Dictionary · Four Principles of Explainable Artificial Intelligence

A global explanation produces a model that approximates the non-interpretable model.

A local explanation explains a subset of decisions or is a per-decision explanation.

Post-hoc explainability targets models that are not readily interpretable by design by resorting to diverse means to enhance their interpretability, such as text explanations, visual explanations, local explanations, explanations by example, explanations by simplification and feature relevance explanations techniques. Each of these techniques covers one of the most common ways humans explain systems and processes by themselves.