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.
| Original language | English |
|---|---|
| Pages (from-to) | 712-716 |
| Number of pages | 5 |
| Journal | IEICE Transactions on Information and Systems |
| Volume | E82-D |
| Issue number | 3 |
| Publication status | Published - 1999 |
| Externally published | Yes |
All Science Journal Classification (ASJC) codes
- Software
- Hardware and Architecture
- Computer Vision and Pattern Recognition
- Electrical and Electronic Engineering
- Artificial Intelligence