SHAP, LIME and other explainability techniques
Tools that show which inputs drove a model’s output.
SHAP assigns each feature a contribution to a prediction; LIME approximates the model locally with a simpler one. Global explanations describe overall behaviour, local ones explain individual decisions. Explanations are approximations and can mislead.
On the exam
For adverse decisions about people, local explanations help give reasons. Validate that explanations are faithful to the model.
Related terms
- ExplainabilityBeing able to say why an AI system produced a given output.
- Transparency and disclosureBeing open that AI is used, and how.
AAIA Test yourself on this with timed AAIA practice questions in the AAIA Exam Simulation Hub, or read the free AAIA exam guide.
Test yourself with today’s question of the day.
