Dr. Danil Prokhorov, Toyota Research Institute NA, Ann Arbor, Michigan
- Vice President for Conferences of the INNS (International Neural Network Society)
- Associate Editor of Neural Networks, IEEE Trans. on Neural Networks and IEEE Trans. on Autonomous Mental Development
- Senior Member of both IEEE and INNS
- Reviewer of grants proposals for the U.S. National Science Foundation (NSF)
- Extended Experience in the Scientific Research Laboratory of Ford Motor Co. (Metropolitan Detroit area)
Subject: “Computational Intelligence in Automotive Applications”
Computational intelligence is traditionally understood as encompassing artificial neural, fuzzy and evolutionary methods and associated computational techniques. Different CI methodologies often get combined with each other and with non-CI methods to achieve superior results in various applications. In this presentation I will discuss CI methodological issues and illustrate them with several applications from the areas of vehicle manufacturing, vehicle system monitoring and control, as well as active safety. These will be representative of CI applications in the industry and beyond. I will also discuss some lessons learned about successful and yet-to-be-successful industrial applications of CI.
Professor David Robertson, University of Edinburgh, UK
- Head of School of Informatics
- Leader, Software Systems and Processes research group
- Editor in Chief, AI Review journal, Automated Experimentation journal
Subject: “Knowledge Engineering on a Social Scale”
For much of its history, formal knowledge representation has aimed to describe knowledge independently of the personal and social context in which it is used, with the advantage that we can automate reasoning with such knowledge using mechanisms that also are context independent. This sounds good until you try it on a large scale and find out how sensitive to context much of reasoning actually is. Humans, however, are great hoarders of information and sophisticated tools now make the acquisition of many forms of local knowledge easy. The question is: how to combine this beyond narrow individual use, given that knowledge (and reasoning) will inevitably be contextualised in ways that may be hidden from the people/systems that may interact to use it? This is the social side of knowledge representation and automated reasoning. I will discuss how the formal reasoning community has adapted to this new view of scale, using examples from my own research and that of others.
Prof. Dr. Bernard De Baets, KERMIT, Ghent University, Belgium
- Full Professor at Ghent University
- Co-Editor-in-Chief, Fuzzy Sets and Systems journal
Subject: “Monotonicity issues in fuzzy modelling, machine learning and decision making”
In many modelling problems, there exists a monotone relationship between one or more of the input variables and the output variable, although this may not always be fully the case in the observed input-output data due to data imperfections. Monotonicity is also a common property of evaluation and selection procedures. In contrast to a local property such as continuity, monotonicity is of a global nature and any violation of it is therefore simply unacceptable. We explore several problem settings where monotonicity matters, including fuzzy modelling, machine learning and decision making.