Zum Inhalt

Workshop Issues in XAI #5 -- Understanding Black Boxes: Interdisciplinary Perspectives September 5-7, 2022

Workshop Issues in XAI #5 -- Understanding Black Boxes: Interdisciplinary Perspectives

September 5th - 7th, 2022

Confirmed Speakers

  • Sabine Ammon, TU Berlin
  • Florian Boge, University of Wuppertal
  • Mieke Boon, University of Twente
  • Philipp Cimiano, University of Bielefeld
  • Juan M. Durán, TU Delft
  • Tim Hunsicker, Saarland University
  • Nicole Krämer, University of Duisburg-Essen
  • Anne Lauber-Rönsberg, TU Dresden
  • Sara Mann, TU Dortmund
  • Anna Monreale, University of Pisa
  • Andrés Páez, University of the Andes
  • Emanuele Ratti, Johannes Kepler University Linz
  • Nadine Schlicker, University Hospital of Marburg


Workshop Description

Artificial intelligent (AI) systems are used to great success in many contexts, e.g. for medical diagnosis or autonomous driving. They often depend on extremely complex algorithms designed to detect patterns in large amounts of data, which makes it difficult to discern their inner workings. However, especially in high-stakes situations, it is important to be able to evaluate desirable system properties, e.g. their safety, fairness or trustworthiness, and so to understand how they work. To address this concern, the field of explainable artificial intelligence (XAI) develops methods to make opaque AI systems understandable by means of explanations.

But what does it mean to understand an (opaque) system or its outputs? What is the link between explanations and understanding? How do different contexts affect the explainability and understandability of AI systems? How important is understanding really and how does this depend on the specific context of use, e.g. on legal vs. medical contexts? How can we make complex systems understandable at all and how do different explainability methods fare in this regard (e.g., surrogate models or perturbation-based methods)? What can theories of understanding and explanation from psychology and philosophy contribute to XAI, and how do these insights mesh with specific explainability approaches from computer science?

Clarifying relevant concepts such as understanding and explanation is an important fundamental step towards developing human-centered XAI methods; vice versa, researchers from philosophy and psychology can gain a deeper understanding of the concepts by reflecting on their application in XAI. In this light, our workshop will bring together researchers from philosophy, psychology, computer science, and law to push forward research on understanding and XAI.

Organization

Homepage: https://explainable-intelligent.systems/issuesinxai5/

Date: September 5, 2022 (Monday) – September 7, 2022 (Wednesday)

The workshop will begin at 11am (CET) on Monday and will end at 2pm (CET) on Wednesday.

 

Venue: International Meeting Center (IBZ), TU Dortmund (https://international.tu-dortmund.de/en/international-campus/international-meeting-center-ibz/) Address: TU Dortmund University, Emil-Figge-Straße 59, 44227 Dortmund, Germany

 

Currently, we are planning the workshop to be held completely in-person. The workshop language is English.

The workshop is organized within the research project “Explainable Intelligent Systems” (EIS) (https://explainable-intelligent.systems/). EIS is an interdisciplinary research group consisting of philosophers, computer scientists, psychologists, and legal scholars. At EIS we investigate how explainability of artificial intelligent systems contributes to the fulfillment of important societal desiderata.

The workshop is the 5th installment of the workshop series “Issues in XAI”, which is co-organized by EIS and its partners, the Leverhulme Centre for the Future of Intelligence (Cambridge), TU Delft, and the project BIAS (Leibniz University Hannover). Both the EIS project and the workshop are funded by the Volkswagen Foundation.

Organization: Eva Schmidt, Sara Mann

If you have any queries, please send an e-mail to sara.mann[at]tu-dortmund.de

Registration

If you would like to join our workshop, please register by sending an e-mail with subject header “Registration” to Sara Mann (sara.mann[at]tu-dortmund.de).

The deadline for registrations is Monday, August 22, 2022.

Kalender

Zur Veranstaltungsübersicht

Mensapläne

Anfahrt & Lageplan

Der Campus der Technischen Universität Dortmund liegt in der Nähe des Autobahnkreuzes Dortmund West, wo die Sauerlandlinie A45 den Ruhrschnellweg B1/A40 kreuzt. Die Abfahrt Dortmund-Eichlinghofen auf der A45 führt zum Campus Süd, die Abfahrt Dortmund-Dorstfeld auf der A40 zum Campus-Nord. An beiden Ausfahrten ist die Universität ausgeschildert.

Direkt auf dem Campus Nord befindet sich die S-Bahn-Station „Dortmund Universität“. Von dort fährt die S-Bahn-Linie S1 im 15- oder 30-Minuten-Takt zum Hauptbahnhof Dortmund und in der Gegenrichtung zum Hauptbahnhof Düsseldorf über Bochum, Essen und Duisburg. Außerdem ist die Universität mit den Buslinien 445, 447 und 462 zu erreichen. Eine Fahrplanauskunft findet sich auf der Homepage des Verkehrsverbundes Rhein-Ruhr, außerdem bieten die DSW21 einen interaktiven Liniennetzplan an.

Zu den Wahrzeichen der TU Dortmund gehört die H-Bahn. Linie 1 verkehrt im 10-Minuten-Takt zwischen Dortmund Eichlinghofen und dem Technologiezentrum über Campus Süd und Dortmund Universität S, Linie 2 pendelt im 5-Minuten-Takt zwischen Campus Nord und Campus Süd. Diese Strecke legt sie in zwei Minuten zurück.

Vom Flughafen Dortmund aus gelangt man mit dem AirportExpress innerhalb von gut 20 Minuten zum Dortmunder Hauptbahnhof und von dort mit der S-Bahn zur Universität. Ein größeres Angebot an internationalen Flugverbindungen bietet der etwa 60 Kilometer entfernte Flughafen Düsseldorf, der direkt mit der S-Bahn vom Bahnhof der Universität zu erreichen ist.