** Special Session **
** The interaction between evolution and learning **
7th International Conference
on Neural Information Processing
Taejon, Korea
November 14-18, 2000
Integrated into this year's ICONIP-2000 conference (http://braintech.kaist.ac.kr/ICONIP2000/) are several special sessions. Papers contributed to the special sessions should be submitted directly to and reviewed by the special session committee. All papers accepted will appear in the conference proceedings. The special session on "The interaction between evolution and learning" will concentrate on the following topics:
  • Information overlap between genetically fixed properties of the neural system and acquired/learned qualities
  • Models for the ontogenetic development of the brain and the role of activity during development
  • The evolution of variability and learning (biological paragon and models
  • Darwinian and Lamarckian evolution - reverse coding and stability
  • Neural models for evaluation during evolutionary optimisation
  • Online learning of neural models during evolution
  • The role of embodiment in evolution and learning during development
  • Evolutionary optimisation of adaptivity in neural networks
  • Applications of interactive evolution&learning in robotics, design and aesthetic optimisation
Thus, we want to encourage submission of work dealing with biologically inspired models of the interaction between evolution and learning, as well as, more application oriented results on the combined usuage of evolutionary and learning techniques, both for the design and formation of neural systems, and for the deployment of neural systems as estimators for evaluating the quality of solutions during evolutionary optimisation with online learning. The analysis of the interaction between evolution and learning, whether with respect to development or to optimisation, will form the common theme for this special session.
List of accepted papers
Cornelius Weber and Klaus Obermayer Emergence of modularity within one sheet of intrinsically active stochastic neurons
Reiji Suzuki and Takaya Arita Interactions between Evolution and Learning in a Population of Globally or Locally Interacting Agents
Hajime Murao and Shinzo Kitamura Evolution of learning in neural networks as a coordinated behavior of neuron-level learning rules
F.J. Vico, M.J. Guillen, F. Veredas and C. Polifeme A clustering method based on competitive learning and genetic search
Martin Kreutz, Anja Busse and Bernhard Sendhoff Evolution of adaptive nonlinear models
Akbar Ghobakhlou, Michael Watts and Nik Kasabov On-line expansion of output space in evolving fuzzy neural networks
Michael Huesken and Bernhard Sendhoff Evolutionary Optimization for Problem Classes with Lamarckian Inheritance
Bernhard Sendhoff, Ursula Körner and Edgar Körner On the integration of biological constraints into the evolution of artificial neural systems
Important dates
September 15, 2000 Camera-ready papers due
August 31, 2000 Early registration
November 14-18, 2000 ICONIP-2000 conference dates (special sessions)
For submission and further enquiries, please contact the special session chair
email Bernhard.Sendhoff@hre-ftr.f.rd.honda.co.jp
www www.el-tec.de
Bernhard Sendhoff
Future Technology Research Division
HONDA R&D Europe (Deutschland) GmbH
Carl-Legien-Strasse 30
63073 Offenbach/Main

Last update 29-07-2000, all inquiries to Bernhard Sendhoff