catastrophic

Definition

"Catastrophic" describes failure that is abrupt and near-total rather than gradual — a cliff, not a slope. The canonical use is catastrophic forgetting, where accuracy on an earlier task collapses almost immediately once training moves to a new one. The word is doing real work: it distinguishes this from ordinary interference or slow drift, and it implies the lost capability does not return on its own.

Explainers using this term

• Continual Learning and Catastrophic Forgetting — Why Models Can't Just Keep LearningOvercoming catastrophic forgetting in neural networks