Keynote speakers
- Kalyanmoy Deb (India)
- Zbigniew Michalewicz (Australia)
- Xin Yao (United Kingdom)
- Hussein Abbass (Australia)
Keynote 1
Reliability Based Optimization for Handling Uncertainty in Evolutionary Algorithms
Professor Kalyanmoy Deb
Indian Institute of Technology Kanpur and Helsinki School of Economics
http://www.iitk.ac.in/kangal/deb.htm
Abstract: Most practical optimization problems involve some sort of uncertainties -- either in a precise evaluation of objective and constraint functions, or through errors introduced by approximate modeling of the optimization problem itself, or in achieving exact specifications of decision variables and problem parameters in practice. In evolutionary optimization studies, the first two uncertainties are usually termed as 'noise' associated with evaluation or modeling of the problem, and the third aspect of uncertainty is dealt under the term 'robust EAs'. In the absence of constraints, the uncertainty in decision variables and parameters can cause differential sensitivities in evaluating solutions. In such scenarios, the practitioners are interested in finding 'robust' solutions which are comparatively less sensitive to variable and parameter uncertainties, rather than finding globally optimal solutions which may be too sensitive. However, in constrained problems, uncertainty in variables and parameters can cause solutions to be infeasible at some instantiations of uncertainty, although the precise specified solution may itself be feasible. One way to handle such constrained optimization problems under uncertainties is to find optimal solutions with a pre-specified reliability against failure or infeasibility. This aspect of reliability based optimization has not received adequate attention by EA researchers. although a plethora of interesting studies exist with classical optimization methodologies. In this lecture, we shall address reliability based constrained optimization, in general and some EA implementations, in particular. It turns out that EAs are much better suited for such optimization tasks compared to their classical counterparts, both in single and in multiple objective optimization problems. We shall also raise some salient research issues in this important area of research and application.
Speaker bio: Kalyanmoy Deb is currently a Professor of Mechanical Engineering at Indian Institute of Technology Kanpur, India and is the director of Kanpur Genetic Algorithms Laboratory (KanGAL). He is the recipient of the prestigious Shanti Swarup Bhatnagar Prize in Engineering Sciences for the year 2005. He has also received the `Thomson Citation Laureate Award' from Thompson Scientific for having highest number of citations in Computer Science during the past ten years in India. He is a fellow of Indian National Academy of Engineering (INAE), Indian National Academy of Sciences, and International Society of Genetic and Evolutionary Computation (ISGEC). He has received Fredrick Wilhelm Bessel Research award from Alexander von Humboldt Foundation in 2003.
His main research interests are in the area of computational optimization, modeling and design, and evolutionary algorithms. He has written two text books on optimization and more than 180 international journal and conference research papers. He has pioneered and a leader in the field of evolutionary multi-objective optimization. He is associate editor of two major international journals and an editorial board member of five major journals. More information about his research can be found from http://www.iitk.ac.in/kangal/deb.htm.
Keynote 2
The Future of Business Intelligence
Professor Zbigniew Michalewicz
University of Adelaide
http://www.cs.adelaide.edu.au/~zbyszek
Abstract: In the modern information era, managers must recognize the competitive opportunities represented by decision–support tools. Business Intelligence is a collection of tools, methods, technologies, and processes needed to transform data into actionable knowledge. Although Business Intelligence can be used to increase profitability, decrease costs, improve customer relationship management, or decrease risk, most companies use it to answer basic queries: How many customers do I have? During the past 12 months, how many products were sold in each region? Who are my 20 best customers?
Clearly, discovered knowledge is of little value if there is no value producing action that can be taken as a consequence of gaining that knowledge. The emphasis on “value producing action” is the future of Business Intelligence. Systems based on this observation are often called Adaptive Business Intelligence systems. These systems combine prediction and optimization techniques to assist decision makers in complex, rapidly changing environments. These systems address the fundamental questions: What is likely to happen in the future? And what is the best course of action? Adaptive Business Intelligence includes elements of data mining, predictive modelling, forecasting, optimization, and adaptability. The talk introduces the concepts behind Adaptive Business Intelligence, which aims at providing significant cost savings & revenue increases for businesses. A few real-world examples will be shown. Current trends in commercial software, as well as the growing importance of adaptability, will also be discussed. For more information, see www.adaptivebusinessintelligence.com.au.
Speaker bio: Zbigniew Michalewicz has published over 200 articles and 15 books on the subject of predictive data mining and logistics optimisation. These include a monograph Genetic Algorithms + Data Structures = Evolution Programs, edited volume Handbook of Evolutionary Computation, a text How to Solve It: Modern Heuristics, last year Winning Credibility: A guide for building a business from rags to riches and Adaptive Business Intelligence, and this year Puzzle-Based Learning.
Zbigniew Michalewicz is Professor in School of Computer Science at the University of Adelaide. He completed his Masters degree at Technical University of Warsaw in 1974 and he received Ph.D. degree from the Institute of Computer Science, Polish Academy of Sciences, in 1981. His last post (before arriving in Australia) was a Professor position at the University of North Carolina, USA, where he lectured from 1987 to 2004. Zbigniew Michalewicz also holds Professor positions at the Institute of Computer Science, Polish Academy of Sciences, the Polish-Japanese Institute of Information Technology, and the State Key Laboratory of Software Engineering of Wuhan University, China. He is associated with the Structural Complexity Laboratory at Seoul National University, South Korea.
Zbigniew Michalewicz has over 30 years of academic and industry experience, currently he serves as Chairman of the Board for SolveIT Software Pty Ltd, a company specialising in custom software solutions for demand forecasting and scheduling and supply chain optimisation.
Keynote 3
Cooperative Coevolution for Large Scale Evolutionary Optimisation
Professor Xin Yao
University of Birmingham
http://www.cs.bham.ac.uk/~xin/
Abstract: Evolutionary algorithms (EAs) have been applied with success to many numerical and combinatorial optimization problems in recent years. However, they often lose their effectiveness and advantages when applied to large and complex problems, e.g., those with high dimensions. Although cooperative coevolution has been proposed as a promising framework for tackling high-dimensional optimization problems, only limited studies were reported by decomposing a high-dimensional problem into single variables (dimensions). Such methods of decomposition often failed to solve nonseparable problems, for which tight interactions exist among different decision variables. In this talk, a recently proposed cooperative coevolution framework [1] will be described, which can optimize large scale nonseparable problems. A random grouping scheme and adaptive weighting are introduced in problem decomposition and coevolution. Instead of conventional evolutionary algorithms, a novel differential evolution algorithm [2] is adopted. Theoretical analysis will be presented to show why and how the new framework can be effective for optimizing large nonseparable problems. Extensive computational results will also be presented to demonstrate the effectiveness of newly proposed algorithm on a large number of benchmark functions with up to 1000 dimensions.
References:
[1] Z. Yang, K. Tang and X. Yao, "Large scale evolutionary optimization using cooperative coevolution,'' Information Sciences, 178(15):2985-2999, August 2008.
[2] Z. Yang, K. Tang, X. Yao, "Self-adaptive differential evolution with neighborhood search," in: Proceedings of the 2008 Congress on Evolutionary Computation (CEC'08), Hong Kong, China, pp.1110-1116, June 2008.
Speaker bio: Xin Yao is a Professor (Chair) of Computer Science at the University of Birmingham, UK. He obtained his BSc from the University of Science and Technology of China (USTC) in Hefei, China, in 1982, MSc from the North China Institute of Computing Technology in Beijing, China, in 1985, and PhD from USTC in Hefei, China, in 1990.
He was a postdoctoral research fellow at the Australian National University (ANU) in Canberra in 1990-91 and at CSIRO Division of Building, Construction and Engineering in Melbourne in 1991-92. He was a lecturer, senior lecturer and an associate professor at the University College, the University of New South Wales (UNSW), the Australian Defence Force Academy (ADFA) in Canberra in 1992-99. He took up a Chair of Computer Science at the University of Birmingham, UK, on the April Fool's Day in 1999.
Currently he is the Director of CERCIA (the Centre of Excellence for Research in Computational Intelligence and Applications) at the University of Birmingham, UK, a Distinguished Visiting Professor of the University of Science and Technology of China in Hefei, China, and a visiting professor of three other universities. He is an IEEE Fellow and a Distinguished Lecturer of IEEE Computational Intelligence Society. He won the 2001 IEEE Donald G. Fink Prize Paper Award and several other best paper awards. In his spare time, he does the voluntary work as the editor-in-chief of IEEE Transactions on Evolutionary Computation, an associate editor or editorial board member of several other journals, and the editor of the World Scientific book series on "Advances in Natural Computation". He has been invited to give more than 45 invited keynote and plenary speeches at conferences and workshops in 16 different countries. He is a Cheung Kong Scholar (Changjiang Chair Professor) of the Ministry of Education of the People's Republic of China.
His research has been well supported by research councils, government organisations and industry. His major research interests include evolutionary computation, neural network ensembles, and their applications. He has more than 230 refereed publications.
Keynote 4
The Future of Intelligent Systems is Non-Dominance
Professor Hussein A. Abbass
University of New South Wales
http://www.cs.adfa.edu.au/~abbass/
Abstract: Multi-objective search normally results in a set of efficient solutions called the non-dominated set. Research has focused on inventing new algorithms and heuristics to find this set - with a myriad of evolutionary-based heuristics invented on this topic alone. However, many practitioners wonder: why do we need to generate a set of efficient solutions when at the end of the day, any traditional decision making process would require a single solution? So why do we need to generate many when we only need one?
In this talk, I argue with evidence that there are many application areas in intelligent and complex systems where all non-dominated solutions are needed. This will be demonstrated through four different application areas. The first is concerned with the advantages of combining the non-dominated set into an ensemble of learning machines [4]. The second demonstrates the use of non-dominance as a measure for complexity in evolutionary robotics and embodied cognition [3]. The third uses the non-dominated set to explore the fitness landscape of conflict in wargaming [2]. The fourth demonstrates the use of the non-dominated set for risk assessment and conflict detection in air traffic management [1].
References:
[1] Alam S., Shafi K., Abbass H.A. and Barlow M., An Ensemble Approach for Conflict Detection in Free Flight by Data Mining, Transportation Research Part C. In Press.
[2] Yang A., Abbass H.A., and Sarker H (2006). Characterizing Warfare in Red Teaming, IEEE Transactions on Systems, Man, Cybernetics, Part B, 36(2), pp. 268-285.
[3] Teo J. and Abbass H.A. (2005) Multi-objectivity and Complexity in Embodied Cognition. IEEE Transactions on Evolutionary Computation, 9(4), pp. 337-360.
[4] Abbass H.A. (2003) Pareto Neuro-Ensemble. The 16th Australian Joint Conference on Artificial Intelligence (AI'03), Perth, Lecture Notes in Artificial Intelligence LNAI 2903, Springer-Verlag, pp. 554-566.
Speaker bio: Hussein Abbass is currently a Professor and Chair of Information Technology at the School of Information Technology and Electrical Engineering, 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 Artificial Life and Adaptive Robotics Laboratory. He is the Chair of the Australian Computer Society National Committee on Complex Systems, the chair of the IEEE-CIS task force on Artificial Life and Complex Adaptive Systems, and a Chief Investigator on the Australian Research Council (ARC) Centre for Complex Systems (ACCS). 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 170+ refereed publications and his research is funded by the Australian Research Council (ARC), Eurocontrol, and other government organisations and industry.