MAKE-Explainable AI

MAKE-Explainable AI

Special Session of the CD-MAKE conference organized
by Katharina HOLZINGER (1), Zeynep AKATA (2), Peter KIESEBERG (1), et al. and Andreas HOLZINGER (3)

(1) Secure Business Austria SBA Research Vienna, AT
(2) University of Amsterdam, NL
(3) Medical University Graz, AT

(organization committee under formation – please contact Andreas Holzinger for inquiries)

Current as of 24.11.2017 19:00 CET

The new European General Data Protection Regulation (GDPR and ISO/IEC 27001) entering into force on May, 25, 2018, affects practically all machine learning and artificial intelligence applied to business. For example it will be difficult to apply black-box approaches for professional use in certain business applications, because they are not able to explain why a decision has been made.

This special session aims to bring together international cross-domain experts interested in law/causality and artificial intelligence/machine learning to stimulate research in explainable AI – towards making decisions interpretable, comprehensible and reproducible. Accepted papers will be presented at the conference and published in the IFIP CD-MAKE Volume of Springer Lecture Notes in Artificial Intelligence (LNAI).

The grand goal of future AI is to make results understandable and transparent and to answer the question of how and why a result was achieved. In fact: “Can we explain how and why a result was achieved?” In the future it is essential not only to answer the question “Which objects are similar?”, but  to answer “Why are those objects similar?” – “What are the underlying explanatory facts that the machine learning algorithms made this decison”.

This highly relevant emerging area is important for all application areas, ranging from health informatics to cyber defense – see the DARPA program on explainable artificial intelligence.

Note: The GDPR replaces the data protection Directive 95/46/EC) of 1995. The regulation was adopted on 27 April 2016 and becomes enforceable from 25 May 2018 after now a two-year transition period and, unlike a directive, it does not require national governments to pass any enabling legislation, and is thus directly binding – which affects practically all data-driven businesses and particularly machine learning and AI technology!

Special Session Keynote Speaker (under construction)

Special Session Committee (under construction)