Machine Learning Foundations

Generalization, explained

Generalization is a model's ability to perform well on new data, not just the data used during training.
Back to Glossary

Part of the Semantic Notion technical glossary.

Short Definition

Generalization is a model's ability to perform well on new data, not just the data used during training.

Intuition

A useful model learns the pattern behind the examples, not only the examples themselves.

Technical Definition

Generalization measures expected performance on unseen samples drawn from the target distribution, usually estimated with validation or test data.

Example

A speech model generalizes if it handles new speakers and accents that were not in the training examples.

Common Misunderstandings

Generalization cannot be proven by training metrics alone.
A model can generalize in one deployment setting and fail after distribution shift.

Start here

Need the broader concept map?

Return to the glossary index to move from this definition into adjacent AI, ML, mathematics, and computer science terms.