Online Continual Learning in Edge-Cloud Applications
Experimental results demonstrate the applicability of the proposed edge-cloud methodology for integrating Continual Learning with Out-of-Distribution (OOD) Detection and Concept Drift Detection in IoT applications and its potential to support model adaptation while mitigating catastrophic forgetting.
Charalampos Davalas, Dimitrios Michail, Christos Diou et al.
· 0 citations