Lecture: Making explainable artificial intelligence understandable Szymon Bobek, Jagellonian University
| Start: | Tuesday 27. October 2026, 15:00 |
|---|---|
| End: | Tuesday 27. October 2026, 16:30 |
| Event language: | angličtina |
| Place: | NB 473 |
| Online event: | Microsoft Teams |
| Contact person: | Vojtěch Svátek |
| Tags: | #prednaska |
What the talk will cover:
- Lessons from industrial use-cases: predictive maintenance,explainable anomaly detection, and visual quality inspection.
- Evidence from a user-centric evaluation of explanation methods.
- Explainability methods based on rules, prototypes, counterfactuals, and feature attribution.
- Open research directions in explainability with neurosymbolic AI, LLMs, VLMs, eye-tracking analysis and conversational systems for interactive, multimodal and expert-aligned explanations.