Distilling EEG representations via capsules for affective computing
•We distill EEG representations via capsule-based architectures.•We encourage lightweight model to mimic heavy model distillation using privileged information.•Our proposed framework performs well given the high compression rate and limited training samples.•Our framework achieves state-of-the-art r...
Saved in:
Published in | Pattern recognition letters Vol. 171; pp. 99 - 105 |
---|---|
Main Authors | , |
Format | Journal Article |
Language | English |
Published |
Elsevier B.V
01.07.2023
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Be the first to leave a comment!