Glossary
What is LwF? Definition and meaning
Keeps a new model's outputs on old tasks close to those of the previous model through distillation.
Definition
LwF: Keeps a new model's outputs on old tasks close to those of the previous model through distillation.
In short: Learning without forgetting.
When it is used
Adding tasks without replaying old data.
Learn more
The full guide to LwF explains how it works, when to use it and how it compares with the alternatives, with examples. The glossary lists every term on the site from A to Z.