AI engineering glossary · AI ethics law product
What is interpretability?
Interpretability (also called model interpretability): The degree to which a human can understand how a model turns inputs into outputs, ideally by inspecting the model itself. A small decision tree or a linear model is interpretable, whereas a deep network with millions of weights is not, at least without extra tools.
Interpretability: an example
A logistic regression with five features lets an analyst read off that each extra missed payment lowers the approval score by a fixed amount.
Related terms
- Explainable AI
- Intrinsically interpretable model
- Post-hoc explanation
- Black-box model
More AI ethics law product terms
Where you learn it
Interpretability is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.