The LOEWE Research Cluster WhiteBox is aimed at developing methods at the intersection between Cognitive Science and AI to make human and artificial intelligence more understandable. It started its interdisciplinary research work in 2021 with the basic hypothesis that explaining an artificial intelligence system may not be fundamentally different from the task of explaining intelligent goal-directed behavior in humans.
The 2023 WhiteBox Symposium on Explainability gathers an excellent line-up of European explainability researches with different scientific backgrounds. A variety of explainability facets will be featured and discussed in the light of the preliminary WhiteBox results.
Guests are very welcome. Participation is free of charge.
| Monday, 27.03.2023 | |
|---|---|
| 08:30 | Opening with coffee & tea |
| 09:00 |
Welcome & WhiteBox introduction Constantin Rothkopf, TU Darmstadt Still no free lunch from deep learning: explaining human decision-making under risk |
| 10:00 |
Carlos Zednik, Eindhoven University of Technology Disentangling explanation, interpretation, and justification in explainable artificial intelligence |
| 11:00 | Break |
| 11:30 |
Stefan Roth, TU Darmstadt *) Explainable deep networks for computer vision |
| 12:30 | Lunch |
| 13:30 | Poster-Session: WhiteBox – current work and results |
| 15:00 |
Wojciech Samek, TU Berlin / Fraunhofer HHI Concept-Level Explainable AI |
| 16:00 |
Hermann Müller, JLU Gießen Explaining observed motor behavior in goal oriented movements as stochastic optimization |
| 17:00 | Final discussion & closing remarks |
| *) Short-term programme adjustment as Ruth Byrne (Trinity College Dublin) was unable to attend due to a traffic strike in Germany. |
S3|20, Room 18 “Friedrich-Ludwig-Weidig-Saal”
Rundeturmstraße 10
64283 Darmstadt
The registration is closed.
