When a model learns its training data too specifically — including its quirks and noise — and performs worse on new, unseen situations as a result.
It's the AI equivalent of a student who memorises exact practice-test answers instead of understanding the underlying concept, then struggles on the real exam.
One of 60 free AI glossary terms
Plain-language definitions for the AI jargon you'll actually run into — no email needed, ever, for this section.
Browse the Full Glossary →