AI Glossary

Oversampling

What does “Oversampling” mean?

Oversampling: Increasing how often a group of examples appears during training.

Oversampling visual guide: Increasing how often a group of examples appears during training.
Visual guide Open full size (new tab)

What is an example of “Oversampling”?

A trainer draws examples of a rare class more frequently.

Keep learning

See also

DatasetTermTraining dataTermData labelingTermData augmentationTermClass imbalanceTerm

Same topic

Hard negativeTermUndersamplingTermParameter-efficient fine-tuningTermOverfittingTermPolicy in reinforcement learningTerm