# What is Neural networks? Definition and meaning

A neural network is a model made of layers of simple units that each compute a weighted sum and a non-linear function, with the weights learned from data.

## Definition

**Neural networks**: A neural network is a model made of layers of simple units that each compute a weighted sum and a non-linear function, with the weights learned from data.

In short: Many small sums, learned.

## When it is used

Neural networks power image recognition, speech, language models, recommendation and many tabular and scientific tasks.

## Where it fits

Neural networks belongs to **Neural network basics** in the [Deep learning](/topics/deep-learning) topic. These are the other terms in the same group:

- **[Activation functions](/glossary/activation-functions)**: An activation function is the non-linear function applied to a neuron's weighted sum before its output is passed on.
- **[Weight initialization](/glossary/weight-initialization)**: Weight initialization is the choice of starting values for a neural network's weights and biases before training begins.
- **[Learning rate schedules](/glossary/learning-rate-schedules)**: A learning rate schedule is a rule that changes the optimiser's learning rate as training progresses.

## Learn more

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