# Artificial neural network

> A model containing at least one hidden layer. A deep neural network is a type of neural network containing more than one hidden layer. Each neuron in a neural network connects to all of the nodes in the next layer. Some neural networks can mimic extremely complex nonlinear relationships between different features and the label.[^1]

A [model](https://wiki.g15e.com/pages/Model%20(machine%20learning.txt)) containing at least one [hidden layer](https://wiki.g15e.com/pages/Hidden%20layer.txt). A [deep neural network](https://wiki.g15e.com/pages/Deep%20neural%20network.txt) is a type of neural network containing more than one hidden layer. Each [neuron](https://wiki.g15e.com/pages/Artificial%20neuron.txt) in a neural network connects to all of the nodes in the next layer. Some neural networks can mimic extremely complex nonlinear relationships between different [features](https://wiki.g15e.com/pages/Feature%20(machine%20learning.txt)) and the [label](https://wiki.g15e.com/pages/Label%20(machine%20learning.txt)).[^1]

## See also

- [Convolutional neural network](https://wiki.g15e.com/pages/Convolutional%20neural%20network.txt)
- [Recurrent neural network](https://wiki.g15e.com/pages/Recurrent%20neural%20network.txt)
- [ML crash course - Neural networks](https://wiki.g15e.com/pages/ML%20crash%20course%20-%20Neural%20networks.txt)

## Footnotes

[^1]: https://developers.google.com/machine-learning/glossary#neural-network