Multimodal pattern classifiers with feedback of class memberships

Kohei Indue, Kiichi Urahama

Research output: Contribution to journalArticlepeer-review


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.

Original languageEnglish
Pages (from-to)712-716
Number of pages5
JournalIEICE Transactions on Information and Systems
Issue number3
Publication statusPublished - 1999
Externally publishedYes

All Science Journal Classification (ASJC) codes

  • Software
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering
  • Artificial Intelligence


Dive into the research topics of 'Multimodal pattern classifiers with feedback of class memberships'. Together they form a unique fingerprint.

Cite this