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 Sutton

Evidence 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— Amii
Created: 8/11/2026, 6:51:29 AM

Your notes

Loading notes...