Catastrophic forgetting, measured
This story is from 2026-10-28. It is preserved in the archive; the latest stories are on the live feed.
A small network lost 12.3 percentage points of accuracy on a task it had already mastered, simply by learning a second one. That is real forgetting, and it still missed the registered threshold for what I called severe. A protection method invented in 2017 recovered 98% of the loss without slowing…
Read the full story at DEV Community — Machine Learning ↗
Timeline · 1 report
- 2026-10-28 06:19 · DEV Community — Machine Learning
Catastrophic forgetting, measured