The Search for Transparency and Accountability in the Age of...
summary
Argues that Responsible AI needs XAI to survive in production and shows concrete tooling and findings: uses IBM bias checks on the German credit dataset, mentions Intel explainable AI toolkit that centralizes SHAP and LIME, and cites PPML and OpenFL for privacy and federated training. Presents a human-focused evaluation with the Merlin bird app comparing heat map, example‑based, concept‑based and prototype explanations, finding experts prefer numeric concepts while lay users prefer visual examples, leaving a clear user‑knowledge gap.
AI-written summary · about
chapters (8)
- 0:00Responsible explainable AI
- 5:43Responsible AI development tools
- 12:31Explainability perspectives
- 16:23Model explainability challenges
- 22:23Centralized explainable AI tools
- 26:41Human-centered explainability
- 32:07Principles to responsible AI
- 36:05Q&A
related talks
39mSponsored Session: The Search for Transparency and Accountability in the Age of AI: RAI & XAI as Essential Tools
46mCan you trust your AI?
15mIntroduction to Explainable AI
30mTrustworthy AI - opening up the black box
11mKeynote: Trusted AI: Bringing Trust Back into AI through Open Source
37mTrusted and Responsible AI (Explainability, Adversarial, Bias, Fairness)
26mResponsible AI-What, Why, How and Future!
37mBuilding a case for Fair and bias-free AI