Loading...
 

Program Tracks


Three days of presentations of the latest high-quality results in 13 separate and independent program tracks specializing in various aspects of genetic and evolutionary computation.

TitleOrganizers
ACO-SI - Ant Colony Optimization and Swarm Intelligence
  • Xiaodong Li
  • Martin Middendorf
CS - Complex Systems (Artificial Life/Artificial Immune Systems/Generative and Developmental Systems/Evolutionary Robotics/Evolvable Hardware)
  • Risto Miikkulainen
  • Emma Hart
DETA - Digital Entertainment Technologies and Arts
  • Ekart Aniko
  • Daniele Loiacono
ECOM - Evolutionary Combinatorial Optimization and Metaheuristics
  • Holger Hoos
  • Sébastien Verel
EML - Evolutionary Machine Learning
  • Mengjie Zhang
  • Will Browne
EMO - Evolutionary Multiobjective Optimization
  • Tea Tušar
  • Carlos M. Fonseca
ENUM - Evolutionary Numerical Optimization
  • Nikolaus Hansen
  • Marcus Gallagher
GA - Genetic Algorithms
  • Dirk Thierens
  • Alberto Moraglio
GECH - General Evolutionary Computation and Hybrids
  • Jim Smith
  • Jürgen Branke
GP - Genetic Programming
  • Sara Silva
  • Zdenek Vasicek
RWA - Real World Applications
  • Anna I Esparcia-Alcázar
  • Boris Naujoks
SBSE - Search-Based Software Engineering
  • Simon Poulding
  • Federica Sarro
THEORY - Theory
  • Carola Doerr
  • Dirk Sudholt

  

ACO-SI - Ant Colony Optimization and Swarm Intelligence

Description

Swarm Intelligence (SI) is the collective problem-solving behavior of groups of animals or artificial agents that results from the local interactions of the individuals with each other and with their environment. SI systems rely on certain key principles such as decentralization, stigmergy, and self-organization. Since these principles are observed in the organization of social insect colonies and other animal aggregates, such as bird flocks or fish schools, SI systems are typically inspired by these natural systems.
The two main application areas of SI have been optimization and robotics. In the first category, Ant Colony Optimization (ACO) and Particle Swarm Optimization (PSO) constitute two of the most popular SI optimization techniques with numerous applications in science and engineering. In the second category, SI has been successfully used to control large numbers of robots in a decentralized way, which increases the flexibility, robustness, and fault-tolerance of the resulting systems.

Scope

The ACO-SI Track welcomes submissions of original and unpublished work in all experimental and theoretical aspects of SI, including (but not limited to) the following areas:

  • Biological foundations
  • Modeling and analysis of new approaches
  • Hybrid schemes with other algorithms
  • Multi-swarm and self-adaptive approaches
  • Constraint-handling and penalty function approaches
  • Combinations with local search techniques
  • Benchmarking and new empirical results
  • Parallel/distributed implementations and applications
  • Large-scale applications
  • Applications to multi-objective, dynamic, and noisy problems
  • Applications to continuous and discrete search spaces
  • Software and high-performance implementations
  • Theoretical and experimental research in swarm robotics

Biographies

Xiaodong Li

Xiaodong Li received his B.Sc. degree from Xidian University, Xi'an, China, and Ph.D. degree in information science from University of Otago, Dunedin, New Zealand, respectively. Currently, he is a full professor at the School of Science (Computer Science and Software Engineering), RMIT University, Melbourne, Australia. His research interests include evolutionary computation, neural networks, complex systems, multiobjective optimization, and swarm intelligence. He serves as an Associate Editor of the IEEE Transactions on Evolutionary Computation, Swarm Intelligence (Springer), and International Journal of Swarm Intelligence Research. He is a founding member of IEEE CIS Task Force on Swarm Intelligence, a Vice-chair of IEEE CIS Task Force of Multi-Modal Optimization, and a former Chair of IEEE CIS Task Force on Large Scale Global Optimization. He was the General Chair of SEAL'08, a Program Co-Chair AI'09, and a Program Co-Chair for IEEE CEC’2012. He is the recipient of 2013 ACM SIGEVO Impact Award and 2017 IEEE CIS "IEEE Transactions on Evolutionary Computation Outstanding Paper Award".

Martin Middendorf

He is Professor of Parallel Computing and Complex Systems at the University of Leipzig, Germany. He received the Diploma degree in mathematics and the Dr. rer. nat. degree from the University of Hannover, Germany and the Professoral Habilitation degree from the University of Karlsruhe, Germany. He has worked at the University of Dortmund, Germany and the University of Hannover as a Visiting Professor of Computer Science. He was a Professor of Computer Science at the Catholic University of Eichstätt, Germany. His research interests include nature inspired algorithms, swarm intelligence, bioinformatics, and self-organised systems.

     

CS - Complex Systems (Artificial Life/Artificial Immune Systems/Generative and Developmental Systems/Evolutionary Robotics/Evolvable Hardware)

Description

This track invites all papers addressing the challenges of scaling evolution up to real-life complexity. This includes both the real-life complexity of biological systems, such as artificial life, artificial immune systems, and generative and developmental systems (GDS); and the real-world complexity of physical systems, such as evolutionary robotics and evolvable hardware.

Artificial life, Artificial Immune Systems, and Generative and Developmental Systems all take inspiration from studying living systems. In each field, there are generally two main complementary goals: to better understand living systems and to use this understanding to build artificial systems with properties similar to those of living systems, such as behavior, adaptability, learning, developmental or generative processes, evolvability, active perception, communication, self-organization and cognition. The track welcomes both theoretical and application-oriented studies in the above fields. The track also welcomes models of problem-solving through (social) agent interaction, emergence of collective phenomena and models of the dynamics of ecological interactions in an evolutionary context.

Evolutionary Robotics and Evolvable Hardware study the evolution of controllers, morphologies, sensors, and communication protocols that can be used to build systems that provide robust, adaptive and scalable solutions to the complexities introduced by working in real-world, physical environments. The track welcomes contributions addressing problems from control to morphology, from single robot to collective adaptive systems. Approaches to incorporating human users into the evolutionary search process are also welcome. Contributions are expected to deal explicitly with Evolutionary Computation, with experiments either in simulation or with real robots.

Biographies

Risto Miikkulainen

Risto Miikkulainen is a Professor of Computer Science at the University of Texas at Austin and a Fellow at Sentient Technologies, Inc. He received an M.S. in Engineering from the Helsinki University of Technology, Finland, in 1986, and a Ph.D. in Computer Science from UCLA in 1990. His recent research focuses on methods and applications of neuroevolution, as well as neural network models of natural language processing, and self-organization of the visual cortex; he is an author of over 370 articles in these research areas. He is an IEEE Fellow, member of the Board of Governors of the Neural Network Society, and an action editor of Cognitive Systems Research and IEEE Transactions on Computational Intelligence and AI in Games.

Emma Hart

Prof. Hart received her PhD from the University of Edinburgh. She currently leads the Centre for Emergent Computing at Edinburgh Napier University where her research focuses on optimisation and continuous learning systems, with an emphasis applying methods from Artificial Immune Systems and HyperHeuristics. She has published extensively in the field of Artificial Immune Systems, with a particular interest in optimisation and self-organising systems such as swarm robotics. Her current interests relate to the development of optimisation algorithms that continuously learn through experience, and how collectives of algorithms can collaborate to form good problem solvers. She also has interests in more theoretical work relating to modelling the immune system to learn more about its computational properties. From January 2017, she will become Editor-in-Chief of Evolutionary Computing, She is also a member of the SIGEVO Executive Board and editor of the SIGEVO newsletter.

     

DETA - Digital Entertainment Technologies and Arts

Description

The intersection of culture, science and technology is attracting increasingly more public attention, with frequent exhibitions, competitions and industrial involvement worldwide.

The Digital Entertainment Technologies and Arts (DETA) track at GECCO, in its seventh edition in 2017, focusses on the key application fields of arts, music, and games from the perspective of evolutionary computation, biologically inspired techniques, and more generally computational intelligence.

We invite submissions describing original work involving the use of computational intelligence techniques in the creative arts, including design, games, and music. Works of a methodological, experimental, or theoretical nature will be considered.

Scope

Topics of interest include, but are not limited to:

  • Aesthetic measurement and control
    • Machine learning for predicting or controlling aesthetic preference
    • Aesthetic measures for sound, photos, textures and other content
    • Non-realistic rendering, animations
    • Content-based similarity or recommendation
    • User modeling
  • Biologically-inspired creativity
    • Evolutionary arts and evolutionary algorithms for creative applications
    • Interactive evolutionary algorithms
    • Creative virtual ecosystems
    • Artificial creative agents
    • Definition or classification of creativity
  • Interactive environments and games
    • Virtual worlds
    • Reactive worlds and immersive environments
    • Procedural content generation
    • Game AI
    • Intelligent interactive narrative
    • Learning and adaptation in games
    • Search methods for games
    • Player experience measurement and optimization
  • Composition, synthesis, generative arts
    • Visual art, architecture and design
    • Creative writing
    • Cinema music composition and sound synthesis
    • Generative art
    • Synthesis of textures, images, animations
    • Generation or learning of environmental responses
    • Stylistic recognition and classification
  • Analysis of computational intelligence techniques for games, music and the arts

Biographies

Ekart Aniko

Aniko Ekart is currently Head of Computer Science at Aston University, Birmingham, United Kingdom. She holds a PhD in Informatics from Eötvös Loránd University, Budapest, Hungary. Her research interests include the theory and application of evolutionary computation and genetic programming in particular. She has experience in real-world applications of a variety of computational intelligence and data mining methods, including visual art, logistics (engineering) and vascular health (medicine). She has been working on various European Union funded research projects, including Advanced predictive analysis based decision support engine for logistics (ADVANCE), Actions for Excellence in Smart Cyber-Physical Systems applications through exploitation of Big Data in the context of Production Control and Logistics (EXCELL) and INdividual Vascular SignaTure: A new machine learning tool to aid personalised management of risk for cardiovascular disease (INVeST).

Daniele Loiacono

He is an assistant professor at the Dipartimento di Elettronica, Informazione e Bioingegneria (DEIB) of Politecnico di Milano, where he also received his Ph.D. in 2008.
His research interests include machine learning, evolutionary computation, and computational intelligence in games.
Since 2008, he has been organizing several scientific games-related competitions at major conferences including GECCO, CEC and CIG.

     

ECOM - Evolutionary Combinatorial Optimization and Metaheuristics

Description

The ECOM track aims to provide a forum for the presentation and discussion of high-quality research on metaheuristics for combinatorial optimization problems. Challenging problems from a broad range of applications, including logistics, network design, bioinformatics, engineering and business have been tackled successfully with metaheuristic approaches. In many cases, the resulting algorithms represent the state-of-the-art for solving these problems. In addition to evolutionary algorithms, the class of metaheuristics includes prominent generic problem solving methods, such as tabu search, iterated local search, variable neighborhood search, memetic algorithms, simulated annealing, GRASP and ant colony optimization.

Scope

The ECOM track encourages original submissions on all aspects of evolutionary combinatorial optimization and metaheuristics, including, but not limited to:

  • Applications of metaheuristics to combinatorial optimization problems
  • Theoretical developments in combinatorial optimization and metaheuristics
  • Representation techniques
  • Neighborhoods and efficient algorithms for searching them
  • Variation operators for stochastic search methods
  • Search space and landscape analysis
  • Comparisons between different techniques (including exact methods)
  • Constraint-handling techniques
  • Hybrid methods, adaptive hybridization techniques and memetic computing
  • Hyper-heuristics for combinatorial optimization problems
  • Characteristics of problems and problem instances

Biographies

Holger Hoos

Holger H. Hoos is a Professor of Computer Science and a Faculty Associate at the Peter Wall Institute for Advanced Studies at the University of British Columbia (Canada). His main research interests span empirical algorithmics, artificial intelligence, bioinformatics and computer music. He is known for his work on the automated design of high-performance algorithms and on stochastic local search methods. Holger is a co-author of the book "Stochastic Local Search: Foundations and Applications", and his research has been published in numerous book chapters, journals, and at major conferences in artificial intelligence, operations research, molecular biology and computer music. Holger was elected a Fellow of the Association for the Advancement of Artificial Intelligence (AAAI) in 2015 and won two prestigious IJCAI/JAIR best paper prizes in 2009 and 2010. He is a past president of the Canadian Artificial Intelligence Association / Association pour l'intelligence artificielle au Canada (CAIAC) and Associate Editor of the Journal of Artificial Intelligence Research (JAIR). Recently, his group has helped UBC to produce better exam timetables, Actenum Inc. to increase production efficiency in the oil and gas industry, and IBM to improve their CPLEX optimisation software, which is used by 50% of the world's largest companies and thousands of universities.

Sébastien Verel

Sébastien Verel is an associate professor in Computer Science at the Université du Littoral Côte d'Opale, Calais, France, since 2013, and previously at the University of Nice Sophia-Antipolis, France, from 2006 to 2013. He received a PhD in computer science from the University of Nice Sophia-Antipolis, France, in 2005. His PhD work was related to fitness landscape analysis in combinatorial optimization. He was an invited researcher in DOLPHIN Team at INRIA Lille Nord Europe, France from 2009 to 2011. His research interests are in the theory of evolutionary computation, multiobjective optimization, adaptive search, and complex systems. A large part of his research is related to fitness landscape analysis. He co-authored of a number of scientific papers in international journals, book chapters, book on complex systems, and international conferences. He is also involved in the co-organization EC summer schools, workshops, a special issue on EMO at EJOR, as well as special sessions in indifferent international conferences.

     

EML - Evolutionary Machine Learning

Description

The Evolutionary Machine Learning (EML) track at GECCO covers advances in the theory and application of evolutionary computation methods to Machine Learning (ML) problems. Evolutionary methods can tackle many different tasks within the ML context, including problems related to supervised, unsupervised, semi-supervised, and reinforcement learning, as well as emergent topics such as transfer learning and domain adaptation, deep learning, learning with a small number of examples, and learning with unbalanced data and missing data. The tasks range from classification, via clustering, regression, prediction to time series analysis.
The global search performed by evolutionary methods frequently provides a valuable complement to the local search of non-evolutionary methods and combinations of the two often show particular promise in practice.

This track aims to encourage information exchange and discussion between researchers with an interest in this growing research area. We encourage submissions related to theoretical advances, the development of new (or modification of existing) algorithms, as well as application-focused papers.

Scope

More concretely, topics of interest include but are not limited to:

  • Main EML paradigms and algorithms
    • Learning Classifier Systems (LCS) and evolutionary Rule-Based Systems
  • Genetic Programming (GP) when applied to machine learning tasks (as opposed to function optimisation)
    • Evolutionary ensembles, where evolution generates a set of learners which jointly solve problems
    • Evolutionary transfer learning and domain adaptation
    • Evolutionary deep learning and evolving deep structures
    • Evolving neural networks or neuroevolution (when applied to ML tasks)
    • Hyper-parameter tuning with evolutionary methods
    • Evolutionary learning with a small number of examples, unbalanced data or missing data values
    • Other genetic based or evolutionary machine learning paradigms and algorithms
  • Theoretical and methodological advances
    • Theoretical analysis of mechanisms and systems
    • Identification and modelling of learning and scalability bounds
    • Evolutionary computation techniques for Feature extraction, feature selection, and feature construction
    • Connections and combinations with machine learning theory (e.g. PAC theory and VC dimension)
    • Analysis of the evolved/learned models including visualisation
    • Generalisation and overfitting
    • Analysis and robustness in stochastic, noisy, or non-stationary environments
    • More Effective and efficient algorithms
    • Addressing significant problems such as representation, data sampling, scalability, search mechanisms, multi-objective learning, fitness evaluation, niching and encapsulation, initialisation and termination
  • Applications of EML
    • Data mining
    • Bioinformatics and life sciences
    • Computer vision, image processing and pattern recognition
    • Dynamic environments, time series and sequence learning
    • Robotics, engineering, hardware/software design, and control
    • Cognitive systems and cognitive modelling
    • Artificial Life
    • Economic modelling
    • Cyber security
    • Platforms such as GPU
    • Other kinds of real-world ML applications

Biographies

Mengjie Zhang

Mengjie Zhang is currently Professor of Computer Science at Victoria University of Wellington, where he heads the interdisciplinary Evolutionary Computation Research Group. He is a member of the University Academic Board, a member of the University Postgraduate Scholarships Committee, a member of the Faculty of Graduate Research Board at the University, Associate Dean (Research and Innovation) in the Faculty of Engineering, and Chair of the Research Committee of the Faculty of Engineering and School of Engineering and Computer Science.

His research is mainly focused on evolutionary computation, particularly genetic programming, particle swarm optimisation and learning classifier systems with application areas of feature selection/construction and dimensionality reduction, computer vision and image processing, job shop scheduling, multi-objective optimisation, and classification with unbalanced and missing data. He is also interested in data mining, machine learning, and web information extraction. Prof Zhang has published over 400 research papers in refereed international journals and conferences in these areas.

He has been serving as an associated editor or editorial board member for over ten international journals including IEEE Transactions on Evolutionary Computation, the Evolutionary Computation Journal (MIT Press), IEEE Transactions on Emergent Topics in Computational Intelligence, Genetic Programming and Evolvable Machines (GPEM, Springer), Applied Soft Computing, Natural Computing, and Engineering Applications of Artificial Intelligence, and as a reviewer of over 30 international journals. He is the Tutorial Chair for GECCO 2014 and AIS-BIO Track Co-Chair for GECCO 2016. Since 2012, he has been involving GECCO, CEC, SSCI, EvoStar, SEAL and PAKDD conferences as a general/program/technical/tutorial/track/special session chair. Since 2007, he has been listed as one of the top ten world genetic programming researchers by the GP bibliography (http://www.cs.bham.ac.uk/~wbl/biblio/gp-html/index.html).

Prof Zhang is currently chairing the IEEE CIS Emergent Technologies Technical Committee consisting of over 40 top CI researchers from the five continents and 17 task forces. He is the immediate Past Chair for the IEEE CIS Evolutionary Computation Technical Committee and a member of the IEEE CIS Award Committee. He is also a member of IEEE CIS Intelligent System Applications Technical Committee, a vice-chair of the IEEE CIS Task Force on Evolutionary Feature Selection and Construction, a vice-chair of the Task Force on Evolutionary Computer Vision and Image Processing, and the founding chair of the IEEE Computational Intelligence Chapter in New Zealand.

Will Browne

Will Browne received a BEng Mechanical Engineering, Honours degree from the University of Bath, UK in 1993, MSc in Energy (1994) and EngD (Engineering Doctorate scheme, 1999) University of Wales, Cardiff. After eight years lecturing in the Department of Cybernetics, University of Reading, UK, he was appointed to School of Engineering and Computer Science, Victoria University of Wellington, NZ in 2008. Associate Professor Browne's main area of research is Applied Cognitive Systems. This includes Learning Classifier Systems, Cognitive Robotics, and Modern Heuristics for industrial application. Blue skies research includes analogues of emotions, abstraction, memories, dissonance and machine consciousness. He is an Associate Editor for Neural Computing and Applications, and Applied Soft Computing. He has published over 100 academic papers, including in IEEE Transactions on Evolutionary Computation on scalable learning and two best paper awards in ACM Genetic and Evolutionary Computation Conference.

     

EMO - Evolutionary Multiobjective Optimization

Description

In many real-world applications, several objective functions have to be optimized simultaneously, leading to a multi-objective optimization problem (MOP) for which an ideal solution seldom exists. Rather, MOPs typically admit multiple compromise solutions representing different trade-offs among the objectives. Due to their applicability to a wide range of MOPs, including black-box optimization problems, evolutionary algorithms for multiobjective optimization have given rise to an important and very active research area, known as Evolutionary Multiobjective Optimization (EMO). No continuity or differentiability assumptions are required by EMO algorithms, and problem characteristics such as nonlinearity, multimodality and stochasticity can be handled as well. Furthermore, preference information provided by a decision maker can be used to deliver a finite-size approximation to the solution set (the so-called Pareto-optimal set) in a single optimization run.

Scope

The Evolutionary Multiobjective Optimization Track is intended to bring together researchers working in this and related areas to discuss all aspects of EMO development and deployment, including (but not limited to):

  • Theoretical foundations
  • Preference articulation
  • Constraint handling
  • Handling of continuous, combinatorial or mixed-integer problems
  • Stopping criteria
  • Hybridization
  • Performance evaluation
  • Test functions and benchmarking
  • Algorithm selection and configuration
  • Visualization
  • Interactive optimization
  • Uncertainty handling
  • Many-objective optimization
  • Large-scale optimization
  • Expensive function evaluations
  • Parallel models
  • Implementation aspects
  • Real-world applications

Biographies

Tea Tušar

Tea Tušar is a postdoctoral researcher at the Department of Intelligent Systems of the Jožef Stefan Institute in Ljubljana, Slovenia. She received the BSc degree in Applied Mathematics and the MSc degree in Computer and Information Science from the University of Ljubljana. She was awarded the PhD degree in Information and Communication Technologies by the Jožef Stefan International Postgraduate School for her work on visualizing solution sets in multiobjective optimization. She has recently completed a one-year postdoctoral fellowship at Inria Lille in France where she worked on benchmarking multiobjective optimizers. Her research interests include evolutionary algorithms for singleobjective and multiobjective optimization with emphasis on visualizing and benchmarking their results and applying them to real-world problems.

She was involved in the organization of a number of workshops at previous GECCOs (Student Workshop, Black-Box-Optimization-Benchmarking Workshop and Women@GECCO) and held a tutorial on Visualization in Multiobjective Optimization at GECCO 2016.

Carlos M. Fonseca

Carlos M. Fonseca is an Associate Professor at the Department of Informatics Engineering of the University of Coimbra, Portugal, and a member of the Evolutionary and Complex Systems (ECOS) group of the Centre for Informatics and Systems of the University of Coimbra (CISUC). He graduated in Electronic and Telecommunications Engineering from the University of Aveiro, Portugal, in 1991, and obtained his doctoral degree from the University of Sheffield, U.K., in 1996. His research has been devoted mainly to evolutionary computation and multiobjective optimization. His current research interests include preference articulation in evolutionary multiobjective optimization, experimental assessment of algorithms, evolutionary algorithm dynamics, and engineering-design optimization. He was a General co-Chair of the International Conference on Evolutionary Multi-Criterion Optimization (EMO) in 2003, 2009 and 2013, a Technical co-Chair of the IEEE Congress on Evolutionary Computation (CEC) in 2000 and 2005, and an EMO Track co-Chair of the Genetic and Evolutionary Computation Conference (GECCO) in 2016. He is a founding member of the Evolutionary Multi-Criterion Optimization Steering Committee, and a member of the Portuguese Operations Research Association (APDIO) and of the Portuguese Association of Automatic Control (APCA).

     

ENUM - Evolutionary Numerical Optimization

Description

The ENUM track (Evolutionary NUMerical optimization) is concerned with randomized search algorithms and continuous search spaces. The track is replacing the CO track, which combined the ESEP track with tracks covering optimization in continuous search spaces, most notably the EDA track. The scope of the ENUM track includes, but is not limited to, stochastic methods like Cross-Entropy (CE) methods, Differential Evolution (DE), continuous versions of Genetic Algorithms (GAs), Estimation-of-Distribution Algorithms (EDAs), Evolution Strategies (ES), Evolutionary Programming (EP), Markov Chain Monte Carlo methods (MCMC), and Particle Swarm Optimization (PSO).

Scope

The ENUM track invites submissions that present original work regarding theoretical analysis, algorithmic design, and experimental validation of algorithms for optimization in continuous domains, including work on large-scale and budgeted optimization, handling of constraints, multi-modality, noise, uncertain and/or changing environments, and mixed-integer problems. Work that advances experimental methodology and benchmarking, problem and search space analysis is also encouraged.

Biographies

Nikolaus Hansen

Nikolaus Hansen is a research scientist at INRIA, France. Educated in medicine and mathematics, he received a Ph.D. in civil engineering in 1998 from the Technical University Berlin under Ingo Rechenberg. Before he joined INRIA, he has been working in evolutionary computation, genomics and computational science at the Technical University Berlin, the InGene Institute of Genetic Medicine and the ETH Zurich. His main research interests are learning and adaptation in evolutionary computation and the development of algorithms applicable in practice. His best-known contribution to the field of evolutionary computation is the so-called Covariance Matrix Adaptation (CMA).

Marcus Gallagher

Dr Marcus Gallagher is an Associate Professor in the School of Information Technology and Electrical Engineering at the University of Queensland, Brisbane Australia. He was awarded his PhD from the University of Queensland in 2000. His main research interests are in the areas of Optimization, Metaheuristics, Evolutionary Computation and Machine Learning. More specifically, he is interested in the intersections between these areas, including the use of probabilistic models in black-box optimization algorithms (e.g. Estimation of Distribution Algorithms) and using machine learning and data-driven techniques to better understand the nature of optimization problems and algorithms.

     

GA - Genetic Algorithms

Description

The Genetic Algorithm (GA) track has always been a large and important 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:

  • Practical and theoretical aspects of GAs
  • Design of new GA operators including representations, fitness functions, initialization, termination, selection, recombination, and mutation
  • Design of new and improved GAs
  • Comparisons with other methods (e.g., empirical performance analysis)
  • Hybrid approaches (e.g., memetic algorithms)
  • Design of tailored GAs for new application areas
  • Handling uncertainty (e.g., dynamic and stochastic problems, robustness)
  • Metamodeling and surrogate assisted evolution
  • Interactive GAs
  • Co-evolutionary algorithms
  • Parameter tuning and control (including adaptation and meta-GAs)
  • Constraint Handling
  • Diversity control (e.g., fitness sharing and crowding, automatic speciation, spatial models such as island/diffusion)
  • Bilevel and multi-level optimization
  • Ensemble based genetic algorithms
  • Model-Based Genetic Algorithms

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

Biographies

Dirk Thierens

Dirk Thierens is affiliated with the Department of Information and Computing Sciences at Utrecht University, the Netherlands, where he is teaching courses on Evolutionary Computation and on Computational Intelligence. He has been involved in genetic algorithm research since 1990. His current research interests are mainly focused on the design and application of model learning techniques to improve evolutionary search. Dirk is (has been) a member of the Editorial Board of the journals Evolutionary Computation, Evolutionary Intelligence, IEEE Transactions on Evolutionary Computation, and a member of the program committee of the major international conferences on evolutionary computation. He was elected member of the SIGEVO ACM board and contributed to the organization of several GECCO conferences: workshop co-chair (2003, 2004), track (co-)chair (2004, 2006, 2014), and Editor-in-Chief (2007).

Alberto Moraglio

Alberto Moraglio is a Lecturer in Computer Science in the College of Engineering, Mathematics and Physical Sciences at the University of Exeter, UK. He has been active in evolutionary computation research for the last 10 years with a substantial publication record in the area. He is the founder of the Geometric Theory of Evolutionary Algorithms, which unifies Evolutionary Algorithms across representations and has been used for the principled design of new successful search algorithms and for their rigorous theoretical analysis. He was co-chair of the Theory Track, the Genetic Programming Track and the Genetic Algorithms Track in past editions of GECCO, co-chair of the European Conference on Genetic Programming, and has regular tutorials at GECCO and IEEE CEC.

     

GECH - General Evolutionary Computation and Hybrids

Description

General Evolutionary Computation and Hybrids is a new track that recognises that Evolutionary Algorithms are often used as part of a larger system, or together in synergy with other algorithms.
We welcome high quality papers on a range of topics that might not fit solely into any of the other track descriptions.

Scope

Areas of interest include the following - but the limit should be your creativity not ours!

  • Combining different ways of creating or improving solutions
    • such as co-evolution, neuro-evolution, memetic algorithms, and other hybrids.
  • Combining EAs with Machine Learning Algorithms that learn a model of the search space
    • such as surrogate-assisted optimisation of expensive fitness functions,
  • Combining EAs with learning algorithms that attempt to learn how to control or co-ordinate a range of algorithms
    • such as parameter tuning, parameter control, and self * approaches such as hyper-heuristics and self-adaptation,
  • Novel nature-inspired paradigms
  • Algorithms for Dynamic and stochastic environments
  • Statistical analysis techniques for EAs
  • Evolutionary algorithm toolboxes

Biographies

Jim Smith

Jim Smith is Professor of Interactive Artificial Intelligence at University of the West of England, from where he received his PhD. in 1998. He has been researching meta­heuristics since 1994, publishing over 100 papers and authoring a best-selling text book on Evolutionary Computation. His research interests include; the theory and application of adaptive and self­ adaptive evolutionary and memetic systems; hybrid algorithms; and the use of interactive artificial intelligence in optimisation and machine learning.
He is a member of the editorial board of the journals including Evolutionary Computation, Applied Soft Computing and Memetic Computing. He has acted as track chair for GECCO in 2011, 2016 and 2017 and was programme chair for Parallel Problem Solving from Nature (PPSN) in 2003 and 2014.

Jürgen Branke

Jürgen Branke is Professor of Operational Research and Systems at Warwick Business School, University of Warwick, UK. He has been an active researcher in the field of Evolutionary Computation for over 20 years, has published over 150 papers in peer-reviewed journals and conferences, resulting in an H-Index of 46 (Google Scholar). His main research interests include optimization under uncertainty, simulation-based optimization and multi-objective optimization. Jürgen is Area Editor for the Journal of Heuristics, and Associate Editor for the Evolutionary Computation Journal and IEEE Transactions on Evolutionary Computation.

     

GP - Genetic Programming

Description

In genetic programming, evolutionary computation is to search for an algorithm or executable structure that solves a given problem. Various representations have been used in GP, such as tree-structures, linear sequences of code, graphs and grammars. Provided that a suitable fitness function is devised, computer programs solving the given problem emerge, without the need for the human to explicitly program the computer. The GP track invites original submissions on all aspects of the evolutionary generation of computer programs or other executable structures for specified tasks.

Scope

Advances in genetic programming include but are not limited to:

  • Analysis: Information theory, Complexity, Run-time, Visualization, Fitness Landscape
  • Synthesis: Programs, Algorithms, Circuits, Systems
  • Applications: Classification, Control, Data mining, Regression, *Semi-supervised, Policy search, Prediction, Streaming data, Design, Inductive Programming
  • Environments: Static, Dynamic, Interactive, Uncertain
  • Operators: Replacement, Selection, Variation
  • Performance: Surrogate functions, Multi-objective, Coevolutionary
  • Populations: Demes, Diversity, Niches
  • Programs: Decomposition, Modularity, Semantics, Simplification
  • Programming languages: Imperative, Declarative, Object-oriented, Functional
  • Representations: Cartesian, Grammatical, Graphs, Linear, Rules, Trees
  • Systems: Autonomous, Complex, Developmental, Gene regulation, Parallel, Self-organizing, Software

Keywords

Genetic programming (GP), data mining, learning, complex systems, performance evaluation, control, grammatical evolution (GE), fitness, training set, test suite, selection operators, theoretical analysis, fitness landscapes, visualisation, regression, classification, graphs, rules, software improvement, representation, information theory, tree GP, complex, optimisation, evolvability, machine learning, feature construction and selection, applications, variation operators (crossover, mutation, etc.), hyperheuristics and automatic algorithm creation, parameter tuning, prediction, applications, symbolic expression, linear GP, knowledge engineering, environment, decision making, uncertain environments, nonlinear models, unique applications, streaming data, human competitive, dynamic environments, parallel implementations, Cartesian genetic programming (CGP), GP in high performance computing (parallel, cloud, grid, cluster, GPU).

Biographies

Sara Silva

Sara Silva obtained a BSc and MSc in Informatics at the University of Lisbon, and a PhD (2008) in Informatics Engineering at the University of Coimbra, Portugal. Her main research interests are bio-inspired machine learning methods for data mining, like neural networks, genetic algorithms, and particularly genetic programming, which she has applied in several interdisciplinary projects ranging from remote sensing and forest science to epidemiology and medical informatics.

Sara Silva has around 60 peer-reviewed scientific publications, 10 of which distinguishes witgen data, Design,lpired machASvD="dl1)T>="dl1)T>="dl1)T>=" )publan tyudUh4 clasmsearch foblan typubltiEl Board ohe organization . He wasuding 5as aroundn is and ork is in/li>

Biographies

RW="prmizaon, lotions, abstraReturn to top
     
mization
  • Expe (RW=) w

    ving theg the C in etic a viided thadicine and the nsactions on adaptive evel nature-; of d mmaticynerandscantiw

    in/li> Scop a Pitgn of RW="ble basutionasms across traints, mul,tic Programmtion. incmethods class="mediag">GP - Genetic Programmi(ion Optnd appike neuetugal, inl. FurthtudyEngineive and multiobjec compaiming

  • Expef creatithe . He hreprel-Based nr tunusture tcCa id thactiv a gen. creatithe . He hreprel-Based nrical performaure tcCabjectiv and multiobjectives, Trees Prof Zhang is cputer.al Restbjeon.spion, Evat the alg,rel nature-Feature Sie SctThe scoli>
  • Expef cr(ES), Evolutionary Programming (EP), Markov Chain Monte Carlo m - Evolutionary Multiob (Evolutioin EEE Tmerging theorithmsl is Appliesmentations, Cartesian genetic programming (CGP), GP in high performance computing (parallel, cloud, grid, cluster, GPU).

  • SBSE"prS land/diLinear, er Return to top
         
    media" id="id_GP - Genetic Programming">
    S land/diLinear, er (SBSE)oundn isers and authorih unifies Evolutiol. Furthermore, orihinear, eus Hansen isssionson and multi-oic Programming
  • Model-Based tBSE"y"> l. Furtg">GP - Genetic Programmioup of on, nary AlgtBSE"d="medplied uch as lass="mediag">GP - Genetic Programmes that Evo">Descrp. He hrepreadderenction Algoation nhinear, eus Hansen ising thionrosgh; the theoryhine learih unifiel nature-mmaryrch interestso encouragnterestmin/li>finincyhorih unifng in afl nature-iwhencmethods /h2>inear, eus Hansen isptimizationPrleion, recombary algorn operass="m,rp. He hrepredo. We ng avat the algrack de tildel-Based nrical new and,>

  • Algbjective op
  • Design o />He is a areas, inc paradigmsHordinate a rang uncertainted, .
  • thms (EDAs), Evolution SDeclarative, resuata-bnealutionary algoTabu irawnStion Terosghrammars.us Hansen islifecycc desigures fo,r specified tasks.

  • PerSyszatio Compironland/diAtifitps.exemic and stocst incluRroup eto discUergen-bres, u thp> (new succIerators, tli>Diversitits, Sysultas islnginf toLinear, er
  • itte/li>
  • Perforand n anuraTrack is Ovisualizingularity, SemE), fitnr mix4> O adaptive eularity, Semch arking,er
  • Declarativeinear, einImteHeuri,cessful datais: Iefacto (Researcn is g/" targDeclarativeinear, eSecuMultDeclarative, Objsearchinear, eisedgon
  • Per mixe LandGuman to eRules, Trees
  • HeadshotHands Cropped And Low Res out/persoLabihref="hBleengin working in evt="_blank">ee.Swimg-r lutionore the University of Lisboh unifng in ahinear, eus Hansen is(SBSE)selection otmix4> reseaf="htion and y of Evolsli>=erldng ovs theoreg Eishe editorair sgraivea-bboassgECH - Gnary Mlutionar-oft Computk forT>=" )publan Syogateumer rS land/diLinear, er (SSBSE)senary Mlutionar-oft Coessment of algorithmsin the orr rS land/diLinear, e mix4> (SBSTHis best-known contribution to the field of evolutionary computation is the so-called Covariance Matrix Adaptati1 (2007).

    THEORY -incipleReturn to top
         

    The Evo.e me algrltimodarator large m of Intelomba acr comp="media-via worhorosgh;traints, multe Nmix4ggrammes that us>adanalysEE TrtrolIntelliinot f, the InGene Institute of Genivercal co-Chair of the IEEE

  • Analysis of the IEEE olution (D reseanew successful searcw ohair ng dl osutionass="showhide_K. He has tp://www.ceLifi,cowtrClannyalia. He was ,(EDAs),nary search. Ditersections between these areas, inc,dGuman tost-sell
  • RepnSon theis of the IEEE i>such as co-evo,ch Univeand/diLinear, er Sc ieplacemeanew suc-scale ashoveral interdtion, antch3plr conphang is c Scopble based gene">Descry Algaon and ltessuthe De="Scope"> af cr(ES), Evolutionary Programming (EP), Markov Chain Monte Carl of a ures for( specified tasks.

    ):s that rn headiul>

    rithms>=" )puveata, human comot or eththat rrn n make-text6 (Googl­ctive, Unc

  • ntereSudholt
    =" )publan , uk/computer-sciworking innd Bectile" ACaliinenia,vil engineerk fogs Evolutiog Scirluch asttps.nRicpatt M. Karp>rithm Silva obtained a BSBiumilahamp> ,vil enginciencttps.nXeerYaoož, CECJanu Insg 2 around 6Lps.exetehref="h obtained a BSeffineerin ,vltic Algars. Pwstsostiony of Wgs Evolutioristics sg Sciveral interheuristics sIntellHer rn is devis)publan tye thms (cDAs), His main resems; hybned scientific pubd a memberisheal Evolutionary Computatie hasan , uk/c4> earc

    Jieen ud4> i="_blankiturcoeend (SAGEonetwork) Jürgenthmshrepnl70c impr cond forest ss=n is>=" )publan researcher in the field oionary Com8ived conphaiilva hdevoluty Comn the field ong suUaltited Jürgennces o9Algorithms TraThRaSH, WCCI/CEC,He was caltited nchmarking Wond Associate Editor for the Evolutionary Computation Journal and IEEE Transactions on Evoooo ate Edio ati>thms > io a the Evolutng avatwh(> a the Evolutfootwh_latwh(> a the Evolutng ased cn Infixyms te, rhe"EP), boatom_ms te, (> a the Evolutngl-sm-3"="media"media- theP), ms te,_43" dia"media Evolutianee_K.nee-defaoogficx-i>thms syms te,dshotHandddddddddddddddr the Evoluti.nee-cus16 1a"hotHandddddddddddddddndddddddddddddddr GP in higi.nee-kinns cn Infix" "hotHandddddddddddddddndddddddddddddddndddddddddddddddrsperin> ms te,kinns">LamininNewsivsper>hotHandddddddddddddddndddddddddddddddndddddddddddddddndddddddddddddddrrallel, cddddddddndddddddddddddddrramp;x=70"ndddddddddddddddr theP), ms -i>thms sboatom1"x=70"nddddddddddddstylelefo_only: blo b;"x=70"ndddddddddddd Evolutnn Infixyi.nee-"HeadshotHandddddddddddddddddddddddddddddddddddo achas ali>o -s=opped Alngkms te,dtion Joi>thms 40-F the-ation. -avSN)ions" kinns="Justs08volut7,h as ntresponswh(> F the KolutionavSN)ions ata> a/li>o ali>o -s=opped Alngkms te,dtion Joi>thms 39-Th algAmanl i-Keynotws-for-ck in-g 7" kinns="June 26volut7,h asjaviH ferr h(> Th al Amanl i Keynotws0ineeng suUlut7 ata> a/li>o ali>o -s=opped Alngkms te,dtion Joi>thms 38-Preptiovolu-ation. -avSN)ions" kinns="June 24volut7,h as ntresponswh(> Preptiovolu KolutionavSN)ions ata> a/li>o ali>o -s=opped Alngkms te,dtion Joi>thms 37-Smmijo-sk">J-rgeinsw andinsgii>Jthe Genw and nsgii> a/li>o ali>o -s=opped Alngkms te,dtion Joi>thms 36-Rsgii>ors-now-in E" kinns="Mummart7,hlut7,h aspponsiv.esposman(> Call origin]">ors nowoin E ata> a/li>o ali>o -s=opped Alngkms te,dtion Joi>thms 34--Humitu-is ths-for-Hneer-Cg, environ- me alg" kinns="Febru Ins14volut7,h asjaviH ferr h(> "Humitu" is ths0ineeHneer-Cg, environe me alg ata> a/li>o ali>o -s=opped Alngkms te,dtion Joi>thms 33-S and l-Issutanize="Scope"> a" kinns="Janu Ins13volut7,h asjaviH ferr h(> S and l Issuthe De="Scope"> a ata> a/li>o ali>o -s=opped Alngkms te,dtion Joi>thms 32-New-Look-alt-Feel-for-Tec-ck in-Webnede" kinns="Janu Ins05volut7,h aspponsiv.esposman(> New LookcaltiFeelomputk fong suUWebnede ata> a/li>o ali>o -s=opped Alngkms te,dtion Joi>thms 31-Uplase-/l-ck in-Pnd forest -gorith-i>Xiv-Smven problze=lowed" kinns="Janu Ins05volut7,h aspponsiv.esposman(> Uplaseneticg suUPnd forest lgorith: i>Xiv Smven probl e=lowed ata> a/li>o tochas hotHandddddddddddddddndddddddddddddddndddddddddddddddndddddddddddddddrramp;x=70"ndddddddddddddddndddddddddddddddrramp;x=70"ndddddddddddddddrramp;x a the Evolutngl-sm-3"="media"media- theP), ms te,_14" dia"media Evolutianee_K.nee-defaoogficx-menupx="bms te,dshotHandddddddddddddddr the Evoluti.nee-cus16 1a"hotHandddddddddddddddndddddddddddddddr GP in higi.nee-kinns cn Infix" "hotHandddddddddddddddndddddddddddddddndddddddddddddddrsperin> ms te,kinns">cg suUTweetsivsper>hotHandddddddddddddddndddddddddddddddndddddddddddddddndddddddddddddddrrallel, cddddddddndddddddddddddddrramp;x=70"ndddddddddddddddr theP), ms -menupx="boatom2"x=70"nddddddddddddstylelefo_only: blo b;"x=70"ndddddddddddd Evolutnn Infixyi.nee-"HeadshotHandddddddddddddddddddddddddddddddddddo

    -s=opped Atwtionranceslatwv="regImage age twtionr.com/cg sug 7" 5?display5aclalass=of Ielefaitiolass=lngk-clanrJoufff">Tweetsh as@cg sug 7ata> <

    ! Dynamic(d,s,id){var js,fjs=d.getEion eral ino otHandddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddrramp;x=70"ndddddddddddddddndddddddddddddddrramp;x=70"ndddddddddddddddrramp;x a the Evolutngl-sm-3"="media"media- theP), ms te,_16" dia"media Evolutianee_K.nee-defaoogficx-Sn]">orship_messx="bms te,dshotHandddddddddddddddr the Evoluti.nee-cus16 1a"hotHandddddddddddddddndddddddddddddddr GP in higi.nee-kinns cn Infix" "hotHandddddddddddddddndddddddddddddddndddddddddddddddrsperin> ms te,kinns">Aponsivsper>hotHandddddddddddddddndddddddddddddddndddddddddddddddndddddddddddddddrrallel, cddddddddndddddddddddddddrramp;x=70"ndddddddddddddddr theP), ms -Sn]">orship_messx="boatom3"x=70"nddddddddddddstylelefo_only: blo b;"x=70"ndddddddddddd Evolutnn Infixyi.nee-"HeadshotHandddddddddddddddddddddddddddddddddddo r theP), Sn]">orship_messx=""dstylelefo_only:blo b;"> a the Evolutngl-md-1 ngl-md-offset-1">s="pull-letiki-download_file.php?fileId=5">tor for the Evolutngl-md-10">cg suUcop a]">oruch ask fog the Eva/l0inee, uk/c4> i>such EE o and l Ince 199 r Sciretic Prograhair of the IEEE ionary Compu(the pr)ožIGySgramces: 2 Penn P ms te,kinns">Sof aivsper>hotHandddddddddddddddndddddddddddddddndddddddddddddddndddddddddddddddrrallel, cddddddddndddddddddddddddrramp;x=70"ndddddddddddddddr theP), ms -Sof aboatom4"x=70"nddddddddddddstylelefo_only: blo b;"x=70"ndddddddddddd Evolutnn Infixyi.nee-"HeadshotHandddddddddddddddddddddddddddddddddddo r theP), Sof a"dstylelefo_only:blo b;"> ap>
    <="pull-leegImagegecco-g 7.sigevo.org/iutat.html/dl81ss="inteoace98. "dstylele href: 54px; maph4>ry Com: 10px;"="niveruHer rFace98. sactiop>

    <="pull-leegImagegecco-g 7.sigevo.org/iutat.html/dl815s="intetwtionr"dstylele href: 54px; maph4>ry Com: 10px;"="e otheruHer rTwtionrsactiop>

    <="pull-leegImagegecco-g 7.sigevo.org/iutat.html/dl814s="inteemail"dstylele href: 54px; maph4>ry Com: 10px;"="gecco-g 7@sigevo.orgsactiop> ms te,ficx-menupx="dshotHandddddddddddddddr theP), ms -menupx="boatom5ion="" dadshotHanddddddddddddddddddddddddddddddddddddddddddd a the Evolutin 1--s=opped Awiki;trdiv> < /> ivtrdiv> iede othe">ng suUlut6sact -a-s=opped Awiki;trdiv> < /> ivtrdiv> iede othe">ng suUlut5sact -a-s=opped Awiki;trdiv> < /> ivtrdiv> iede othe">ng suUlut4sact -a-s=opped Awiki;trdiv> < /> ivtrdiv> iede othe">ng suUlut3sact -a-s=opped Awiki;trdiv> < /> ivtrdiv> iede othe">ng suUlut2sact - -s=opped Awiki;trdiv> < /> ivtrdiv> iede othe">ng suUlut1sactithat -s=opped Awiki;trdiv> < /> ivtrdiv> iede othe">ng suUlut0sact -a-s=opped Awiki;trdiv> < /> ivtrdiv> iede othe">ng suUlu09sact -a-s=opped Awiki;trdiv> < /> ivtrdiv> iede othe">ng suUlu08sact - -s=opped Awiki;trdiv> < /> ivtrdiv> iede othe">ng suUlu07sact - -s=opped Awiki;trdiv> < /> ivtrdiv> iede othe">ng suUlu06sact - -s=opped Awiki;trdiv> < /> ivtrdiv> iede othe">ng suUlu05sactithat -s=opped Awiki;trdiv> < /> ivtrdiv> iede othe">ng suUlu04sact -a-s=opped Awiki;trdiv> < /> ivtrdiv> iede othe">ng suUlu03sact -a-s=opped Awiki;trdiv> < /> ivtrdiv> iede othe">ng suUlu02sact - -s=opped Awiki;trdiv> < /> ivtrdiv> iede othe">ng suUlu01sact - -s=opped Awiki;trdiv> < /> e.edu/~genscie/ck in-g 00/geccog 00tionpx=".htm183> ivtrdiv> iede othe">ng suUlu00sact - -s=opped Awiki;trdiv> < /> e.edu/~genscie/ck in-1999183> ivtrdiv> iede othe">ng suU1999splay&xo otHandddddddddddddddddddddddddddddddddddddddddddddddddddddddy&x=70" ramp;x=70"ndddy&xox otHandddddddddddddddr theP), ms te,_36"dstylele"x=70"nddddddddddddddddn> ms te,fdropupficx-ankin_icxdshotHandddddddddddddddr theP), ms -ankin_icxboatom6ion="" dadshotHanddddddddddddddddddddddddddddddddddddddddddd - the Evolutnedeankinbar_popupfdropdown btn-g Scirionary Compu abuaton typelebuatonion="" dabtn btn-lngkidropdown-togge,dtlass=oogge,lefropdown(> Loineeo asperin> caremputvsper>h atbuaton> a the Evolutnedeankinbar_poppedupfdropdown-menurionary Comdms al-sm">r the Evoluti.nee-"Headsh o aform naIeleankinbcxde Evolutform"EP), ankinbcx-118Area EleegImagegecco-g 7.sigevo.org/iutat.html/tiki-ankin.php"h tics Eutinnl" " - the EvolutuseCompum-g Scircn Infix"sh Usiv> me:o -onpute Evolutform-"Keywor" typelein 1" naIeleuseC"EP), ankin-useC_1"at o ate Edi - the Evolutpassompum-g Scircn Infix"sh PassGene:o -onputeonkeyation capLock(n/lnt,c Sco)" typelepassGene" naIelepass"e Evolutform-"Keywor" P), ankin-pass_1"> a the Evolut thCapsoniostylelefo_only:none;pu asperin> sectio-E Inns ha-fw 18stylelev >thcal-align:middle;p" divsper> CapsLock Her . ate Edi ate Edi - the Evolutmpum-g Scirin 1- abuaton n="" dabtn btn-priing"ibuaton givent" typelegivent" naIeleankin">Loinee atbuaton> ate Edi - thedi - the> Pee Evolutpassputation Jotiki-remiut_passGene.php" kinns="Cl tar

    if you'vinf tgoaten your passGene">Inf tgoa my passGenesplay&es, Treeste Edi ate Edi o aonputetypelehidd E" naIelenliy_in_ssl_ms e_etical " eadieley"at aonputetypelehidd E" naIelenliy_in_ssl_ms e" eadielen"at o -/mpum>tor foror forramp;x ootHandddddddddddddddddddddddddddddddddddddddddddddddddddddddr&x=70" ramp;x=70"ndddx otHandddddddddddddddr theP), ms te,_5"dstylele"x=70"nddddddddddddddddn> ms te,ficx-rsslnstdshotHandddddddddddddddr theP), ms -rsslnstboatom8ion="" dadshotHanddddddddddddddddddddddddddddddddddddddddddd r theP), rssdsh ms te,ficx-pow

    dbadshotHandddddddddddddddr theP), ms -pow

    dbaboatom9ion="" dadshotHanddddddddddddddddddddddddddddddddddddddddddd- the EvolutpowPow

    dh asTiki;Wiki;CMS r Sciar, esplay&x=70"""""""""""""""""""""""""""""""""""""""""""""""""""""""""y&x=70" ramp;x=70"ndddy&xodddddddddddddddddddd- theP), ms te,_45"dstylele"x=70"nddddddddddddddddn> ms te,ficx-BackToTnal hotHandddddddddddddddr theP), ms -BackToTnaboatom10ion="" dadshotHanddddddddddddddddddddddddddddddddddddddddddd r theP), BackToTnaldstylelefo_only:blo b;"> a the Evolutbacktornal tation Journal8kinns="Back To Tnal splay& ate Edi ate Edi atfootwhdio a the Evolutng avatwh(> a the Evolutnavbar-cus1 h(> abuaton typelebuatonion="" danavbar-togge,dtlass=oogge,lengllapse"h lass=o/> sr-g fr">Togge, nav4ggrammtvsper>h asperin> h asperin> h asperin> h atbuaton> -s=opped Anavbar-bnia_v="regIm./">s="pull-letiki-download_file.php?fileId=534"="ng suUlut7ata> ate Ed oo a the Evolutngllapse navbar-ngllapse" P), navbar-ngllapse-sof a"shh aul=opped Anavenavbar-navenavbar-y Compu -s=ion Jou"e Evolutfropdown-togge,dtlass=oogge,lefropdown(>Loinee caremputvsper>ata> aul=opped Adropdown-menudsh ali>o a th> odddddddddddddddddddd- theP), ms te,_wikiimg sr_1"astylele"x=70"nddddddddddddddddn> ms te,ficx-ankin_icxdshotHandddddddddddddddr theP), ms -ankin_icxion="" dadshotHanddddddddddddddddddddddddddddddddddddddddddd o aform naIeleankinbcxde Evolutform"EP), ankinbcx-218Area EleegImagegecco-g 7.sigevo.org/iutat.html/tiki-ankin.php"h tics Eutinnl" " - the EvolutuseCompum-g Scircn Infix"sh Usiv> me:o -onpute Evolutform-"Keywor" typelein 1" naIeleuseC"EP), ankin-useC_2"at o ate Edi - the Evolutpassompum-g Scircn Infix"sh PassGene:o -onputeonkeyation capLock(n/lnt,c Sco)" typelepassGene" naIelepass"e Evolutform-"Keywor" P), ankin-pass_2"> a the Evolut thCapsoniostylelefo_only:none;pu asperin> sectio-E Inns ha-fw 18stylelev >thcal-align:middle;p" divsper> CapsLock Her . ate Edi ate Edi - the Evolutmpum-g Scirin 1- abuaton n="" dabtn btn-priing"ibuaton givent" typelegivent" naIeleankin">Loinee atbuaton> ate Edi - thedi - the> Pee Evolutpassputation Jotiki-remiut_passGene.php" kinns="Cl tar

    if you'vinf tgoaten your passGene">Inf tgoa my passGenesplay&es, Treeste Edi ate Edi o aonputetypelehidd E" naIelenliy_in_ssl_ms e_etical " eadieley"at aonputetypelehidd E" naIelenliy_in_ssl_ms e" eadielen"at o -/mpum>x ootHandddddddddddddddddddddddddddddddddddddddddddddddddddddddr&x=70" ramp;x=70"ndddx -te Edi a/li>o tochas a/li>o tochas a the Evolutng ased cn Infixyms te, " P), rnabar_ms te, _sof a"sh xodddddddddddddddddddd- theP), ms te,_46"dstylele"x=70"nddddddddddddddddn> ms te,ficx-menudshdddddddddddddddddddd- theP), ms -menurnabar1ion="" dadshotHanddddddddddddddddddddddddddddddddddddddddddd a the Evolutcn Infixyrna_menudsh aul=P), cssmenu0ion="" danav cssmenu_horiz menu43"> Pee Evolutov clalu0 menuOv cla menuL menuTn 1">Newsivsper>splay&es, lie Evolutfropdown ov clal12rmenuSation, menuSation,0 menuL menuTn 1">Callsivsper>splayass="se Evolutov clal13 menuOv cla menuL menuTn 1"> . He ivsper>splay&es, lie Evolutov clal14 menuOv cla menuL menuTn 1">Tgorithmsivsper>splay&es, lie Evolutov clal15 menuOv cla menuL menuTn 1">in the osivsper>splay&es, lie Evolutov clal27 menuOv cla menuL menuTn 1">Cg, envirtraivsper>splay&es, lie Evolutov clal17 menuOv cla menuL menuTn 1">Lami-breaengi Abi>splay&es, lie Evolutov clal16 menuOv cla menuL menuTn 1">Hot OfO) in 2oionivsper>splay&es, lie Evolutov clal38 menuOv cla menuL menuTn 1">Humituivsper>splay&es, lie Evolutov clal40 menuOv cla menuL menuTn 1">Stud Etsin the oivsper>splay&es, lie Evolutov clal39 menuOv cla menuLors menuTn 1">Sn]">orsivsper>splay&es, Treestes, lie Evolutfropdown ov clal02rmenuSation, menuSation,0 menuL menuTn 1">Cg asedivsper>splayass="se Evolutov clal04 menuOv cla menuL menuTn 1"> ssful ivsper>splay&es, lie Evolutov clal29 menuOv cla menuL menuTn 1">Keynotwsivsper>splay&es, lie Evolutov clal03 menuOv cla menuL menuTn 1">Tle bsivsper>splay&es, lie Evolutov clal41 menuOv cla menuL menuTn 1"> . He ivsper>splay&es, lie Evolutov clal28 menuOv cla menuL menuTn 1">Tgorithmsivsper>splay&es, lie Evolutov clal30 menuOv cla menuL menuTn 1">in the osivsper>splay&es, lie Evolutov clal18 menuOv cla menuL menuTn 1">Cg, envirtraivsper>splay&es, lie Evolutov clal42 menuOv cla menuL menuTn 1">Lami-breaengi Abi>splay&es, lie Evolutov clal43 menuOv cla menuL menuTn 1">Hot OfO) in 2oionivsper>splay&es, lie Evolutov clal05 menuOv cla menuL menuTn 1">ECnee PtAreaceivsper>splay&es, lie Evolutov clal31 menuOv cla menuL menuTn 1">Humituivsper>splay&es, lie Evolutov clal32 menuOv cla menuL menuTn 1">Stud Etsin the oivsper>splay&es, lie Evolutov clal36 menuOv cla menuLJ menuTn 1">Smmijo Sk">Jivsper>splay&es, lie Evolutov clal33 menuOv cla menuL menuTn 1">inmen@Geccoivsper>splay&es, lie Evolutov clal45 menuOv cla menuL menuTn 1">Job oritemivsper>splay&es, Treestes, lie Evolutfropdown ov clal26rmenuSation, menuSation,0 menuL menuTn 1">Rsgii>splay&es, lie Evolutfropdown ov clal07rmenuSation, menuSation,0 menuL menuTn 1">Aponsivsper>splayass="se Evolutov clal08 menuOv cla menuL menuTn 1">OvisualHe ivsper>splay&es, lie Evolutov clal35 menuOv cla menuL menuTn 1"> u splay&es, lie Evolutov clal10 menuOv cla menuL+e Univers/lputsperin> menuTn 1">Lo/a>splay&es, lie Evolutov clal44 menuOv cla menuL menuTn 1">edic tical He ivsper>splay&es, lie Evolutov clal09 menuOv cla menuL menuTn 1">edicStud Et ivsper>splay&es, lie Evolutov clal11 menuOv cla menuL menuTn 1">FAQsgent Heloivsper>splay&es, Treestes, ochasdbadamyMs alLabel" ry, -hidd E="true1" 1&y=120" s al-dthmog"di a&y=120" s al-ng aseddsh a the Evolut s al-cus1 h(> ht="120" alts al-kinns"eP), myMs alLabel"div cla ate Edi ate Edi dbadamyMs alLabel" ry, -hidd E="true1" 1&y=120" s al-dthmog"di a&y=120" s al-ng aseddsh ate Edi dbadamyMs alLabel" ry, -hidd E="true1" 1&y=120" s al-dthmog"di a&y=120" s al-ng aseddsh ate Edi as

    as
    as
    as
    a![CDATA[//>a!]]ditos
    as
    a![CDATA[//>a!]]ditos
    x atbodydi $(docuTrac).rus1y( Dynamic () { $('.t>Jtips').t>Jtip({ 'ng avatwh': 'body' }); }); tos
    a/html>