# Generalization (machine learning)

> A model's ability to make correct predictions on new, previously unseen data. A model that can generalize is the opposite of a model that is overfitting.[^1]

A [model](https://wiki.g15e.com/pages/Model%20(machine%20learning.txt))'s ability to make correct predictions on new, previously unseen data. A model that can generalize is the opposite of a model that is [overfitting](https://wiki.g15e.com/pages/Overfitting.txt).[^1]

You [train](https://wiki.g15e.com/pages/Training%20(machine%20learning.txt)) a model on the [examples](https://wiki.g15e.com/pages/Example%20(machine%20learning.txt)) in the [training set](https://wiki.g15e.com/pages/Training%20data.txt). Consequently, the model learns the peculiarities of the data in the training set. Generalization essentially asks whether your model can make good [predictions](https://wiki.g15e.com/pages/Prediction%20(machine%20learning.txt)) on examples that are *not* in the training set.

To encourage generalization, [regularization](https://wiki.g15e.com/pages/Regularization%20(machine%20learning.txt)) helps a model train less exactly to the peculiarities of the data in the training set.

## See also

- [ML crash course - Datasets, generalization, and overfitting](https://wiki.g15e.com/pages/ML%20crash%20course%20-%20Datasets,%20generalization,%20and%20overfitting.txt)

## Footnotes

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