Core ML Concepts · advanced · concept 31 of 176
Continual Learning & Catastrophic Forgetting
Neural networks trained on a new task tend to overwrite what they knew, which is why models are retrained from scratch instead of updated in place. Continual learning studies how to add knowledge without erasing the old, one of the most practical unsolved problems in the field.
Key terms
Catastrophic forgettingReplay bufferElastic weight consolidationTask interferenceOnline learning
Learn these first
Where you meet it in the real world
Personalization without retraining, robots that learn on the job, keeping deployed models current
Videos
▶ Continual Learning for Long-Running Agents: Agents That Keep Getting Better ↗
NVIDIA Developer · YouTube
Guides and articles
Courses, papers, and more