Interpretability
AIGP glossary · Last reviewed: · By Victor Humenhuk (AIGP certified)
Interpretability - Degree a human can consistently understand and predict how the model works internally.
In the AIGP body of knowledge, Interpretability comes up under Module 8: AI Governance Vocabulary.
Interpretability in context
- Testing is continuous, risk-tailored and documented - test for ==accuracy, robustness, reliability, privacy, interpretability, safety, security and bias==. (Testing and Validation)
- ==Conformity assessment is the EU AI Act gate for high-risk systems before market==, and explainability (why an output) is distinct from interpretability (how the model works inside). (Governance, assurance and oversight)
Where Interpretability is covered in the AIGP study notes
Related terms
- AI governance
- Accountability
- AI assurance
- AI audit
- Oversight
- Transparency
- Explainability
- Contestability
- Conformity assessment
- Impact assessment
Test yourself on Interpretability
Recognising a definition is not the same as applying it in an exam scenario. Work through the free AIGP practice questions, or read the full AIGP study guide - every study note is free.