# Semi-supervised learning

> Training a model on data where some of the training examples have labels but others don't. One technique for semi-supervised learning is to infer labels for the unlabeled examples, and then to train on the inferred labels to create a new model. Semi-supervised learning can be useful if labels are expensive to obtain but unlabeled examples are plentiful. Self-training is one technique for semi-supervised learning.[^1]

Training a [model](https://wiki.g15e.com/pages/Model%20(machine%20learning.txt)) on data where some of the training examples have labels but others don't. One technique for semi-supervised learning is to infer [labels](https://wiki.g15e.com/pages/Label%20(machine%20learning.txt)) for the [unlabeled examples](https://wiki.g15e.com/pages/Unlabeled%20example.txt), and then to train on the inferred labels to create a new model. Semi-supervised learning can be useful if labels are expensive to obtain but [unlabeled examples](https://wiki.g15e.com/pages/Unlabeled%20example.txt) are plentiful. [Self-training](https://wiki.g15e.com/pages/Self-training%20(machine%20learning.txt)) is one technique for semi-supervised learning.[^1]

## Footnotes

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