AISB 2020 Symposium
Overcoming Opacity in Machine Learning

April 6th-9th, 2020
St Mary’s University, London

boxes

AISB 2020 Symposium
Overcoming Opacity in Machine Learning

April 6th-9th, 2020
St Mary’s University, London

Boxes


Computing systems are opaque when their behavior cannot be explained or understood. This is the case when it is difficult to know how or why inputs are transformed into corresponding outputs, and when it is not clear which environmental features and regularities are being tracked. The widespread use of machine learning has led to a proliferation of opaque computing systems, giving rise to the so-called Black Box Problem in AI. Because this problem has significant practical, theoretical, and ethical consequences, research efforts in Explainable AI aim to solve the Black Box Problem through post hoc analysis, or to evade the Black Box Problem through the use of interpretable systems. Nevertheless, questions remain about whether or not the Black Box Problem can actually be solved or evaded, and if so, what it would take to do so.

This symposium brings together researchers from Artificial Intelligence, Cognitive Science, Philosophy, and Law to investigate the nature, causes, and consequences of opacity in different scientific, technical, and social domains, as well as to explore and evaluate recent efforts to overcome opacity in Explainable AI.


Venue & Registration

The symposium will be held concurrently with other symposia at the annual convention of the Society for the Study of Artificial Intelligence and Simulation of Behavior (AISB). The AISB convention takes place from April 6th to 9th, 2020, at St Mary’s University in Twickenham, London, UK.

Early-bird registration is now possible via the AISB convention homepage!


Program

The keynote speaker at the symposium (pending confirmation) will be Brent Mittelstadt (Oxford Internet Institute, University of Oxford).

Further program information will be posted as soon as it is available.


Call for Papers

Submissions are solicited for a full-day symposium on opacity, the Black Box Problem, and Explainable AI, and may take the form of full papers (up to 8 pages) or extended abstracts (up to 2 pages). These may report on novel methods and technical solutions in Explainable AI, present philosophical work on the Black Box Problem and its solution, and/or explore the social, legal, and ethical ramifications of opacity. Submissions with an interdisciplinary focus are especially encouraged.

Papers and extended abstracts should be formatted according to the ECAI style guides (PDF, LaTeX, or Word), prepared for blind review, and submitted by email to opacity@explanations.ai with "[submission]" in the subject. The authors of all accepted submissions will be invited to give 30-minute presentations at the symposium, as well as to submit camera-ready versions to be published in the AISB convention proceedings.

Submission deadline: January 10th, 2020
Notification of acceptance: February 10th, 2020
Camera-ready deadline: March 2nd, 2020


Organizing Committee

Carlos Zednik, Otto-von-Guericke University Magdeburg
Hannes Boelsen, Otto-von-Guericke University Magdeburg


Program Committee

Colin Allen, University of Pittsburgh
Cameron Buckner, University of Houston
Nir Fresco, Ben-Gurion University of the Negev
Frank Jäkel, Technical University Darmstadt
Holger Lyre, Otto-von-Guericke University Magdeburg
Saskia Nagel, RWTH Aachen University
Constantin Rothkopf, Technical University Darmstadt
Sebastian Stober, Otto-von-Guericke University Magdeburg