Call for Papers/ Submitting Papers Call for Workshops Proposals Call for late breaking papers ECP Free Tutorials Planned Workshops Graduate Student Workshop Committees and Program Tracks Hotel and Local Arrangements Keynote Speakers Registration SIGEVO Additional Information Competitions

Committees and  Program Tracks 

Una-May O'Reilly, CSAIL, MIT. 

Hans-Georg Beyer   

Franz Rothlauf 

Simon Lucas

David E. Goldberg   
Erik Goodman  
John R. Koza  
Riccardo Poli   

R. Paul Wiegand   
Ronald W. Morrison

Michael O'Neill    
Laurence D. Merkle      

Cem Baydar, Accenture:
Tina Yu, Chevron:



A-Life, Evolutionary Robotics and Adaptive Behavior:      more info Hod Lipson
Ant Colony Optimization and Swarm Intelligence:    more info Christian Blum
Artificial Immune Systems:   more info Dipankar Dasgupta 
Biological Applications:    more info James A. Foster   
Wolfgang Banzhaf
Coevolution:    more info Edwin De Jong
Estimation of Distribution Algorithms: more info
Martin Pelikan
Evolutionary Combinatorial Optimization:   
more info
Gunther Raidl
Evolutionary Multiobjective Optimization -Co-Chairs:    
Kalyanmoy Deb
Eckart Zitzler 
Evolutionary Strategies, Evolutionary Programming:    more info Dirk Arnold
Evolvable Hardware:    more info Andy Tyrrell
Genetic Algorithms:    more info Erick Cantu-Paz
Genetic Programming:    more info Terry Soule  
Learning Classifier Systems and Other Genetics-Based Machine Learning   more info
Xavier Llora
Meta-heuristics and Local Search: more info Jean-Paul Watson
Real World Applications:    more info: Eric Bonabeau
Search-based Software Engineering:   more info Spiros Mancoridis


Erik D. Goodman (chair)
David Andre
Wolfgang Banzhaf
Kalyanmoy Deb
Kenneth De Jong
Marco Dorigo
David E. Goldberg
John H. Holland
John R. Koza
Una-May O'Reilly
Ingo Rechenberg
Marc Schoenauer
Lee Spector
Darrell Whitley
Annie S. Wu

A-Life, Evolutionary Robotics and Adaptive Behavior:
This track examines evolutionary computation as model for understanding natural systems and for generating biologically-inspired artificial systems. From artificial models of biological systems, to the synthesis of "life" on artificial media; from self-organizing, self-replicating, and self-learning structures, to bio-inspired adaptive robots and mobile agents; This area deals with algorithmic, synthetic, empirical, and theoretical advances in artificial systems inspired by evolution, biology, and life.

  to top

Ant Colony Optimization and Swarm Intelligence:
Swarm intelligence (SI) algorithms take their inspiration from the collective behaviour of, for example, ant colonies, flocks of birds, or fish schools. Examples are algorithms for clustering and data mining inspired by ants' cemetery building behaviour, dynamic task allocation algorithms inspired by the behaviour of wasp colonies, particle swarm optimization (PSO) algorithms, and many more. A particularly successful strand of SI is ant colony optimization (ACO).
The inspiring source of ACO is the foraging behavior of real ants, which works via an indirect communication between the ants by means of pheromone trails. Their foraging behaviour allows them to find shortest paths between their nest and food sources. This functionality of real ant colonies is exploited in artificial ant colonies in order to solve discrete (as well as continuous) optimization problems, but also to solve tasks such as routing and load balancing arising in networks. This track invites submissions that present original work on ACO/SI algorithms. Submissions in the following areas of ACO/SI research are encouraged:

- applications of ACO/SI algorithms to real-world problems
- applications of ACO/SI algorithms to scientific test cases
- new theoretical results on ACO/SI
- new swarm intelligence algorithms
- new hybrids between ACO/SI algorithms and other methods for
- biological foundations of ACO/SI
- models of the behavior of social insects

  to top

Artificial Immune Systems:

The field of artificial immune systems (AIS) is an emerging area, which explores and employs different immunological mechanisms in order to solve computational problems. This special track will provide a great opportunity for presenting and disseminating latest work in the field of Artificial Immune Systems. Papers in this track would include (but are not limited to):

·        Computational models of the Immune System,

·        Extensions or improvements of existing AIS models,

·        Applications of Immunity-Based Techniques,

·        Combination of AIS with other soft computing paradigms

·        Hardware implementations of AIS

·        Immunoinformatics, etc.

  to top

Biological Applications:
The scope of this track will be any research applying genetic and evolutionary computation to biological hypotheses and data. GEC uses the process of evolution as an algorithmic heuristic, and so GEC provides an algorithmic approach to answering biological questions. All "flavors" of GEC are included in this scope: genetic algorithms, genetic programming, evolution strategies, evolutionary programming, and hybrid systems with any of these components.

Some specific appropriate biological issues that GEC may address include:

• Data mining in biological data bases
• Sequence alignment
• Phylogenetic reconstruction
• Gene expression and regulation, alternative splicing
• Functional diversification through gene duplication and exon
• Structure prediction for biological molecules (structural
and proteomics)
• Network reconstruction for development, expression, catalysis
• Dynamical system approaches to biological systems
• Simulation of cells, viruses, organisms and whole ecologies
• Sensitivity of speciation to variations in evolutionary
• Relationships between evolved systems and their environment
(phylogeography, e.g.)
• Relationships within evolved communities (cooperation,
symbiosis, etc.)

  to top

Coevolution offers the potential to address problems for which no accurate evaluation function is known. Rather than following a fixed approximation of the unknown true evaluation function for a problem, the coevolutionary evaluation of an individual depends on other evolving individuals. The optimization process can thereby adaptively construct its own evaluation function.

Coevolution can be an effective approach for problems where performance can be measured using tests, as well as for problems in which multiple components that make up a whole are to be co-adapted. In addition to these forms of optimization, the adaptive nature of the evaluation process in coevolution may in principle give rise to a self-propelled and open-ended evolutionary process.

It has been found early on that the dynamic evaluation of coevolution can lead to unreliability. In recent years however, the possible goals for coevolutionary algorithms have become better understood, and for several algorithms theoretical properties have been provided. These developments generate the exciting prospect that practical reliable algorithms for coevolution may now be within reach.

The Coevolution Track of the 2005 Genetic and Evolutionary Computation Conference provides a venue where researchers from all directions and approaches to coevolution can meet. Submissions on any aspect of coevolution are encouraged, including but not limited to the following:

* Applications
* Measuring progress
* Game-theoretic studies
* New coevolutionary algorithms
* The structure of coevolution problems
* Empirical studies of coevolutionary methods
* Behavioral dynamics of coevolutionary setups
* Theoretical guarantees for coevolutionary algorithms
* Empirical comparisons between coevolutionary and other methods

For detailed information, see

  to top

Estimation of Distribution Algorithms:

Estimation of distribution algorithms (EDAs) replace traditional variation operators of genetic and 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 genetic and 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. As a result, EDAs provide a robust and scalable solution to many important classes of optimization problems with only little problem specific knowledge.

This track invites submissions that present original work on EDAs with the focus on theory and applications of EDAs, the design of new EDAs, and the improvement of existing EDAs. More specifically, submissions in the following areas of EDA research are encouraged:

- EDA theory (modeling, prediction, limitations)
- EDA applications (interesting artificial and real-world problems)
- efficiency enhancement of EDAs
- empirical studies of EDAs
- theoretical and empirical comparison of EDAs and other optimization
- design of new EDAs
- design of hybrid methods by combining EDAs with other optimization
- adaptation of operators/parameters in EDAs

  to top

Evolutionary Combinatorial Optimization:
Evolutionary algorithms have often been shown to be effective for difficult combinatorial optimization problems appearing in various industrial, economical, and scientific domains. Prominent examples of such problems are scheduling, timetabling, network design, transportation and distribution problems, vehicle routing, traveling salesperson, other graph problems, satisfiability, packing problems, planning problems, and general mixed integer programming.

Topics of interest include, but are not limited to:
- Applications of evolutionary algorithms and related nature-inspired meta-heuristics like memetic algorithms or ant colony optimization to combinatorial optimization problems;
- hybrid methods and hybridization techniques;
- representation techniques;
- evolutionary operators;
- constraint-handling techniques;
- parallelization;
- theoretical developments;
- search space analyses;
- comparisons to other (also non-evolutionary) techniques.

  to top

Evolutionary Strategies, Evolutionary Programming:
Both evolution strategies (ES) and evolutionary programming (EP) are nature-inspired optimization paradigms that generally operate on the " natural" problem representation (i.e., without a genotype-phenotype mapping). For example, when used in connection with real-valued problems, both ES and EP use real-valued representations of search points. Moreover, both may 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 that may include, but is not limited to, theoretical and empirical evaluations of ES/EP, improvements and modifications to the algorithms, and applications of ES/EP to benchmark problems and test function suites. Particularly encouraged are submissions with focus on

- adaptation mechanisms
- interesting ES/EP applications
- ES/EP theory
- ES/EP in uncertain and/or changing environments
- comparisons of ES/EP with other optimization methods
- hybrid strategies
- meta-strategies
- constrained and/or multimodal problems

  to top

Evolvable Hardware:
Evolvable hardware techniques enable self-reconfigurability and adaptability of programmable devices and thus have the potential to significantly increase the functionality of deployed hardware systems. Evolvable Hardware is expected to have major impact on future system designs. Evolvable hardware is also expected to greatly enrich the area of commercial applications in which adaptive information processing is needed; such applications range from human-oriented hardware interfaces and internet adaptive hardware to automotive applications.

Evolvable Hardware is an emerging field that applies evolution to automate design and adaptation of physical structures such as electronic systems, antennas, MEMS and robots. The aim of this track is to bring together leading researchers from the evolvable hardware community, representatives of the automated design and programmable/ reconfigurable hardware communities, and end-users from the aerospace, military and commercial sectors. Contributions dealing with theory, techniques, and performance evaluation, are solicited, but not limited to, the following:

- Intrinsic and on-line evolution
- Hardware/software co-evolution
- Novel devices, testbeds and tools supporting evolvable hardware
- Adaptive computing and adaptive hardware
- Real-world applications of evolvable hardware.

  to top

Genetic Algorithms

This track invites submissions that present original work on genetic algorithms. We welcome submissions on theory, design of new GAs (including representations and operators), improvements of existing algorithms, comparisons with other methods, empirical evaluations, and other topics relevant to GAs.
  to top

Genetic Programming:
Genetic Programming (GP) is the automatic induction of computer programs and other variable-size structures representing executable programs or computable functions from a high-level statement of a < problem through evolutionary algorithms. This track invites submissions of original work in all areas and derivatives of GP. Areas of interest include: theory, algorithm design, and novel representations, operators and algorithms.
Authors interested in submitting manuscripts are encouraged to look at previous years' papers. A sample of papers of papers from the GP track for GECCO-2004 includes: "pi Grammatical Evolution" by Michael O'Neill et al. "Evolving Caching Strategies for the Internet" by Juergen Branke et al., "A Descriptive Encoding Language for Evolving Modular Neural Networks" by Jae-Yoon Jung and James A. Reggia, and "Evolving Quantum Circuits and Programs through Genetic Programming" by Paul Massey et al.

  to top

Learning Classifier Systems and Other Genetics-Based Machine Learning:
Since the inception of learning classifier systems (LCS) by John Holland, learning paradigms driven by genetic algorithms (GA) have shown their competence on a broad spectrum of fields and applications. In a broader spectrum, genetics-based machine learning (GBML) systems have successfully tackled the creation of cognitive models, classification and prediction systems, and anticipatory mention a few.
Recently, GBML has been experiencing an important renaissance thanks to two key factors: (1) the new GA theoretical achievements have provided a better understanding of the underlying complex mechanisms used, and (2) the successful applications of such systems to real-world problems such as data mining.

The track for LCS and other GBML encourage the authors to submit papers encompassing one or more of the areas suggested below.

(a) Theoretical advances in LCS and GBML

Theoretical analysis of mechanisms
Identification of learning, anticipation, and scalability bounds
Connections to ML theory
Analysis of the influence of noise
Complexity measures for maze environments
LCS and reinforcement learning

(b) Systems and frameworks

Michigan style (SCS, NewBoole, EpiCS, ZCS, XCS .)
Pittsburgh style (GABIL, GIL, COGIN, REGAL, GA-Miner, GALE, MOLCS, GAssist.)
Anticipatory LCS (ACS, ACS2, YACS, MACS .)
Incremental evolutionary rule learning
Genetic-based inductive learning, genetic fuzzy systems, learning based on estimation of distribution algorithms
Hybrids (XCS with messy coding, s-expressions, or neural network
conditions .)

(c) Problems

Competent operators design and implementation
Aliasing states in static environments
Dynamic environments and time series learning
Default hierarchies
Data sampling
Knowledge representations, extraction and inference
Building block identification and linkage learning for GBML systems

(d) Application areas

Rapid application development frameworks for GBML
Data mining
Bioinformatics and life sciences
Robotics, engineering, hardware/software design, and control
Stock market analysis, trading, and prediction

  to top

Meta-Heuristics and Local Search:
The distinction between evolutionary/nature-inspired algorithms and meta-heuristics such as tabu search, scatter search, and variable neighborhood search is largely counterproductive. Despite surface-level dissimilarities, the central themes underlying these two types of heuristic are nearly identical, e.g., intensification versus diversification, mechanisms for escaping local optima, intelligent design of move/mutation/crossover operators, and the structure of the fitness landscape.
We invite submissions that explore research topics at the intersection of these two historically isolated communities, such as the design of hybrid algorithms and cross-paradigm comparisons of algorithm performance. We are especially interested in papers that demonstrate either fundamental similarities or differencesbetween the different approaches, with the goal of understanding the types of problems or sub-problems for which particular techniques are most appropriate.

  to top

Real World Applications
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.
(2) Papers that present rigorous comparisons across techniques in a real world application.
(3) Papers that present novel uses of EC in the real world.
(4) Papers that present new applications of EC to real world problems.

Domains of applications include all industries (e.g., automobile, biotech, chemistry, defense, 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.).

The RWA track differs from the Evolutionary Computation Practice (ECP) workshop in that

(1) RWA only accepts papers with the same high technical and scientific quality as that of the rest of the GECCO track papers. ECP is generally< suitable for researchers and managers from industry, who have less time to write a technical paper but still would like to present significant successes of the technology solving a real-world problem.

(2) Papers accepted in the RWA track will be published in the GECCO 2005 Proceedings. Therefore, if publication is important to you, we suggest you submit your papers to RWA.

  to top

Search-based Software Engineering:
The goals of the GECCO SBSE track are to:
• develop and extend the emerging community working on Search-Based Software Engineering
• continue to inform researchers in Evolutionary Computation about problems in Software Engineering
•Increase awareness and uptake of Evolutionary computation technology within the Software Engineering community
• Provide definitions of representations, fitness/cost functions, operators and search strategies for Software Engineering problems.

Topics include (but are not limited to) the application of search- based algorithms to:
Requirements engineering
System and software design
Network design and monitoring
Software security
System and software integration
Quality assurance and testing
Project management, control, prediction, administration and organization
Maintenance, change management, optimization and transformation
Development processes

As an indication, `search- based' techniques are taken to include (but are not limited to):
* Genetic Algorithms
* Genetic Programming
* Evolution Strategies
* Evolutionary Programming
* Simulated Annealing
* Tabu Search
* Ant Colony Optimization
* Particle Swarm Optimization Papers should address a problem in the software engineering domain and  should approach the solution to the problem using a heuristic search st rategy. Papers may also address the use of methods and techniques for i mproving the applicability and efficacy of search-based techniques when applied to software engineering problems. While experim ental results are  important, papers that do not contain results, but rather present new approaches, concepts and/ or theory will also be considered. Below is a list of the best papers from GECCO 2002 and 2003. GECCO 2002: Improving Evolutionary Testing by Flag Removal, Mark Harman, Lin Hu, Robert Hierons, Andre Baresel, Harmen Sthamer GECCO 2003: Modeling the Search Landscape of Metaheuristic Software Clustering Algorithms, Brian Mitchell, Spiros Mancoridis

  to top

GECCO 2004 site     GECCO 2003 site       GECCO 2002 site         GECCO 2001 site      GECCO 2000 site
Copyright ©, 2004-2005. GECCO. All rights reserved. USA. Web programming and design: Gerardo Valencia & Gabriela Coronado