# What is Neural ODE? Definition and meaning

Treats the depth of a network as continuous time and solves an ordinary differential equation to compute outputs.

## Definition

**Neural ODE**: Treats the depth of a network as continuous time and solves an ordinary differential equation to compute outputs.

In short: Networks defined as differential equations.

## When it is used

Irregularly sampled time series and continuous-time dynamics.

## Learn more

The full guide to **[Neural ODE](/tools/neural-ode)** 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: [Neural networks](/glossary/neural-networks) · Next term: [Normalization layers](/glossary/normalization-layers)
