Glossary term
Glossary term
Foundations
The ability to explain or to present an ML model's reasoning in understandable terms to a human.
Most linear regression models, for example, are highly interpretable. (You merely need to look at the trained weights for each feature.) Decision forests are also highly interpretable. Some models, however, require sophisticated visualization to become interpretable.
You can use the Learning Interpretability Tool (LIT) to interpret ML models.
Created for this library
A bank's model risk team requires interpretability reports for every model that affects credit decisions before approval.
A medical AI team selects models with strong interpretability for diagnosis-assist features so clinicians can understand each prediction.
A regulatory consulting firm helps clients align their interpretability practices with upcoming AI rules in their jurisdiction.
Definition source: Google for Developers Machine Learning Glossary | Creative Commons Attribution 4.0 License