AI engineering glossary · ML fundamentals
What is OOD (out-of-distribution)?
Out-of-distribution (also called OOD): Describes inputs that differ substantially from the data a model was trained on. Models often behave unpredictably or confidently wrongly on such inputs, so detecting them is important for safe deployment.
Out-of-distribution: an example
A model trained on clear daylight road photos is shown a snowstorm night image; that is far outside what it learned from.
Related terms
More ML fundamentals terms
- Outlier
- Overfitting
- Overparameterisation
- PAC learning
- Parameter
- Parametric model
- Pipeline
- Probabilistic model
Where you learn it
Out-of-distribution is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.