# 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](/tools/byol)** explains how it works, when to use it and how it compares with the alternatives, with examples. The [glossary](/glossary) lists every term on the site from A to Z.

Previous term: [Browser agents](/glossary/browser-agents) · Next term: [Camunda](/glossary/camunda)
