# Artificial neuron

> In machine learning, a distinct unit within a hidden layer of a neural network. Each neuron performs the following two-step action:

In [machine learning](https://wiki.g15e.com/pages/Machine%20learning.txt), a distinct unit within a [hidden layer](https://wiki.g15e.com/pages/Hidden%20layer.txt) of a [neural network](https://wiki.g15e.com/pages/Artificial%20neural%20network.txt). Each neuron performs the following two-step action:

1. Calculates the [weighted sum](https://wiki.g15e.com/pages/Weighted%20sum.txt) of input values multiplied by their corresponding weights.
2. Passes the weighted sum as input to an [activation function](https://wiki.g15e.com/pages/Activation%20function.txt).

A neuron in the first hidden layer accepts inputs from the feature values in the [Input layer](https://wiki.g15e.com/pages/Input%20layer.txt). A neuron in any hidden layer beyond the first accepts inputs from the neurons in the preceding hidden layer. For example, a neuron in the second hidden layer accepts inputs from the neurons in the first hidden layer.[^1]

## Footnotes

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