Skip to content

Glossary: Probability for ML

Held-out data

Also written: held out, held-out, validation data

Data kept aside and not used for fitting a model, so it can give an honest check of how the model performs. For example, a temperature can be fitted on one half of the data and calibration checked on the other half.

Where the book teaches it

Related terms

Temperature scalingOverfittingLeave-one-out