Elastic Weight Consolidation
Technique to prevent catastrophic forgetting
Episodes
-
#5868: Fine-Tuning Parakeet for Um-Free, Hebrish SpeechParakeet runs great on a phone — but fine-tuning it happens on a GPU. Here's the actual recipe for dropping ums and catching Hebrew. -
#5805: Freeze the Model, Move the LabelsYour classifier isn't stale — your label set moved. Why retraining is cheap, and why not retraining might be smarter. -
#1700: Can LLMs Learn Continuously Without Forgetting?We explore a new approach: micro-training updates every few days to keep AI knowledge fresh without constant web searches. -
#1066: Beyond the Blank Slate: The Evolution of AI TrainingExplore the "weight surgery" techniques labs use to expand AI models without losing their core knowledge or starting from zero.