Bird-of-a-feather Workshops
.











 
 

Program Committees
Submitting Papers    Tutorials
Workshops
Graduate Student Workshop   Exhibitions
Hotel & Local Arrangements
Support
Administrative Information
Home


The GECCO-2000 Program Committee is pleased to announce the following Bird-of-a-feather workshops to be held during the 2000 Genetic and Evolutionary Computation Conference (GECCO-2000).

GECCO-2000 Workshops will be held on July 8, 2000. Anyone registered for GECCO-2000 may attend these workshops; no advanced notice is required. For information regarding participating or presenting at a particular workshop, please see the workshop homepage for further details. For general inquiries regarding workshops, please contact Annie S. Wu at aswu@cs.ucf.edu. The workshop schedule will be posted on this page as soon as it is available.


Evolutionary Computation and Parallel Processing

Erick Cantu-Paz and Bill Punch

Evolutionary Computation researchers have long had an interest in parallel processing, due to the ease with which many EC algorithms can be implemented in a parallel fashion. Furthermore, many real-world applications of EC require some parallel processing in order to make practical progress. This workshop invites discussion on general issues of parallel processing in the context of EC, including (but not limited to):

  • Theory applied to EC parallel processing (population sizing, speedup, etc.)
  • Controlled experimental studies
  • Insightful practical examples of EC parallel processing
  • Hardware/software considerations (Beowulf processing, distributed parallel processing, etc.)
  • Application of EC to parallel processing problems (process scheduling, automatic parallelization, etc.)
  • Future research directions


Artificial immune systems

Dipankar Dasgupta

The workshop will be devoted to exploring different immunological mechanisms and their relations to information processing and problem solving. From an information-processing perspective, the natural immune system is an adaptive learning system that employs several parallel and complementary mechanisms for defense against foreign pathogens. Based on the immunological principles, a new area of research is rapidly emerging, called the Artificial Immune Systems. These computational techniques have many potential use in pattern recognition, fault detection, computer security, and a variety of other applications. Topics of interest include (but are not limited to):

  • Computational algorithms based on immunological principles
  • Immunogenetic approaches
  • Immunity-based optimization and learning
  • Autonomous Decentralized/Self-Organizing Systems
  • Immunity-based Design and Scheduling
  • Immunological approaches to computer & network security
  • Artificial Immune systems and their applications


Evolutionary computation in the development of artificial neural networks

Julian Dorado and Andrew Hunter

A wide variety of EC techniques such as GA, GP and ES have been applied to NN in diverse areas including architecture design, control of learning algorithms, and reinforcement learning domains. Modern approaches include sophisticated forms of GA, such as multi-objective GAs, and sophisticated approaches to evolution, such as the use of developmental growth from genotypic description to phenotypic structure. This workshop will bring together researchers using EC techniques to solve a broad range of problems in NN design and application. The objective is to characterise the diverse range of EC techniques applied to NN in a single forum.


Data mining with evolutionary algorithms

Alex A. Freitas

The goal of the workshop is to discuss research integrating the areas of data mining and evolutionary algorithms. Some relevant issues are:

  1. how to use evolutionary algorithms to discover comprehensible, interesting knowledge;
  2. how to tailor evolutionary algorithms for a specific data mining task;
  3. to understand for which kinds of problems evolutionary algorithms perform better/worse than other data mining methods;
  4. how to scale up evolutionary algorithms to mine large data sets;
  5. how to incorporate domain knowledge in evolutionary algorithms.


Memetic algorithms

William Hart, Natalio Krasnogor, and Jim Smith

Memetic algorithms (MAs) are evolutionary algorithms (EAs) that apply a separate local search process to refine individuals (i.e. improve their fitness by hill-climbing). Under different contexts and situations, MAs are also known as hybrid EAs, genetic local searchers, Baldwinian EAs, Lamarkian EAs, etc.

Combining global and local search is a strategy used by many successful global optimization approaches, and MAs have in fact been recognized as a powerful algorithmic paradigm for evolutionary computing. In particular, the relative advantage of MAs over EAs is quite consistent on complex search spaces.

It is the purpose of this workshop to bring together researchers working on the general topic of Memetic Algorithms. This workshop will provide a forum for identifying and exploring the key issues that affect the theory, design and application of MAs.


Genetic algorithms in visual art and music

Colin G. Johnson and Juan Jesus Romero Cardalda

Over the last decade, many researchers have used genetic algorithms and similar adaptive methods in the creation of works of art, both visual arts and music. However the methods used in these various attempts have been empirical and there is little synthetic or comparative work between these various systems. The aim of this workshop will be to review these various methods, compare the various ideas that have been put forward, and work towards a methodology for taxonomizing, analysing and improving the performance of these methods to lay the foundations for a more unified theory in this application area.


Gene expression: The missing link in evolutionary computation

Hillol Kargupta

The evaluation of the DNA sequence through the construction of mRNA sequence and the protein is called gene expression. Gene expression can be viewed as a series of transformations of the representation of the genetic fitness function. This workshop will explore the role of this process based on our basic understanding of search, learning, and optimization. The topics of interest include, but are not limited to:

  1. Theoretical and experimental analysis of gene expression operators.
  2. Relation of gene expression and efficient, scalable genetic and evolutionary computation.
  3. Evolutionary algorithms motivated by gene expression.
  4. Insightful applications of gene expression-based computation.


Evolutionary methods for AI planning

Martin Middendorf

Planning has been a vital area of artificial intelligence (AI) for several years and many heuristics and tools for planning have been developed in recent years. But only a few of them so far use evolutionary algorithms (EAs). The goal of the workshop is to get together researchers interested in the subject, discuss applications of evolutionary methods in AI-planning and identify promising research directions. Areas of interest include, but are not limited to:

  • EAs for generating plans
  • Construction of planners with EAs
  • Decomposition of planning problems by EAs
  • Plan merging with EAs
  • Handling of multiple goals with EAs
  • EAs for planing under ressource constraints
  • Probability distribution based evolutionary methods for planning


Optimization by building and using probabilistic models

Martin Pelikan, Heinz Muehlenbein, and Alberto Ochoa Rodriguez

Recently, there has been a growing interest in evolutionary algorithms that guide the exploration of the search space by building and using probabilistic models of promising solutions (e.g. PBIL, cGA, UMDA, BMDA, MIMIC, FDA, and BOA). These algorithms have shown to resolve a number of problems the conventional GAs experience great difficulties with and solve a number of difficult problems quickly, accurately, and reliably. The workshop invites discussion on general issues of research in this area, including (but not limited to):

  • recent advances in the covered area of research
  • recent theoretical and empirical results
  • promising directions of future research


Evolution of sensors in nature, hardware, and simulation

Daniel Polani, Thomas Uthmann, and Kerstin Dautenhahn

In natural evolution one finds impressive examples for the principle of exploiting new sensory channels and making use of the implicit information they encode. Different senses have emerged in a vast multitude of variants, often utilizing organs not originally "intended" for the purpose they serve at present. Motivated by these observations, the topic of sensor evolution is becoming a very modern and promising direction of research between biology, robotics and Artificial Life. The workshop strives at insights into biological strategies to access new information channels, at developing new concepts for design of sensors for flexible and adaptive autonomous agents and an understanding of the relationship between the information available to an agent and the way it is processed.


Genetic and evolutionary computation paradigm in educational models for engineering

Oswaldo Velez-Langs

The main goals of this workshop are to encourage and to stimulate to the GEC community to be visionaries in the educational future of the engineering. The complete paradigm of the GEC is available for be used directly in the outline of new ways, from development and learning to emerging creativity. We can create an most sensitive spirit in our students that let to them to perceive the beyond possibilities and probabilities. Who is advised is armed.


The GECCO-2000 Bird-of-a-feather workshops are being organized by:

Annie S. Wu
University of Central Florida
School of Computer Science
P.O. Box 162362
407-823-5922
aswu@cs.ucf.edu


The deadline for GECCO workshop proposals has passed. The original GECCO-2000 Workshop Call-For-Proposals is available here.