Current deep learning methods do not support reliable continual learning—despite decades of work on catastrophic forgetting and recent work on catastrophic loss of plasticity—and this is a major limitation of applying runtime learning to complex real-world problems
factualpending
Speaker
Richard SuttonEvidence Quote
“today's deep learning methods...continual learning, they don't work very well...for the nonlinear case, for the deep learning case, we can't have reliable continual learning yet”
Source
Rich Sutton, The OaK Architecture: A Vision of SuperIntelligence from Experience - RLC 2025— AmiiCreated: 8/11/2026, 7:21:57 AM
Your notes
Loading notes...