ml:catastrophic_forgetting
This is an old revision of the document!
Table of Contents
Catastrophic Forgetting
Catastrophic forgetting is when a neural network is trained to do one task but loses that ability when trained to do a second task.
Overviews
Papers
In NLP
- Zheng et al 2025 - Spurious Forgetting in Continual Learning of Language Models Argues that the drop in performance while doing continued training “often reflects a decline in task alignment rather than knowledge loss”
Related Pages
ml/catastrophic_forgetting.1738370688.txt.gz · Last modified: 2025/02/01 00:44 by jmflanig