Brain-Inspired Continual Learning: Robust Feature Distillation and Re-Consolidation for Class Incremental Learning

H Khan, NC Bouaynaya, G Rasool - IEEE Access, 2024 - ieeexplore.ieee.org
Artificial intelligence and neuroscience have a long and intertwined history. Advancements
in neuroscience research have significantly influenced the development of artificial …

[PDF][PDF] Saliency-driven Experience Replay for Continual Learning

G Bellitto, FP Salanitri, M Pennisi, M Boschini… - Advances in Neural …, 2024 - iris.unimore.it
Abstract We present Saliency-driven Experience Replay-SER-a biologically-plausible
approach based on replicating human visual saliency to enhance classification models in …

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 …