Using Explainable AI to garner trust and overcome adoption inhibitors
summary
95% cite cultural, organizational and process barriers to AI adoption, and trust—not just transparency—is the bottleneck. Presents concrete XAI methods: shop method, anchors, contrastive explanations and counterfactuals, and demos an explainer dashboard applied to the Kaggle Titanic set where sex dominates feature importance and sibling/spouse count unexpectedly raises survival odds. Recommends turning explainability into usable understandability via UX, ethical guard rails, design thinking and C‑suite accountability, and cites GDPR’s right to explanation as an enforceable step.
AI-written summary · about
chapters (17)
- 0:00Start
- 0:13Why Is an Ai More Pervasive
- 0:25An Example of Explainable Ai in Action
- 4:42What Explainability Is
- 5:07Transparency
- 6:10Explainability
- 7:48Human Centered User Experience
- 8:26Ethical Guard Rails
- 9:54Design Thinking
- 10:43Accountability Standards
- 12:55The Shaft Model
- 14:21Sum Method Contrastive Explanations Method
- 16:28Explainer Dashboard
- 18:50Individual Prediction
- 19:39The Contributions Plot
- 21:24Partial Dependence Plot
- 23:17Explainability and Understandability
related talks
19mMoving Forward with Explainable AI: Adoption Rate & Essential Dimensions for a Reliable Use
15mIntroduction to Explainable AI
28mThe Need for Explainable AI
35mWhy Do You Need an Explainable Ai?
39mThe Search for Transparency and Accountability in the Age of...
16mBuilding Trust through Explainable AI
24mWhy and How to Build Explainability into your ML Workflow
48mExplainable Artificial Intelligence (XAI): Why, When, and How?