Similarity-Based Adaptation for Task-Aware and Task-Free Continual Learning

T Adel - Journal of Artificial Intelligence Research, 2024 - jair.org
Continual learning (CL) is a paradigm which addresses the issue of how to learn from
sequentially arriving tasks. The goal of this paper is to introduce a CL framework which can …

Patch-Based Contrastive Learning and Memory Consolidation for Online Unsupervised Continual Learning

C Taylor, V Vassiliades, C Dovrolis - arXiv preprint arXiv:2409.16391, 2024 - arxiv.org
We focus on a relatively unexplored learning paradigm known as {\em Online Unsupervised
Continual Learning}(O-UCL), where an agent receives a non-stationary, unlabeled data …