Skip to content
Main menu hidden.

Image: AdobeStock

XAI – Explainable AI

Research group Explainable AI is developed in order to make the decisions or actions taken by an AI agent understandable for humans who interact with the system. Not only do many users prefer to have a system that has explanations for its actions, in several countries the legal framework is moving towards requiring this functionality from AI systems.

The research group XAI – Explainable AI consists out of:

Professor Kary Främling
Kary Främling is the head of the eXplainable Artificial Intelligence (XAI) team at the university of Umea in Sweden. Kary has been an active researcher in Artificial Intelligence since the 1980's, focusing on topics such as neural network learning, multiple criteria decision support and reinforcement learning. His PhD thesis from 1996 entitled « Learning and Explaining Preferences with Neural Networks for Multiple Criteria Decision Making » (in French : Modélisation et apprentissage des préférences par réseaux de neurones pour l'aide à la décision multicritère ») can be considered to be one of the first research initiatives that explicitly address the topic of Explainable Artificial Intelligence, including aspects such as confidence, robustness and reliability of the reasoning. He is currently Professor in Data Science at Umeå University, Sweden.

Kary is also the Founder and Head of the team Adaptive Systems of Intelligent Agents, (formerly known as the team « Distributed Information Architectures for collaborative LOGistics ») at Aalto University, Finland. The DIALOG software developed by the team was presumably the first Internet of Things (IoT) implementation worldwide in 2002. DIALOG was described in research articles since 2002 (see e.g. « FRÄMLING, Kary, HOLMSTRÖM, Jan, ALA-RISKU, Timo, KÄRKKAINEN, Mikko. Product agents for handling information about physical objects. Report of Laboratory of Information Processing Science series B, TKO-B 153/03, Helsinki University of Technology, 2003. 20 p. »).

Kary has 147 published research papers, 2608 citations, and h-index 22 (source: Google Scholar date: 22/10/2018). He is a member of the Editorial Board of the Computers in Industry journal, he has been the reviewer for 29 journals and Member of the Program or Scientific Committees of 32 conferences and workshops.

He was the Guest Editor of the Special Issue on Intelligent Products of the Computers in Industry journal in 2009, together with Prof. Duncan McFarlane from Cambridge University.

Kary has organized 6 special sessions and workshops :

  • Workshop on "Reinforcement learning in non-stationary environments" of ECML 2005;
  • Special Session on Closed-loop PLM & Intelligent products at the International Conference on Industrial Engineering and Systems Management, 2011;
  • Special Session on Intelligent Products at 14th IFAC Symposium on Information Control Problems in Manufacturing (INCOM 2012);
  • Special Session on Intelligent Products in Manufacturing & Services Systems, 2nd International Conference on Communications, Computing and Control Applications (CCCA'2012);
  • Special Session on Intelligent Products: concepts, deployments and related aspects at 11th IFAC Workshop on Intelligent Manufacturing Systems (IMS'13);
  • Special Session on Smart City Interoperability and Cross-Platform Implementation at APMS'2018.
  • Special session Technologies and Infrastructures for Smart grids, Buildings, and Cities at IEEE International Conference on Industrial Informatics (INDIN'19)

Amber Zelvelder, PhD Student holding a BSc in Computer science from Oxford Brookes University and a MSc in Cybernetics from the University of Reading. She has a professional background in Web Development, Business Intelligence, Assistive Technology and Information Analysis.

Research leader

Kary Främling


Participating departments and units at Umeå University

Department of Computing Science

Research area

Computing science
Latest update: 2018-12-04