# Generalization curve

> A plot of both training loss and validation loss as a function of the number of iterations. A generalization curve can help you detect possible overfitting.[^1]

A plot of both [training loss](https://wiki.g15e.com/pages/Training%20loss.txt) and [validation loss](https://wiki.g15e.com/pages/Validation%20loss.txt) as a function of the number of [iterations](https://wiki.g15e.com/pages/Iteration%20(machine%20learning.txt)). A generalization curve can help you detect possible [overfitting](https://wiki.g15e.com/pages/Overfitting.txt).[^1]

## Footnotes

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