|IEEE CEC 2010 Invited Sessions|
Playing Games with Computational Intelligence
Prof. Simon Lucas
University of Essex, UK
Monday, July 19
15:30h - 16:30h
Games provide an ideal environment in which to study computational intelligence, offering a range of challenging and engaging problems. This talk will begin with an overview of the field including some sample applications and an introduction to the main learning algorithms (evolution and temporal difference learning) in the context of games.
Despite each of these having a long history, there is still little agreement on which works best when, and why. I'll offer some insights into by showing the dependence of the algorithms on the choice of function approximator, and also show how information theory can help to guide the choice of algorithm.
Simon M. Lucas (SMIEEE) is a professor of computer science at the University of Essex (UK), where he leads the game intelligence group. He is the founding editor-in-chief of the IEEE Transactions on Computational Intelligence and AI in Games. His main research interests are evolutionary computation, games, and pattern recognition, and he has published widely in these fields with over 130 peer-reviewed papers. He was chair of IAPR Technical Committee 5 on Benchmarking and Software (2002 - 2006) and is the inventor of the scanning n-tuple classifier, a fast and accurate OCR method. Professor Lucas has chaired or co-chaired many international conferences, including the first IEEE Symposium on Computational Intelligence and Games in 2005. He is an associated editor of the IEEE Transactions on Evolutionary Computation, and the Springer Journal of Memetic Computing. He was an invited keynote speaker or tutorial speaker at IEEE CEC 2007, IEEE WCCI 2008, IEEE CIG 2008, PPSN 2008, and IEEE CEC 2009.
Modeling and Optimization for Large Engineering Systems: Hybrid Computational Intelligence and Multi-agent System Approach
Dr. Dipti Srinivasan
National University of Singapore, Singapore
Wednesday, July 21
14:30h - 15:30h
Intelligent agents and multi-agent systems offer a particularly attractive approach for the design and implementation of complex, flexible and scalable information systems. Such systems are particularly well suited for large engineering systems such as transportation and energy systems. This talk will discuss modelling of such systems using distributed multi-agent systems that incorporate different computational intelligence-based methodologies in knowledge acquisition, decision-making, learning, and goal formulation. This hybridization presents several new, innovative distributed cooperative problem solving approaches, incorporating advanced cooperation mechanisms in multi-agent systems and implementing them using various computational intelligence techniques and other relevant algorithms. Simulation results obtained on two large engineering problems will be discussed.
Dipti Srinivasan is an Associate Professor at the Electrical & Computer Engineering department at the National University of Singapore. Her main areas of interest are neural networks, evolutionary computation, intelligent multi-agent systems, and application of computational intelligence techniques to engineering optimization, planning and control problems. Her research has focused on the development of hybrid neural network architectures, learning methods and their practical applications for large complex engineered systems, such as the electric power system and urban transportation systems. These systems are examined in various projects by applying multidisciplinary methods that are able to cope with the problems of imprecision, learning, uncertainty and optimization, when concrete models are constructed.
She is an active member of IEEE, and is currently serving as the Vice-Chair of IEEE Women in Computational Intelligence (WCI) committee. She is the current chair of the IEEE Power Engineering Chapter, Singapore, member of the IEEE Computational Intelligence Chapter, and a member of the Intelligent Transport System technical committee. She serves on editorial boards of many journals including IEEE Transactions on Intelligent Transportation Systems, IEEE Transactions on Neural Networks, International Journal of Uncertainty, Fuzziness and Knowledge-based Systems, and Neurocomputing journal.
Evolutionary Computation for Risk Assessment
Dr. Hussein Abbass
University of New South Wales, Australia
Thursday, July 22
15:30h - 16:30h
Risk is internationally defined as the impact of uncertainty on objectives. In this talk, I will give an overview of the different role evolutionary computation (EC) can play in the area of risk assessment. I will explain the difference between risk assessment on the one hand, and optimization and learning on the other hand. I will show that many of the challenges we need to overcome to use EC for risk assessment are already hot issues in EC that have been studied for decades under different titles. Nevertheless, I will also demonstrate that these issues, when investigated using a risk assessment lens, new challenges - including fundamental ones - arise and interesting insights are gained. Examples in this talk are extracted from Air Traffic Management and Strategic Planning.
Dr. Hussein Abbass is currently a Professor and Chair of Information Technology at the School of Engineering and Information Technology, University of New South Wales, the Australian Defence Force Academy in Canberra, Australia. He is the Director of the University Defence and Security Applications Research Centre, and the Director of the Adaptive Robotics Laboratory. He is a fellow of the Australian Computer Society, an Associate Fellow of the Australian Institute of Management (AIM), a senior member of the IEEE, the Chair of the Australian Computer Society National Committee on Complex Systems, and the chair of the IEEE-CIS task force on Artificial Life and Complex Adaptive Systems. He holds an Advisory Professor at Vietnam National University, Ho-Chi Minh city, and held visiting positions at Imperial College London and University of Illinois. He is on the editorial board for two journals IJICC and IJASS. His main research interests include evolutionary games, learning (data mining) and optimization, ensemble learning, and multi-agent systems. He has 180+ refereed publications and his research is funded by the Australian Research Council (ARC), Eurocontrol, and other government organisations and industry. He is an associate editor for IEEE Transactions on Evolutionary Computation; IEEE Computational Intelligence Magazine; International Journal of Intelligent Computing and Cybernetics; and International Journal of Artificial Life Research.