# Loss (machine learning)

> During the training of a supervised learning, a measure of how far a model's prediction is from its label. A loss function calculates the loss.[^1]

During the [training](https://wiki.g15e.com/pages/Training%20(machine%20learning.txt)) of a [supervised learning](https://wiki.g15e.com/pages/Supervised%20learning.txt), a measure of how far a model's [prediction](https://wiki.g15e.com/pages/Prediction%20(machine%20learning.txt)) is from its [label](https://wiki.g15e.com/pages/Label%20(machine%20learning.txt)). A [loss function](https://wiki.g15e.com/pages/Loss%20function.txt) calculates the loss.[^1]

## Footnotes

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