Topic | Name | Description |
---|---|---|
Topic 5 | Lecture slides | |
Topic 6 | Slides Sune Holm Lecture Ethics Health AI | |
AI and Trust: Explainability, Transparency | AI and Trust: Explainability, Transparency (Part 1) - Prof. Dragutin Petkovic | |
AI and Trust: Explainability, Transparency (Part 2) - Prof. Dragutin Petkovic | ||
Z-Inspection: A Process to Assess Trustworthy AI | ||
Topic 12 | Week of December 4th | Video lecture: Trustworthy AI: A Human-Centered Perspective
https://www.youtube.com/watch?v=yG_poIyRwT8 Assignments of the week:
Paper 1: Brundage et al. (2020) – Toward Trustworthy AI Development:Mechanisms for Supporting Verifiable Claims
https://arxiv.org/pdf/2004.07213.pdf
Paper 2: Arya et al. (2019) – One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques
https://arxiv.org/pdf/1909.03012.pdf |