Loading timeline…
20102010s
Explainable AI (XAI)
Methods and techniques to interpret the hidden decisions mathematically of deep neural networks.
Why It Was Important
As deep 'black box' models entered healthcare, finance, and criminal justice, tracing why a model made a decision became legally and ethically paramount. Methods like LIME and SHAP values emerged to reverse-engineer feature importances, attempting to build human trust in algorithmic outputs.
Who Invented It
AI Ethics and Safety Community
A broad coalition of regulators, ethicists, and mathematical researchers.
Applications
- Algorithmic Auditing
- Healthcare Deployment
- Regulatory Compliance
Key Papers
- "Why Should I Trust You?": Explaining the Predictions of Any Classifier
Marco Tulio Ribeiro, Sameer Singh, Carlos Guestrin · KDD 2016
Videos
Introduction to Explainable AI (XAI) | Interpretable models, agnostic methods, counterfactuals
A Data Odyssey