# Iteration (machine learning)

> A single update of a model's parameters--the model's weights and biases--during training. The batch size determines how many examples the model processes in a single iteration. For instance, if the batch size is 20, then the model processes 20 examples before adjusting the parameters. When training a neural network, a single iteration involves the following two passes:[^1]

A single update of a [model](https://wiki.g15e.com/pages/Model%20(machine%20learning.txt))'s parameters--the model's [weights](https://wiki.g15e.com/pages/Weight%20(machine%20learning.txt)) and [biases](https://wiki.g15e.com/pages/Bias%20(machine%20learning.txt))--during [training](https://wiki.g15e.com/pages/Training%20(machine%20learning.txt)). The [batch size](https://wiki.g15e.com/pages/Batch%20size%20(machine%20learning.txt)) determines how many examples the model processes in a single iteration. For instance, if the batch size is 20, then the model processes 20 examples before adjusting the parameters. When training a [neural network](https://wiki.g15e.com/pages/Artificial%20neural%20network.txt), a single iteration involves the following two passes:[^1]

1. A forward pass to evaluate loss on a single [batch](https://wiki.g15e.com/pages/Batch%20(machine%20learning.txt)).
2. A backward pass ([backpropagation](https://wiki.g15e.com/pages/Backpropagation.txt)) to adjust the model's parameters based on the [loss](https://wiki.g15e.com/pages/Loss%20(machine%20learning.txt)) and the [learning rate](https://wiki.g15e.com/pages/Learning%20rate.txt).

## Footnotes

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