The OAK architecture requires solving reliable continual learning for deep neural networks, which currently fails due to catastrophic forgetting and loss of plasticity, with some solution approaches including continual backprop and meta-learning of new features
factualpending
Speaker
Richard SuttonEvidence Quote
“the oak architecture requires reliable continual learning... for the deep learning case, we can't have reliable we don't yet”
Source
Rich Sutton, The OaK Architecture: A Vision of SuperIntelligence from Experience - RLC 2025— AmiiCreated: 8/11/2026, 6:51:29 AM
Your notes
Loading notes...