Issues in Explainable AI:
Black Boxes, Recommendations, and Levels of Explanation

Saarbrücken, Germany
Sept 30 – Oct 02, 2019

An EIS Workshop



“Explainable Intelligent Systems” (EIS) is an interdisciplinary research project at Saarland University and the University of Zurich, funded by a generous grant from the Volkswagen Foundation. Together with CPEC, the Center for Perspicuous Computing TRR 248, EIS invites to a workshop on issues in Explainable AI.

EIS is concerned with questions such as:
+ How does the need for trustworthy intelligent systems induce a need for explainable AI?
+ What kind of explanations do intelligent systems need to provide of their behavior in particular contexts?
+ How can such systems be designed so as to provide the needed explanations?

The workshop brings together experts from philosophy, computer science, law, and psychology to tackle questions such as the above.

Invited speakers:
+ Dan Brooks (University of Cincinnati)
+ Hans-Johann Glock (University of Zurich)
+ Geoff Keeling (Leverhulme Centre for the Future of Intelligence, Cambridge)
+ Farzad Nozarian (DFKI, Saarland University)
+ Rune Nyrup (Leverhulme Centre for the Future of Intelligence, Cambridge)
+ Sonja Ötting (University of Bielefeld)
+ Alejandro Saucedo (Institute for Ethical AI and Machine Learning, London)
+ Marija Slavkovik (University of Bergen)
+ Clemens Stachl (Ludwig-Maximilians-Universität Munich)
+ Silja Vöneky (University of Freiburg)

The workshop includes both traditional talks and interactive discussion sessions. Additionally, there will be a public outreach event (in German) on “Explainable Intelligent Systems: Understanding. Responsibility. Trust”. It will consist of a public keynote by Silja Vöneky and a subsequent panel discussion, to take place at Saarbrücken’s town hall, see https://explainable-intelligent.systems/offentliche-veranstaltungen

The workshop is organized by EIS and its partners
+ Center for Perspicuous Computing https://perspicuous-computing.science/
+ Saarland University https://www.uni-saarland.de/
+ Universität Zürich https://www.uzh.ch/
in cooperation with
+ Leverhulme Centre for the Future of Intelligence, Cambridge
+ TU Delft
+ German Research Center for Artificial Intelligence DFKI

Further and up-to-date information can be found here: https://explainable-intelligent.systems/workshop/

Participation in the event is free of charge, but a registration is required for logistic reasons, by e-mail to Jeannette Lang .