Glossary
What is BYOL? Definition and meaning
Trains an online network to predict the output of a slowly moving target network, with no negative examples.
Definition
BYOL: Trains an online network to predict the output of a slowly moving target network, with no negative examples.
In short: Self-supervised learning without negative pairs.
When it is used
Representation learning where choosing negatives is awkward.
Learn more
The full guide to BYOL 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.
Previous term: Browser agents · Next term: Camunda