NeuroGenesys All reference videosAcademy • Reference video • 1:11:21Open on YouTube
Maintaining Plasticity in Deep Continual Learning - Rich Sutton - CoLLAs 2022
Conference on Lifelong Learning Agents (CoLLAs)
Why watch
Loss of plasticity and continual backprop, from the source.
Featured in
Watch next
1:16:40Institute of Data Science (IDS), NUSUnifying Continual Learning and OOD Detection by Liu Bing
Bing Liu, senior author of Kim et al. (NeurIPS 2022), on why class-IL splits into within-task prediction × task-id prediction. This is the theorem our decomposition rests on.
Watch
42:07Paul HandContinual Learning and Catastrophic Forgetting
A lecture on the classic remedies: EWC, LwF, progressive nets and generative replay.
Watch
1:39:31ContinualAI[Continual Learning Course] Lecture #2: Understanding Catastrophic Forgetting
Covers task-, domain- and class-incremental settings and why class-IL is the hard one.
Watch
1:01:29Conference on Lifelong Learning Agents (CoLLAs)Why do neural networks lose plasticity? - Clare Lyle - CoLLAs 2023
Mechanisms of plasticity loss. Our runs pointed to the optimizer and weight norm.
Watch
Hosted by YouTube and played through its privacy-enhanced embed. The creator is not affiliated with NeuroGenesys; a video is a way in, not a source.
