# What is Bayesian deep learning? Definition and meaning

Combines deep networks with Bayesian methods to quantify what the model does not know.

## Definition

**Bayesian deep learning**: Combines deep networks with Bayesian methods to quantify what the model does not know.

In short: Neural networks with uncertainty over weights and outputs.

## When it is used

Uncertainty-aware prediction and calibrated confidence.

## Learn more

The full guide to **[Bayesian deep learning](/tools/bayesian-deep-learning)** 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: [Backpropagation](/glossary/backpropagation) · Next term: [Bayesian optimization](/glossary/bayesian-optimization)
