Ant Colony Optimization and Swarm Intelligence:

Description
Swarm Intelligence (SI) deals with natural and artificial systems composed of a large number of
individuals that generate collective behaviors using decentralized control and self-organization. These behaviors are a result of the local interactions of the individuals with each other and with
their environment. SI algorithms are inspired by the behavior of social insects such as ants, bees, and wasps, as well as by that of other animal societies such as flocks of birds, or fish schools. Two popular swarm intelligence techniques for optimization are ant colony optimization (ACO) and particle swarm optimization (PSO). Other examples of SI techniques include honey bee optimization, bacterial foraging, firefly optimization, and algorithms inspired by ants' cemetery building behavior, or dynamic task allocation algorithms inspired by the behavior of wasp colonies.

The ACOP/SI track invites sbmissions of original and previously unpublished work in the following areas of research:
1. applications of ACO, PSO, and other SI algorithms to real-world problems and games
2. SI techniques for difficult optimization problems:
1. including multi-objective optimization,
2. dynamic and uncertain environments,
3. dynamic multi-objective optimization,
4. finding multiple solutions,
5. tracking multiple solutions in dynamic environments,
6. dynamic constraints
1. new computational models and techniques based on SI
2. new hybrids between these algorithms and other methods
3. biological foundations
4. models of the behavior of natural and artificial SI systems
5. theoretical analysis of SI algorithms
6. benchmarking SI algorithms and new empirical results
7. Multiswarm methods, adaptation and self adaptation techniques

Keywords
Ant Colony Optimization, Particle Swarm Optimization, Bacterial Foraging, Bee Colony Optimization, Fish School Optimization, Firefly Optimization, Multiagent Societies, Swarm Robotics, Collective Intelligence, Emergent Behavior

Biosketches

Andries Engelbrecht He is a professor in Computer Science at the University of Pretoria, South Africa. He also holds the position as South African Research Chair in Artificial Intelligence, and leads the Computational Intelligence Research Group at the University of Pretoria, consisting of 50 Masters and PhD students. He obtained his Masters and PhD degrees in Computer Science from the University of Pretoria in 1994 and 1999 respectively. His research interests include swarm intelligence, evolutionary computation, artificial neural networks, artificial immune systems, and the application of these CI paradigms to data mining, games, bioinformatics, and finance. He has published over 200 papers in these fields in journals and international conference proceedings, and is the author of the two books, "Computational Intelligence: An Introduction" and "Fundamentals of Computational Swarm Intelligence". In addition to these, he is a co-editor of the upcoming books, "Applied Swarm Intelligence" and "Foundations on Computational Intelligence". He is an associate-editor of the IEEE Transactions on Evolutionary Computation, Journal of Swarm Intelligence, and the IEEE Transactions on Computational Intelligence and AI in Games. Additionally, he serves on the editorial board of 3 other international journals, and is co-guest-editor of special issues of the IEEE Transactions on Evolutionary Computation and the Journal of Swarm Intelligence. He served on the international program committee and organizing committee of a number of conferences, organized special sessions, presented tutorials, and took part in panel discussions. As member of the IEEE Computational Intelligence Society (CIS), he is a member of the Games technical committee and chair of its Swarm Intelligence for Games task force. He also serves as a member of the Computational Intelligence and Machine Learning Virtual Infrastructure Network. He is the founding chair of the South African Chapter of the CIS.

David A. Pelta He received a computer science degree from the National University of La Plata, La Plata, Argentina, in 1998 and the Ph.D. degree in computer science from the University of Granada, Granada, Spain, in 2002. Currently, he is a Professor at the Department of Computer Science and AI, University of Granada. Among his research interests are soft computing techniques, cooperative strategies for optimization, adversarial reasoning, and self-adaptive systems. He is a member of the Models of Decision and Optimization Research Group. He is involved in research projects funded by the Spanish Government and the European Community. He has published several journal papers, coedited three books and five special issues on relevant journals. Dr. Pelta serves on the editorial board of the Memetic Computing journal and acts as reviewer for many journals, including Bioinformatics, Soft Computing, Swarm Intelligence, etc. More information at: http://decsai.ugr.es/~dpelta

Artificial Life, Robotics, Evolvable Hardware

Description
This track promotes evolutionary computation and bio-inspired heuristics as instruments able to face engineering problems and scientific questions in different areas that include (but are not
limited to): artificial life, robotics, and evolvable hardware.

Artificial life studies artificial systems (software, hardware, or chemical) with properties similar to those of living systems. There are two main complementary goals: to better understand living systems and to use this understanding to build artificial systems with properties of living systems, such as adaptability, evolvability, active perception, communication, organization.

Evolutionary computation techniques can be particularly useful for a large branch of robotics. The evolution of controllers, morphologies, sensors, and communication protocols is being used to build systems to provide robust, adaptive and scalable solutions to different problems
in robotics.

Finally, the term “evolvable hardware” has been used in the past to denote both the design of electronic devices able to evolve themselves, and the generic exploitation of evolutionary techniques for creating hardware. While the first task sounds ambitious, the second is routinely applied by industries. The track will show both real and potential applications.

Keywords
artificial life, robotics, evolution, hardware, adaptive behavior, perception, communication, self-organization, controllers, morphologies, sensors.

Biosketch

Carlos Gershenson He is a full time researcher at the Universidad Nacional Autónoma de México. He holds a PhD summa cum laude from the Vrije Universiteit Brussel, Belgium (2002-2007). His thesis was on “Design and Control of Self-organizing Systems”. He holds an MSc degree in Evolutionary and Adaptive Systems, from the University of Sussex (2001-2002), and a BEng degree in Computer Engineering from the Fundación Arturo Rosenblueth, México. (1996-2001). He has a wide variety of academic interests, including self-organizing systems, artificial life, evolution, complexity, cognition, artificial societies, and philosophy. He is Editor-in-Chief of Complexity Digest (http://comdig.unam.mx), Book Review editor for the journal Artificial Life, Complexity-at-large editor for the journal Complexity.

Giovanni Squillero He received his M.S. and Ph.D. degrees in computer science engineering, respectively, in 1996 and 2000, from Politecnico di Torino, Torino, Italy, and is presently an Assistant Professor at the same institution. His research interests combine evolutionary techniques with verification, testing, and fault-tolerant design of electronic systems.

Bioinformatics, Computational, Systems, and Synthetic Biology

Description
The scope of this track is any research that applies evolutionary (and related) techniques to solving biological and biomedical problems. All "flavors" of evolutionary techniques consistent with GECCO are included in this scope, including genetic algorithms, genetic programming, estimation of distribution algorithms, evolution strategies, evolutionary programming, ant colony optimization, swarm intelligence, artificial immune systems, artificial life and hybrid methods with any of these components. Papers that integrate evolutionary methods into bioinformatics, biomedical informatics, biostatistics, patient specific information processing, computational biology, systems biology and synthetic biology, for example, are welcome. Research that demonstrates experimental validation and/or biological interpretation of computational results, specially in systems and synthetic biology, are also particularly welcome. Some specific examples of biological and biomedical issues that papers could address include:

1. Data mining (e.g.and classification or clustering) in biological or biomedical databases
2. Metabolomics, Proteomics and Genomics
3. Biological network analysis
4. Systems biology
5. Synthetic biology
6. Diagnostic or predictive testing in epidemiology and genetics
7. Functional diversification through gene duplication and exon shuffling
8. Gene expression and regulation, alternative splicing
9. Genetic association studies
10. Haplotype and linkage disequilibrium analysis
11. Image analysis and pattern recognition
12. Microarray data analysis
13. Network reconstruction for development, expression, catalysis etc.
14. Pharmacokinetic and pharmacodynamic analysis
15. Phylogenetic reconstruction and analysis
16. Relationships between evolved systems and their environment (e.g. phylogeography)
17. Relationships within evolved communities (cooperation, coevolution, symbiosis, etc.)
18. Sensitivity of speciation to variations in evolutionary processes
19. Sequence and structure alignment and analysis
20. Simulation of biological processes, cells, viruses, organisms and whole ecologies
21. Structure prediction for biological molecules (structural biology)

Biosketches

Alex Freitas He obtained his PhD in Computer Science from the University of Essex, UK, in 1997. He is currently a Reader in Computational Intelligence (position equivalent to Associate Professor) at the University of Kent, UK. He has published over 130 peer-reviewed papers, is a member of the editorial board of four international journals, and has (co-)organized several conferences and workshops in the areas of evolutionary algorithms, swarm intelligence and data mining. His current research interests are data mining and knowledge discovery, biologically-inspired computational intelligence algorithms, bioinformatics and the biology of ageing.

Marylyn D. Ritchie She is an Associate Professor in the Departments of Molecular Physiology and Biophysics and Biomedical Informatics, an Investigator in the Center for Human Genetics Research, and the Director of the Program in Computational Genomics. Dr. Ritchie is a statistical and computational geneticist with a focus on methods development for the exploration of the genetic architecture of common, complex disease. She has expertise in development and application of novel statistical and data mining methods for the detection of complex genetic models associated with clinical endpoints. Her research studies include genome-wide association studies in several common diseases, pharmacogenomics, and through the use of large DNA biobanks linked to electronic medical records. Her research program involves an interdisciplinary group of investigators focusing on both methodological development and applied studies.

Digital Entertainment Technologies and Arts -  New Frontier Track

Description
Digital Entertainment Technologies and Arts encompass the young areas of games, music and arts and all aspects of supportive computational methods. Arts, musics and games are currently becoming key application fields for genetic and evolutionary computation and related techniques. Indeed, they match up well with the desire of innovative game production and creative artists active in music and visual design. Moreover, they pair up well, as game development depends on visual and music/sound creativity. This new frontiers track explicitly focusses on these areas and propels joint works, thereby strengthening a currently forming area of high scientific, commercial, and cultural interest.

This track invites submissions that present original work on the use of computational intelligence techniques and related algorithms in games, music and arts, be it of methodological, experimental or theoretical nature. Topics of interest include, but are not limited to:

- Automated content generation
- Biologically-inspired creativity
- Evolutionary arts
- Virtual world
- Game artifical intelligence
- Educational/serious games
- Intelligent interactive narrative
- Learning and adaptation in games
- Theoretical or experimental analysis of CI techniques for games, music and arts
- Related competitions or benchmarking
- Player satisfaction
- Music in games, games on music

Keywords
procedural content generation, believability, fun, creativity, aesthetic

Biosketches

Mike Preuss He is Research Associate at the Computer Science Department, University of Dortmund, Germany (since 2000), where he also received his Diploma degree in 1998. His research interests focus on the field of evolutionary algorithms for real-valued problems, namely on multimodal and multiobjective niching and the experimental methodology for (non-deterministic) optimization algorithms. He is currently working on the adaptability and applicability of computational intelligence techniques for various engineering domains, computer games and music.

Christian Gagné He is assistant professor of computer engineering at Université Laval in Quebec City (Canada) since 2008, and member of the Computer Vision and Systems Laboratory. He received is B.Ing. (computer engineering), M.Sc. (electrical engineering) and Ph.D. (electrical engineering) from Université Laval in 2000, 2003 and 2005, respectively. In the 2005-2006 period, he was ERCIM postdoctoral fellow jointly at the INRIA Saclay-Ile-de-France in Orsay (France) and the University of Lausanne (Switzerland). He also worked as research analyst for Informatique WGZ (2006-2007) and MacDonald, Dettwiler and Associates Ltd. (2007), as consultant on research projects with Defence R&D Canada -- Valcartier. His research interests are on the engineering of distributed intelligent systems, in particular systems involving evolutionary computation (genetic programming, LCS, co-evolution), machine learning (reinforcement learning, ensemble methods, pattern recognition), and distributed computing (sensor networks, autonomic computing, high-performance computing). Prof. Gagné is co-organizing the GECCO 2009, 2010 and 2011 Evolutionary Art Competition, and acting as guest editor for a forthcoming special issue on evolutionary art in the International Journal of Arts and Technology (IJART).

Evolutionary Combinatorial Optimization and Metaheuristics

Description
The aim of this track is to provide a forum for high quality research on metaheuristics for combinatorial optimization problems. Plenty of hard problems in a huge variety of areas, including logistics, network design, bioinformatics, engineering, business, etc., have been tackled successfully with metaheuristic approaches. For many problems the resulting algorithms are considered to be state-of-the-art. Apart from evolutionary algorithms, the class of metaheuristics includes prominent members such as tabu search, iterated local search, variable neighborhood search, memetic algorithms, simulated annealing, GRASP, ant colony optimization and others.

Scope: Submission concerning applications or the theory of all kinds of metaheuristics for combinatorial optimization problems are encouraged. Topics include (but are not limited to):

1. Applications of metaheuristics to combinatorial optimization problems
2. Theoretical developments in combinatorial optimization and metaheuristics
3. Representation techniques
4. Neighborhoods and efficient algorithms for searching them
5. Variation operators for stochastic search methods
6. Search space analysis
7. Comparisons between different (also exact) techniques
8. Constraint-handling techniques
9. Hybrid methods, Adaptive hybridization techniques and Memetic Computing Methodologies
10. Insight into problem characteristics of problem classes

Keywords
local search, variable neighborhood search, iterated local search, tabu search, simulated annealing, very large scale neighborhood search, search space analysis, hybrid metaheuristic, matheuristic, memetic algorithm, ant colony optimization, particle swarm optimization, scatter search, path relinking, GRASP, vehicle routing, cutting and packing, scheduling, timetabling, bioinformatics, transport optimization, routing, network design, representations

Biosketches

Yew Soon Ong He is currently an Associate Professor with the School of Computer Engineering, Nanyang Technological University, Singapore. He is also Director of the Center for Computational Intelligence. His current research interest lies in Nature-Inspired Computing & Design that spans across Evolutionary & Memetic computation, Robust & Complex Design, Stochastic Optimization, Informatics, and cloud computing. He is 1) co-founder editor-in-chief of Memetic Computing Journal 2) co-founder chief editor of Book Series on Studies in Adaptation, Learning, and Optimization, 3) associate editor of IEEE Computational Intelligence Magazine, 4) associate editor of IEEE Transactions on Systems, Man and Cybernetics - Part B, 5) member of editorial board in (i) Soft Computing Journal, (ii) International Journal of Computational Intelligence, 6) guest editor of i) IEEE Transactions on Evolutionary Computation, ii) IEEE Transactions on Systems, Man and Cybernetics - Part B, iii) Journal of genetic Programming and Evolvable Machine and iv) Soft Computing Journal. Besides serving as editors of special issues dedicating to research on Memetic Computing, and Evolutionary Computation in Dynamic and Uncertain Environments in high-quality journals, he has also co-edited volumes on Advances in Natural Computation, and Evolutionary Computation published by Springer Verlag. He is also founder and chair of the Task Force on Memetic Computing in the IEEE Computational Intelligence Society Emergent Technology Technical Committee. He has coauthored over 100 refereed publications comprising of 42 refereed journals, 66 refereed conference papers and 5 book chapters, excluding 5 edited books, 3 edited special issues and 2 patents filed. More information can be found at http://www.ntu.edu.sg/home/asysong

Günther Raidl Prof. Raidl heads the Algorithms and Data Structures group of the Institute of Computer Graphics and Algorithms at the Vienna University of Technology. In September 2005 he received a professorship position for combinatorial optimization at this University. Before, he was Research Assistant, Lecturer and Assistant Professor at the Vienna University of Technology. Prof. Günther Raidl received his PhD in 1994 and completed his habilitation in Practical Computer Science in 2003 at the Vienna University of Technology. His research interests include algorithms and data structures in general, combinatorial and continuous optimization, mathematical programming techniques, metaheuristics, hybrid optimization approaches, evolutionary computation, network design, cutting and packing, transport optimization, warehouse logistics, scheduling, and bioinformatics. Günther Raidl is associate editor for the International Journal of Metaheuristics and the Evolutionary Computation Journal. Furthermore he is co-founder and steering committee member of the European Conference on Evolutionary Computation in Combinatorial Optimization (EvoCOP) and has been editor-in-chief of the 2009 Genetic and Evolutionary Computation Conference (GECCO). He has (co-)edited 12 books and authored over 100 reviewed articles in journals, books, and conference proceedings. More information can be found at http://www.ads.tuwien.ac.at/raidl/

Estimation of Distribution Algorithms

Description
Estimation of distribution algorithms (EDAs) are based on the explicit use of probability distributions. They replace traditional variation operators of evolutionary algorithms, such as mutation and crossover, by building a probabilistic model of promising solutions and sampling the built model to generate new candidate solutions. Using probabilistic models for exploration in evolutionary algorithms enables the use of advanced methods of machine learning and statistics for automated identification and exploitation of problem regularities for broad classes of problems. In addition they provide natural ways to introduce problem information into the search by means of the probabilistic model and also to get information about the problem that is being optimized. EDAs provide a robust and scalable solution to many important classes of optimization problems with only little problem specific knowledge.

The aim of the track is to attract the latest high quality research on EDAs in particular, and the use of probability distribution in evolutionary algorithms in general. We encourage the submission of original and previously unpublished work in, e.g., the following areas:

1. Advances in the theoretical foundations of EDAs
2. Novel applications for EDAs
3. Case studies or showcases that highlight the use of EDA in practical decision making
4. Interfaces between EDA, Ant Colony Optimization, Evolution Strategies, Cross-Entropy Method or other
5. Position papers
6. Reviews of specific EDA-related aspects
7. Comparisons of EDA to other metaheuristics, EAs, classical methods from Operations Research or hybrids thereof
8. EDA for dynamic, multiobjective or noisy problems and interactive EDA
9. Hybrid EDAs
10. New EDAs

Keywords
Evolutionary Algorihms based on Probabilistic Models, Cross-entropy method, Theoretical aspects of Estimation of Distribution Algorithms, Applications of Estimation of Distribution Algorithms, Estimation of Distribution Algorithms in Real Code Optimization, Estimation of Distribution Algorithms in Combinatorial Optimization, Estimation of Distribution Algorithms in Multi-objective Optimization, Hybrid Estimation of Distribution Algorithms

Biosketch

José A. Lozano He received an M.Sc. degree in mathematics and an M.Sc. degree in computer science from the University of the Basque Country, Spain, in 1991 and 1992 respectively, and the PhD degree in computer science from the University of the Basque Country, Spain, in 1998. Since 2008 he is full professor of the University of the Basque Country, Spain where he leads the Intelligent System Group. He is the coauthor of more than 50 ISI journal publications and co-editor of the first book published about Estimation of Distribution Algorithms. His major research interests include machine learning, pattern analysis, evolutionary computation, data mining, metaheuristic algorithms, and real-world applications. Prof. Lozano is associate editor of IEEE trans. on Evolutionary Computation and member of the editorial board of Evolutionary Computation journal, Soft Computing and other three journals.

Marcus Gallagher He received his BCompSc and GradDipSc from the University of New England, Australia in 1994 and 1995 respectively, and his PhD degree in 2000 from the University of Queensland, Australia.  He is a Senior Lecturer in the Complex and Intelligent Systems Research group in the School of Information Technology and Electrical Engineering at the University of Queensland.  His main research interests are metaheuristic optimization and machine learning algorithms, in particular techniques based on statistical modelling, in particular Estimation of Distribution Algorithms. He is also interested in biologically inspired algorithms, methodology for empirical evaluation of algorithms and the visualization of high-dimensional data.

Evolutionary Multiobjective Optimization

Description
The so called multiobjective optimization problems (MOPs) are those having several (two or more), normally conflicting, objectives that have to be satisfied at the same time. The multiple objectives might originate from one or several decision makers. Evolutionary Multiobjective Optimization (EMO) refers to the use of metaheuristics (mainly but not limited to evolutionary algorithms) to solve MOPs, aiming to find good trade-off (or compromise) solutions.

The EMO track at GECCO aims to bring together both experts and newcomers working on this area to discuss different issues including (among others) the following:

1. Real-world applications in engineering, business, computer science, biological sciences, scientific computation, etc.
2. New multi-objective optimization algorithms based on metaheuristics such as: genetic algorithms, evolution strategies, scatter search, genetic programming, evolutionary programming, artificial immune systems, particle swarm optimization, ant colony optimization, etc.
3. Performance measures for EMO.
4. Test functions and comparative studies of algorithms for EMO.
5. Techniques to maintain diversity in an EMO context.
6. Theoretical aspects of EMO.
7. Dimensionality analysis (e.g., techniques to deal with a high number of objectives and/or decision variables).
8. Parallelization of EMO techniques
9. Hybrid approaches (e.g., combinations with mathematical programming techniques).
10. Local search in an EMO context (e.g., memetic algorithms for multiobjective optimization).
11. Multiobjective combinatorial optimization.
12. Incorporation of preferences into EMO algorithms.
13. Handling uncertainty and noise in an EMO context.
14. Dynamic multiobjective optimization using EMO algorithms.
15. Special representations and operators for EMO algorithms.
16. Software architectures for development of EMO algorithms.
17. Learning and intelligent mechanisms for EMO.

Keywords
multi-objective optimization, applications of evolutionary multi-objective optimization, dynamic multi-objective optimization, expensive evaluation functions, interactive multi-objective methods, machine learning in multi-objective optimization, multiple criteria techniques, niching, elitism and diversity techniques, parallel multi-objective algorithms

Biosketches

Carlos Coello-Coello Dr. Coello received a PhD in Computer Science from Tulane University (in the USA) in 1996. He is currently Professor of Computer Science at CINVESTAV-IPN, in Mexico City, México. He has published over 250 papers in international peer-reviewed journals, book chapters, and conferences. He has also co-authored the book Evolutionary Algorithms for Solving Multi-Objective Problems (Second Edition, Springer, 2007) and has co-edited 3 books on evolutionary multi-objective optimization. He actually serves as associate editor of the journals IEEE Transactions on Evolutionary Computation, Evolutionary Computation, Computational Optimization and Applications, Soft Computing, Pattern Analysis and Applications, Memetic Computing and the Journal of Heuristics. He is also a member of the editorial board of the journals Engineering Optimization and the International Journal of Computational Intelligence Research. He received the 2007 National Research Award (granted by the Mexican Academy of Science) in the area of exact sciences. His main research interest is the development of algorithms based on bio-inspired metaheuristics for solving multi-objective optimization problems.

Dario Landa-Silva He is a lecturer in the School of Computer Science at the University of Nottingham in the UK and a member of the Automated Scheduling, Optimisation and Planning research group (ASAP). His research interests are at the interface between computer science, operations research and artificial intelligence with particular interest on the application of search and optimization techniques (e.g. meta-heuristics, hyper-heuristics, evolutionary algorithms, multi-objective and multi-criteria methods) and mathematical programming to tackle combinatorial problems (e.g. office space allocation, space planning, scheduling, timetabling, vehicle routing and similar problems) in order to underpin the development of intelligent decision support systems across a range of applications.

Evolution Strategies and Evolutionary Programming

Description
Evolution strategies (ES) and evolutionary programming (EP) are nature-inspired optimization paradigms that generally operate on the "natural" problem representation (i.e., without a non-trivial genotype-phenotype mapping). For example, when used in connection with
real-valued problems, ES and EP use real-valued representations of search points. Moreover, both often rely on sophisticated mechanisms for the adaptation of their strategy parameters. ES and EP owe much of their success to their universal applicability, ease of use, and robustness.

This track invites submissions that present original work on ES/EP and related algorithms that may include, but is not limited to, theoretical and empirical evaluations, further development and improvement of the algorithms, and applications to benchmark problems and test function
suites. Particularly encouraged are submissions with focus on:

1. Adaptation mechanisms
2. Interesting ES/EP applications
3. ES/EP theory
4. Comparisons of ES/EP with other optimization methods
5. Related algorithms, such as differential evolution
6. Hybrid strategies, such as surrogate methods
7. ES/EP in uncertain and/or changing environments
8. Constrained and/or multimodal problems

Keywords
evolution strategy, evolutionary programming, differential evolution, adaptation, self-adaptation, continuous domain, CMA-ES, natural gradient, surrogate methods, uncertainties, noise, dynamical environments

Biosketches

Nikolaus Hansen He is a researcher at The French National Institute for Research in Computer Science and Control (INRIA). He received a Ph.D. in civil engineering from the Technical University Berlin in 1998 and his Habilitation in computer science from the University Paris-Sud in 2010. Before he joined INRIA, he worked in applied artificial intelligence and genomics, and he has done research in evolutionary computation and computational science at the TU Berlin and the ETH Zurich. His main research interests are learning and adaptation in evolutionary computation and the development of algorithms applicable in practice. His most important scientific contribution has been the CMA-ES algorithm.

Silja Meyer-Nieberg She works at the Universitaet der Bundeswehr Muenchen, in Neubiberg, Germany. She received the PhD degree from the department of Computer Science, Technical University of Dortmund, Germany in 2007. Her main research interests are evolution strategies, focusing in particular on self-adaptation and noise.

Genetic Algorithms

Description

The Genetic Algorithm (GA) track has always been the largest scientific track at GECCO. We invite submissions to the GA track that present original work on all aspects of genetic algorithms, including, but not limited to:

1. Practical and theoretical aspects of GAs
2. Design of new GAs (including representation and operators)
3. Improvements over existing algorithms
4. Comparisons with other methods / empirical performance analysis
5. Hybrid approaches
6. New application areas
7. Handling uncertainty (dynamic and stochastic problems, robustness)
8. Metamodelling
9. Interactive GAs
10. Co-evolutionary algorithms
11. Tuning and adapting parameters

As a large and diverse track, the GA track will be an excellent opportunity to present and discuss your research/application with experts and participants of GECCO.

Keywords
genetic algorithms, evolutionary algorithms, recombination, mutation, selection , representations, operators, parameters, adaptation, uncertainty

Biosketches

Jim Smith He is a Reader In Artificial Intelligence at the University of the West of England, where he has been researching and publishing in Evolutionary Computation since 1994. He has authored numerous papers in the area, co-authored a textbook with Gusz (see below) and is on the editorial board of the journal Evolutionary Computation. His EC research interests include self-adaption of operators, Memetic Algorithms, and Interactive Evolutionary Algorithms.

Gusz Eiben He is a Professor of Computational Intelligence at the Free University of Amsterdam. He is one of the European early birds of evolutionary computing with his first EC paper dating back to 1990. Since then he has published great many refereed papers and, together with Jim Smith, the book "Introduction to Evolutionary Computing". His recent research interest include parameter tuning and adaptation and on-the-fly evolution in robotics.

Genetics-Based Machine Learning

Description
The Genetics-Based Machine Learning (GBML) track encompasses advancements and new developments in any system that addresses machine learning problems with evolutionary computation methods. Combinations of machine learning with evolutionary computation techniques are particularly welcome.

Machine Learning (ML) presents an array of paradigms -- unsupervised, semi-supervised, supervised, and reinforcement learning -- which frame a wide range of clustering, classification, regression, prediction and control tasks. The combination of the global search capabilities of Evolutionary Computation with the reinforcement abilities of ML underlies these problem solving tools.

The field of Learning Classifier Systems (LCS), introduced by John Holland in the 1970s, is one of the most active and best-developed forms of GBML and we welcome all work on LCSs. Artificial Immune Systems (AIS) are another family of techniques included in this track, which takes inspiration of different immunological mechanisms in vertebrates in order to solve computational problems. Moreover, neuroevolution technologies, which combine neural network techniques with evolutionary computation, are welcome. However, also any other technique or approach listed below will be considered gladly.

In list form, the GBML track encourages submissions including but not limited to the following areas:

1.Theoretical advances

• Theoretical analysis of mechanisms and systems
• Identification and modeling of learning and scalability bounds
• Connections and combinations with machine learning theory
• Analysis and robustness in stochastic (or noisy) environments
• Complexity analysis in MDP and POMDP problems

2.System advancements and new developments

• Evolutionary rule learning, including but not limited to:
• Michigan style (SCS, NewBoole, EpiCS, ZCS, XCS, UCS...)
• Pittsburgh style (GABIL, GIL, COGIN, REGAL, GA-Miner, GALE, MOLCS, GAssist...)
• Anticipatory LCS (ACS, ACS2, XACS, YACS, MACS...)
• Iterative Rule Learning Approach (SIA, HIDER, NAX, BioHEL, ...)
• Genetic-based inductive learning
• Genetic fuzzy systems
• Learning using evolutionary estimation of distribution algorithms
• Evolution of Neural Networks Evolution of ensemble systems
• Other hybrids combining evolutionary techniques with other machine learning techniques
• Artificial Immune Systems

3.System Enhancements

• Competent operator design and implementation
• Encapsulation and niching techniques
• Hierarchical architectures
• Default hierarchies
• Knowledge representations, extraction and inference
• Data sampling
• (Sub-)Structure (building block) identification and linkage learning
• Integration of other machine learning techniques

4.Applications

• Data mining
• Large scale datasets
• Bioinformatics and life sciences
• Rapid application development frameworks for GBML
• Robotics, engineering, hardware/software design, and control
• Cognitive systems and cognitive modeling
• Dynamic environments Time series and sequence learning
• Artificial Life
• Adaptive behavior
• Network security
• Other kinds of real-world applications

5.Related Activities

• Visualisation of performance
• Platforms for GBML, e.g. GPGPUs
• Competitive performance, e.g. GBML performance in Competitions and Awards
• Education and dissemination of GBML, e.g. software for teaching andexploring aspects of GBML.

Keywords
Genetics-based machine learning, evolutionary rule learning, learning Classifier Systems, Michigan style LCS, Pittsburgh style LCS, Anticipatory LCS, Artificial Immune Systems, Iterative Rule Learning, Genetic-based inductive learning, Genetic fuzzy systems, Learning using evolutionary estimation of distribution algorithms, Evolution of ensemble systems, Neuroevolution technologies, Evolutionary concepts within Machine Learning, Applications

Biosketch

Will Browne Browne’s thesis for an Engineering Doctorate regarded the industrial development of a Learning Classifier System for the Data Mining of quality control within a Steel Mill. A post-doctorate appointment from 1998 to 2001 was in the Control and Instrumentation Research Group, University of Leicester, UK. From October 2001 to August 2009 he lectured in the Cybernetic Intelligence Research Group, University of Reading. He was appointed to Senior Lecturer, Victoria University of Wellington, NZ, in September 2009. His main area of research is Applied Cognitive Systems - using inspiration from natural intelligence to enable computers/machines/robots to exhibit useful behaviours. This includes Learning Classifier Systems, modern heuristics for industrial application and Cognitive Robotics. Conferences / Workshops Organisation has included COGRIC 2006: Cognitive Robotics and Control, EPSRC/NSF sponsored workshop that brought together internationally leading figures in order to discuss latest advancements and direct future research. He has served on the organising committee of International Workshop on Learning Classifier Systems for 2009 and 2010.

Ester Bernardó I am associate professor of the Computer Engineering Department at Enginyeria i Arquitectura La Salle, Ramon Llull University. I hold a B.Sc. degree in telecommunications engineering, an M.Sc. degree in electronic engineering, and a Ph.D. degree in computer science, from Enginyeria i Arquitectura La Salle, Ramon Llull University, Barcelona. My research interests in machine learning focus on genetic algorithms and machine learning. I investigate the capabilities of evolutionary computation algorithms, especially the so-called learning classifier systems, for knowledge discovery and data mining problems. Since my visit at Bell Labs with Dr. Tin K. Ho during 2002- 2003, I have been working on the study of data complexity, i.e., the identification of the sources of complexity of real-world problems and how these complexities affect the performance of classifiers. I have participated in several projects of data mining, and have co-edited two books on genetic-based machine learning. I serve as associate editor of Pattern Recognition Letters.

Genetic Programming

Description
In the field of Genetic Programming, evolutionary algorithms are used to automatically search for an algorithm or structure solving a given problem. Representations include tree-structures, linear sequences of code, graphs or grammars. The use of Genetic Programming basically reduces the programming of computers to the definition of a suitable fitness function. The Genetic Programming (GP) track invites original submissions on all aspects of the evolutionary generation of computer programs or other variable sized structures for specified tasks. Topics include but are not limited to:

1. Theoretical developments
2. Empirical studies of GP performance and behavior
3. Novel algorithms, representations and/or operators
4. Hybrid architectures including GP components
5. Unconventional evolvable computation
6. Evolution of tree or graph structures
7. Evolution of Lindenmayer Systems
8. Grammar-based GP
9. Linear GP
10. Self-Reproducing Programs
11. Evolution of various classes of automata or machines (e.g. cellular automata, finite state machines, pushdown automata, Turing machines)
12. Object-oriented Genetic Programming
13. Evolution of functional languages

Keywords
classification, planning, evolutionary theory, parallelization, mage generation, animation, functional gp, financial application, GPU, dynamic systems, gp fitness landscape, symbolic regression, cgp and its applications, developmental gp and financial applications, modular gp and analysis, bloat, SAT, local search, grammatical evolution, coevolution, hierarchical gp, evolvability, applications (robot, financial, gene chip etc), constraints, grammar, data mining, visualization, art

Biosketch

Lee Spector He is a Professor of Computer Science in the School of Cognitive Science at Hampshire College and an Adjunct Professor in the Department of Computer Science at the University of Massachusetts, Amherst. He received a B.A. in Philosophy from Oberlin College in 1984, and a Ph.D. from the Department of Computer Science at the University of Maryland in 1992. Dr. Spector teaches and conducts research in artificial intelligence, artificial life, and a variety of areas at the intersections of computer science with cognitive science, physics, evolutionary biology, and the arts. He is the Editor-in-Chief of the Springer journal Genetic Programming and Evolvable Machines, a member of the editorial board of the MIT Press journal Evolutionary Computation, a member of the Executive Committee of the ACM Special Interest Group on Evolutionary Computation (SIGEVO), and the author of numerous publications including the book Automatic Quantum Computer Programming: A Genetic Programming Approach. He has received the highest honor bestowed by the National Science Foundation for excellence in both teaching and research, the NSF Director's Award for Distinguished Teaching Scholars, and he has won several other awards and honors including two gold medals in the Human Competitive Results contest of the Genetic and Evolutionary Computation Conference and election as a fellow of the International Society for Genetic and Evolutionary Computation.

Tina Yu She is an Associate Professor in the Department of Computer Science at Memorial University of Newfoundland. Tina conducts research in machine learning, computational intelligence and applies them to a variety of areas such as energy, medicine and economics. She serves at the editorial board of a Springer journal Genetic Programming and Evolvable Machines and a MIT Press journal Evolutionary Computation.

Generative and Developmental Systems

Description
Generative and Developmental Systems (GDS) is the study of indirect representations (also known as generative or developmental encodings), i.e. indirect mappings between the genotype and phenotype. Indirect representations are often inspired by biological development, where complex phenotypes are grown from compact genomes. The aim of such systems is to exploit powerful representations that efficiently encode complex structures and increase the scalability and evolvability of evolutionary algorithms.

Traditionally, GDS has focused on mappings that involve a developmental stage, implemented in a variety of ways including re-write systems and cell chemistry simulations. However, GDS concerns a wide range of indirect encodings, including high-level abstractions of biological development and environmental interactions.

GDS research both sheds light on biological development and furthers engineering goals by harnessing generative representations for evolutionary design. Overall, GDS concerns a wide range of indirect representations concerned with the genotype-phenotype map and encourages comparison, discussion, and analysis of the advantages and relationships among various representations. The GDS track is also open to papers regarding applications of generative encodings to interesting problems.

We invite all papers related to GDS, including those in the following subject areas: artificial development, artificial embryogeny, compositional pattern producing networks (CPPNs), computational embryology, developmental encodings, evolutionary design, generative representations, genetic regulatory networks (GRNs), indirect encodings, genotype to phenotype mappings, procedural representations, Lindenmayer Systems (L-Systems), etc.

For more information, visit the GDS Community webpage at http://gds.wikispot.org

Keywords
generative and developmental systems, generative representations, generative encodings, developmental representations, developmental encodings, indirect representations and encodings, compositional pattern producing networks (CPPNs), computational embryology, evolutionary design, genetic regulatory networks (GRNs), genotype to phenotype map, genotype to phenotype mapping, procedural representations, Lindenmayer Systems (L-Systems), development, growth, developmental biology, representations

Biosketches

Jeff Clune He is a Postdoctoral Fellow in Hod Lipson's lab at Cornell University, funded by a Postdoctoral Research Fellowship in Biology from the National Science Foundation. He studies generative encodings, which enhance evolutionary algorithms by augmenting them with concepts from developmental biology. Such concepts enable the assembly of complex forms from compact genomes. He combines these generative encodings with neuroevolution, a technology that harnesses the power of evolution to construct artificial neural networks (ANNs). Evolving ANNs with generative encodings creates large-scale, structurally organized ANNs that produce sophisticated, coordinated behaviors. Jeff demonstrates the capabilities of such ANNs in robotic control problems. He also develops evolutionary algorithms to investigate open questions in evolutionary biology, and has published work on the evolution of altruism, phenotypic plasticity, and evolvability. This work contributes to biology, because it improves our knowledge of evolving systems, and enhances computer science, because it helps design better evolutionary algorithms. Jeff is the co-chair of the Generative and Developmental Systems track at GECCO, the Genetic and Evolutionary Computation Conference (2010-2011). He won the best paper award in that track in 2009. He has a Ph.D. in computer science from Michigan State University, a master's degree in philosophy from Michigan State University, and a bachelor's degree in philosophy from the University of Michigan. Jeff is also a co-author of Avida-ED, a software tool for teaching evolution. Articles about his research have appeared in many news publications, including The New Scientist, The Daily Telegraph, Slashdot, and U.S. News & World Report.

Greg Hornby He is UCSC's Deputy Director of Information Sciences for their division at NASA Ames Research Center. He recieved is Ph.D. in Computer Science from Brandeis University in 2002 for Generative Representations for Evolutionary Design Automation. He evolved the dynamic gait used on the consumer version of Sony's Aibo and also the X-band antennas used on NASA's ST-5 mission. He also developed the Age Layered Population Structure (ALPS) for improving the robustness of stochastic search algorithms, such as EAs.

Parallel Evolutionary Systems

Description
The future of computing is parallel, as it seems that the current trend in CPU development is: slower cores on the same chip. This observation is quite pessimistic for sequential algorithms, but luckily enough, evolutionary algorithms are inherently parallel!

This GECCO track aims at developing the cross-fertilization of knowledge between evolutionary algorithms (meta-heuristics in general) and parallelism. Working in two domains of research is both difficult and fruitful. Knowledge on parallelism and networking helps in creating parallel algorithms for clusters or grids of computers. However, it is also necessary to develop proper benchmarks, software tools, and metrics to measure the behavior of algorithms in a meaningful way. A conceptual separation between physical parallelism and decentralized algorithms is needed to better analyze the resulting algorithms. This track expects high quality papers on contributions to the theory and the application of techniques born from the crossover of the traditional parallel field and meta-heuristics. Submissions providing significant contributions to problem solving (efficiency and also accuracy) while being methodologically well-founded are also welcome.

This track includes (but is not limited to) topics concerning design, implementation, and application of parallel evolutionary algorithms and meta-heuristics (GA, ES, EP, GP, ACO, PSO, SA, EDAs, TS, etc). As an indication, contributions are welcome in the following areas:

• Parallel evolutionary algorithms and meta-heuristics
• Master/slave models
• Massively parallel algorithms
• SIMD/MIMD and FPGA parallelization
• Distributed and shared memory parallel algorithms
• Parallel algorithms on multi-core machines and clusters of machines
• Parallel hybrid/memetic algorithms
• Grid computing
• Peer to peer (P2P) algorithms
• Ad-hoc and mobile networks for parallel algorithms
• Theory on decentralized and parallel algorithms
• Parallel software frameworks/libraries
• Parallel test benchmarks
• Algorithms and tools for helping in designing new parallel algorithms
• Statistical assessment of performance for parallel algorithms
• Real-world applications in data mining, bioinformatics, engineering, and telecommunications, etc.
  

Keywords
Parallel evolutionary algorithms, Parallel meta-heuristics, Massively parallel algorithms, SIMD, MIMD and FPGA parallelization, Grid computing, multi-core machines, graphics hardware

Biosketch

Man Leung Wong Dr. Wong is an associate professor at the Department of Computing and Decision Sciences at Lingnan University, Tuen Mun, Hong Kong. His research interests are evolutionary computation, data mining, parallel algorithms on Graphics Processing< Units, machine learning, knowledge acquisition, fuzzy logic, and approximate reasoning. His articles on these topics have been published in Evolutionary Computation, IEEE Transactions on Evolutionary Computation, IEEE Transactions on Pattern Analysis and Machine Intelligence, IEEE Transactions on Systems, Man, and Cybernetic, IEEE Intelligent Systems, IEEE Engineering in Medicine and Biology, Management Science, Decision Support Systems, Expert Systems with Applications, Journal of the American Society for Information Science and Technology, Fuzzy Sets and Systems, International Journal of Approximate Reasoning, etc. He received his B.Sc., M.Phil., and Ph.D. in computer science from the Chinese University of Hong Kong in 1988, 1990, and 1995, respectively.

Pierre Collet He is Professor at the Computer Science Laboratory (LSIIT) of the Strasbourg University, where he leads a team on Data-Mining, Theoretical Bioinformatics and Stochastic Optimization. The SONIC (Stochastic Optimization and Nature Inspired Computing) group that he leads within the FDBT team is developing a platform called EASEA (https://lsiit.u-strasbg.fr/easea) to parallelize evolutionary computation on massively parallel systems (the EASEA platform routinely runs on a cluster of 20 machines for a total of 5000 cores). Pierre Collet regularly organizes the EA international conferences, has been Program Chair of EuroGP and track chair for the Symposium on Applied Computing and other conferences, and is (along with Man Leung Wong) the guest editor of a special issue of the GPEM journal on Evolutionary Algorithms for Data-Mining.

Real World Applications

Description
The Real World Applications (RWA) track invites submissions that present rigorous applications of Evolutionary Computation (EC) to real world problems. Of particular interest are:

1. Papers that describe advances in the field of EC for implementation purposes, including scalability for solution quality, scalability for algorithm complexity, and implementations in industrial packages like Matlab, Mathematica, and R.
2. Papers that describe EC systems using distributing computing (cloud, MapReduce / Hadoop, grid, GPGPU, etc) for real world applications.
3. Papers that present rigorous comparisons across techniques in a real world application.
4. Papers that present novel uses of EC in the real world.
5. Papers that present new applications of EC to real world problems.

Domains of applications include all industries (e.g., automobile, biotech, chemistry, defense, finance, oil and gas, telecommunications, etc.) and functional areas include all functions of relevance to real world problems (logistics, scheduling, timetabling, design, pattern recognition, data mining, process control, predictive modeling, etc.).

Keywords
Real-world applications, distributed computing, scalability, industrial applications, scalable implementations.

Biosketch

Steven Gustafson He is a computer scientist at the General Electric Global Research Center in Niskayuna, New York. As a member of the Computational Intelligence Lab, he develops and applies advanced AI and machine learning algorithms for complex problem solving. He received his PhD in computer science from the University of Nottingham, UK, where he was a research fellow in the Automated Scheduling, Optimisation and Planning Research Group. He received his BS and MS in computer science from Kansas State University, where he was a research assistant in the Knowledge Discovery in Databases Laboratory. Dr. Gustafson is a member of several program committees, a member of the editorial board of the Journal of Artificial Evolution and Applications, and a Technical Editor-in-Chief of the new journal Memetic Computing. In 2006, he received the IEEE Intelligent System's "AI's 10 to Watch" award.

Search-Based Software Engineering

Description
Search-Based Software Engineering (SBSE) is the application of search algorithms to the solution of software engineering tasks. The field has grown very rapidly over the last decade or so, both in terms of the size of the research community as well as the range of SBSE applications. Indeed, 2011 represents a significant milestone for the field: it will be the 10th anniversary of the SBSE track at GECCO. We encourage members of community to mark this anniversary by submitting to, and attending, the SBSE track at GECCO 2011.

We invite papers that address any problem in the software engineering domain through the use of heuristic search techniques. Neither the search technique nor the software engineering problem are limited to the examples given below: we particularly encourage papers demonstrating novel search strategies or the application of SBSE techniques to new problems in software engineering. Papers may also address the use of methods and techniques for improving the applicability and efficacy of search-based techniques when applied to software engineering tasks. While experimental results are important, papers that do not contain results---but instead present new approaches, concepts, or theory---are also very welcome.

As an indication of the wide scope of the field, search techniques include (but are not limited to):

1. genetic algorithms
2. genetic programming
3. evolution strategies
4. evolutionary programming
5. simulated annealing
6. tabu search
7. ant colony optimization
8. particle swarm optimization

The software engineering tasks to which they are applied are drawn from throughout the engineering lifecycle and include (but are not limited to):

1. project management, control, prediction, administration, and organisation
2. requirements engineering and selection
3. developing highly-dynamic service-oriented systems
4. configuring cloud-based architectures
5. enabling self-healing, self-optimizing systems
6. creating recommendation systems to support the development process
7. software security
8. system and software integration
9. quality assurance and testing
10. network design and monitoring
11. maintenance, change management, program repair, refactoring and transformation

Keywords
Search-Based Software Engineering, Software Engineering, Software Testing, Requirements Analysis, Project Management, Software Maintenance, Software Architecture

Biosketches

Simon Poulding He is a lecturer in the Enterprise Systems group in the Department of Computer Science at the University of York, UK. The group investigates the unique challenges of developing and deploying the types of large-scale, complex information systems that are critical to the success of modern organisations. He is also a member of SEBASE, a large collaborative SBSE project involving researchers at three UK universities and from industry. His research interests are the application of SBSE techniques to enterprise-scale software engineering challenges, such as the identification of effective testing strategies. He also has a strong interest in experimental design and statistical analysis for computer science in general, and SBSE in particular, especially efficient techniques that enable principled and reliable investigation.

Moshe Sipper He is a Professor of Computer Science at Ben-Gurion University, Israel. His current research focuses on evolutionary computation, mainly as applied to software development and games. At some point or other he also did research in the following areas: bio-inspired computing, cellular automata, cellular computing, artificial self-replication, evolvable hardware, artificial life, artificial neural networks, fuzzy logic, and robotics. Dr. Sipper has published over 130 scientific papers. He is an Associate Editor of the IEEE Transactions on Evolutionary Computation, the IEEE Transactions on Computational Intelligence and AI in Games, and Genetic Programming and Evolvable Machines, and an Editorial Board Member of Memetic Computing. Dr. Sipper won the 1999 EPFL Latsis Prize, the 2008 BGU Toronto Prize for Academic Excellence in Research, and four HUMIE Awards (Human-Competitive Results Produced by Genetic and Evolutionary Computation).

Self-* Search -    New Frontier Track

Description
Search and optimization problems are everywhere, and search algorithms are getting increasingly powerful. However, they are also getting increasingly complex, and only autonomous self-managed systems that provide high-level abstractions can turn search algorithms into widely used methodologies. Such systems should be able to configure themselves on the fly, automatically adapting to the changing problem conditions, based on general goals provided by their users.

The aim of the Self* Search track at GECCO 2011 is to bring together all researchers interested in software systems able to automatically tune, configure, or even generate and design optimization algorithms and search heuristics.

The Self* Search track is a brand new track in 2011, selected among the competing entries to the "New Frontiers Track" for its novelty and potential. It is an exciting opportunity to explore emerging new research directions, and to confront ideas originating from the different fields of computer science concerned with adaptive search and optimization, from artificial intelligence to operational research and mathematical programming.

We invite all papers related to Self* Search, in particular (but not limited to) those in the following subject areas: hyper-heuristics, adaptive and self-adaptive parameter control, adaptive operator selection, automated construction of search heuristics, systems to build systems, computer-aided algorithm design, multi-level search, experimental analysis of algorithms, automatic algorithm configuration, adaptive multimeme algorithms, software self-assembly, reactive search, intelligent optimization, algorithm selection and portfolios, and all applications of self* techniques to multi-objective, dynamic, and complex real-world problems.

Self* Search related papers were scattered across several GECCO tracks in previous editions. We have this year a unique opportunity to both gather and unify these threads into a single track, and open up the scope for new and more ambitious research directions in automated heuristic design, and autonomic computing in general. Our program committee will be selected among the top Self* Search researchers in the world. Our hope is that your numerous submissions will demonstrate the importance of this line of research, and that this track will continue to flourish with your support and enthusiasm.

Biosketches

Gabriela Ochoa She is a senior research fellow in the Automated Scheduling, Optimisation and Planning (ASAP) Research Group, School of computer Science, University of Nottingham, UK. She holds a BEng and a Master degree in Computer Engineering from the Simon Bolivar University, Venezuela; and a PhD in Artificial intelligence from the University of Sussex, UK. Her research interests lie in the foundations and application of evolutionary algorithms and heuristic search methods, with emphasis in automated heuristic design, self-* search heuristics, fitness landscape analysis, and applications in combinatorial optimization, medicine and biology. Her articles on these topics have been published in Evolutionary Computation, IEEE Transactions on Evolutionary Computation, Genetic Programming and Evolvable Machines, Journal of Theoretical Biology, Physical Review E, Artificial Intelligence in Medicine, Journal of the Operations Research Society, GECCO, PPSN, etc. She has organized several workshops, special sessions and tutorials in hyper-heuristics and self-* search (GECCO, PPSN, LION, CEC), and edited two journal special issues in these topics (Journal of Heuristics, and Evolutionary Computation). She conceived and is currently coordinating the first Cross-domain Heuristic Search Challenge (http://www.asap.cs.nott.ac.uk/chesc2011/), an international research competition that aims to measure the performance of single search strategies across multiple problem domains rather than specifically selected ones.

Marc Schoenauer He is "Directeur de Recherche" with INRIA. He graduated at Ecole Normale Superieure in Paris, and obtained a PhD in Numerical Analysis at Paris 6 University in 1980. From 1980 to 2001, he has been with CNRS, working at the Applied Maths Laboratory at Ecole Polytechnique. He then joined INRIA, and later founded the TAO team in September 2003 together with Michele Sebag. Marc Schoenauer has been working in the field of Evolutionary Computation since the early 90s, is author of more than 120 papers in journals and major conferences of that field. He is or has been advisor of 26 PhD students. He has also been part-time Associate Professor at Ecole Polytechnique from 1990 to 2004. Marc Schoenauer is member of the Executive of SIGEVO, the ACM Special Interest Group for Evolutionary Computation. He has served in the IEEE Technical Committee on Evolutionary Computation from 1995 to 1999, and is member of the PPSN Steering Committee. He was the founding president (1995-2002) of Evolution Artificielle, the French Society for Evolutionary Computation. Marc Schoenauer has been Editor in Chief of Evolutionary Computation Journal (2002-2009), is or has been Associate Editor of IEEE Transactions on Evolutionary Computation (1996-2004), of TCS-C (Theory of Natural Computing) (2001-2006), of Genetic Programming and Evolvable Machines (1999-), and of the Journal of Applied Soft Computing (2000-). He serves on the Program Committees of all major conferences in the field of Evolutionary Computation.

Theory

Description
The GECCO 2010 theory track welcomes all papers that address theoretical issues in the whole of evolutionary computation and allied sciences. So, in addition to Genetic Algorithms, Evolutionary Strategies, Genetic Programming and other traditional EC areas, we also very much welcome theory papers in Artificial Life, Ant Colony Optimization, Swarm Intelligence, Bioinformatics, Computational Biology, Estimation of Distribution Algorithms, Generative and Developmental Systems, Genetics-Based Machine Learning, Search Based Software Engineering, and more.

The theory track welcomes submissions performing theoretical analyses or concerning theoretical aspects in the areas described above. Results can be proven with mathematical rigor or obtained via a thorough experimental investigation.

Keywords
theory, evolutionary computation, randomized search heuristics, computational complexity, convergence, information theory.

Biosketches

Anne Auger She received her diploma in mathematics from the University of Paris VI, France, in 2001. She also obtained the french highest diploma for teaching mathematics, "Agregation de mathematiques". She received the doctoral degree from the university Paris VI in 2004. Afterwards, she worked for two years (2004-2006) as a postdoctoral researcher at ETH (in Zurich) in the Computational Laboratory (CoLab). Since October 2006, she holds a permanent research position at INRIA (French National Research Institute in Computer Science and Applied Mathematics). Her research interests are stochastic continuous optimization, including theoretical analyses of randomized search heuristics. She published more than fifteen articles at top conferences and journals in this area. She co-organized the biannual Dagstuhl seminar "Theory of Evolutionary Computation" in 2008 and 2010.

Carsten Witt He studied Computer Science at the Technical University of Dortmund, Germany, where he received his diploma and Ph.D. in 2000 and 2004, respectively. In spring 2009, he moved to the Technical University of Denmark, where he now works as an associate professor in algorithms. Carsten's main research interests are the theoretical aspects of randomized search heuristics, in particular evolutionary algorithms, ant colony optimization and particle swarm optimization. He co-organized the biannual Dagstuhl seminar "Theory of Evolutionary Algorithms" in 2008 and 2010 and has given tutorials on the computational complexity of bio-inspired search heuristics in combinatorial optimization at GECCO 2008, PPSN 2008 (together with Frank Neumann), Thrash 2009 (together with Thomas Jansen) and at GECCO 2010. Together with Frank Neumann, he has authored the textbook "Bioinspired Computation in Combinatorial Optimization - Algorithms and Their Computational Complexity".