Bring in the Lawyers: Explainable AI Driven Decision-making
summary
Covers explainable AI for enterprise decision-making, focusing on regulatory and legal risks (e.g., GDPR, banking, fraud detection) that push organizations toward interpretable models like logistic regression and decision trees. Surveys recent research and practical approaches for explaining black‑box models (neural networks) in real-world use cases—showing how explanations must be role‑relevant to build trust and meet legal/regulatory requirements.
AI-written summary · about
chapters (5)
- 0:00Start
- 3:26Real World industrial Strength Solutions Use Hierarchical Systems of Numerous Complex Model Systems
- 9:06Machine Learning in the Wild
- 9:50ML Algorithmic Trade-Off
- 12:05Disadvantages of Black Box Systems
related talks
32mOn the Importance of Explainability
24mToward Trustworthy AI: Explainability and Robustness
19mMoving Forward with Explainable AI: Adoption Rate & Essential Dimensions for a Reliable Use
45mAI-404: Explanation Not Found
45mWhat Security Measures Are Necessary to Trust in AI?
39mThe Search for Transparency and Accountability in the Age of...
46mCan you trust your AI?
50mDehumanizing Agents: Why Explainability is Crucial in the LLM Era