/en_transactions/information/10.1587/e82-d_3_712/_p
Copy
@ARTICLE{e82-d_3_712,
author={Kohei INOUE, Kiichi URAHAMA, },
journal={IEICE TRANSACTIONS on Information},
title={Multimodal Pattern Classifiers with Feedback of Class Memberships},
year={1999},
volume={E82-D},
number={3},
pages={712-716},
abstract={Feedback of class memberships is incorporated into multimodal pattern classifiers and their unsupervised 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.},
keywords={},
doi={},
ISSN={},
month={March},}
Copy
TY - JOUR
TI - Multimodal Pattern Classifiers with Feedback of Class Memberships
T2 - IEICE TRANSACTIONS on Information
SP - 712
EP - 716
AU - Kohei INOUE
AU - Kiichi URAHAMA
PY - 1999
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E82-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 1999
AB - Feedback of class memberships is incorporated into multimodal pattern classifiers and their unsupervised 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.
ER -
English
