WORKSHOP ON COMPLEXITY THROUGH DEVELOPMENT AND SELF-ORGANIZING REPRESENTATIONS
(CODESOAR-2006)
http://codesoar.research.ucf.edu
to be held as part of the
2006 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE (GECCO-2006)
July 8-12, 2006 (Saturday-Wednesday)
Renaissance Seattle Hotel
Seattle, Washington, USA
Organized by ACM SIG-EVO
www.sigevo.org/GECCO-2006
PAPER SUBMISSION DEADLINE FOR WORKSHOP: 31 MARCH, 2006
AUTHOR NOTIFICATION: 12 APRIL, 2006
CAMERA-READY DEADLINE: 19 APRIL, 2006
Chairs
Ivan Garibay*, Sanjeev Kumar**, Julian Miller***, Ozlem Garibay*, Kivanc Oner*
*Evolutionary Computation Laboratory, University of Central Florida
**Sibley School of Mech. and Aerospace Eng. , Cornell University
***Department of Electronics , University of York
BACKGROUND:
This workshop follows on from the successful workshops on self-organization in
representations in evolutionary algorithms, and scalable, evolvable, emergent
developmental systems at previous GECCO conferences. This year's workshop is a
unified workshop covering both closely related areas. It promises to be an
exciting, thought provoking, and successful workshop.
Evolutionary algorithms (EAs) have been applied to an ever increasing variety
of problem domains, for which they have achieved human competitive results on
small evolutionary design problems. The application of EAs to tasks of ever
increasing difficulty is fraught with problems, namely: stagnation of search
in large search spaces, negative epistatic effects, disruption of large
building blocks, and scalability, amongst others. Recently, the problem of
scalability has attracted much attention, and deservedly so, as its resolution
is linked to other critical and demanding open research problems such as:
development, evolvability, and modularity. In order to improve the scalability
of such systems fundamental research must be undertaken to discover how to
evolve increasingly more complex designs.
For this we look at the two systems that have achieved scalability: human
engineering and natural systems. Manually constructed systems have achieved
such things as aircraft with over a million parts, software with tens of
millions of lines of code and over a hundred million transistors in
microprocessors, suggesting that we can improve the scalability of automated
design by using principles of engineering. Similarly, natural evolution and
developmental biology have produced adaptable and self-repairing systems of
even greater complexity using principles of self-organization.
Self-organization is fundamental to the developmental process at all levels:
molecular, genetic, and cellular. Nature evolves instructions in the form of
genes that are used to specify the construction of organisms during the
process of development. With reports of the number of genes in the human
genome being revised downwards, the role of self-organization in complex webs
of gene regulation is all the more salient. Given these new findings, perhaps
the self-organization of genotypic instructions and biological structure from
cells during multicellular development is a key missing ingredient from EAs?
To this end, it is anticipated that models of biological cells and
multicellular development represent a valuable source of knowledge that will
aid us in designing EAs with emergent phenomena such as: adaptability,
scale-free-ness, evolvability, and robustness. Regardless of the developmental
model or generative representation chosen -- cellular automata, genetic
regulatory networks, L-systems, etc - we must understand exactly what gives
such systems their computational power and exactly how they affect evolvability.
This workshop will focus on domain-independent methods for representing complex
solutions with self-organizable building blocks, and on developmental
principles for specifying the construction of complex systems. The workshop
welcomes multidisciplinary work, including submissions from biologists on
relevant biology that may help shed more light on developmental, self-organizing
principles for evolutionary computation.
TOPICS OF INTEREST:
- Models of complexity building using self-organization
- Emergent behavior in representations
- Methods of design and evaluation of self-organizable representational building
blocks
- Scalability of self-organizational processes to high complexities
- Self-organization theoretical approaches: complexity, chaos, synergetics,
self-organized criticality, non-equilibrium thermodynamics, etc.
- Self-organized development
- Genotype-phenotype mappings for self-organization and single & multicellular
development
- Pattern formation, morphogenesis, cellular differentiation, and growth
- Models of genetic regulatory networks, modularity, segmentation, and
compartmentalization
- Scalability & Evolvability of developmental processes
- Robustness, self-repair and regeneration in developmental processes
- Real world applications of developmental principles
SUBMISSION PROCEDURE:
Please submit proposed contributions via email to:
igaribay at cs.ucf.edu
in PS or PDF format by March 31st.
Contributions can vary from one-page position statements up to full twelve-page
camera-ready papers. Accepted contributions will be published in the GECCO-2006
proceedings.