Infinite dSprites for Disentangled Continual Learning: Separating Memory Edits from Generalization

arXiv:2312.16731v2 Announce Type: replace
Abstract: The ability of machine learning systems to learn continually is hindered by catastrophic forgetting, the tendency of neural networks to overwrite existing knowledge when learning a new task. Continual learning methods alleviate this problem through regularization, parameter isolation, or rehearsal, but they are typically evaluated on benchmarks comprising only a handful of tasks. In contrast, humans are able to learn continually in dynamic, open-world environments, effortlessly achieving one-shot memorization of unfamiliar objects and reliably recognizing …

abstract arxiv catastrophic forgetting continual cs.cv cs.lg knowledge learn learning systems machine machine learning memory networks neural networks regularization systems through type