Evolution of structure and learning — A GP approach
Recently evolutionary algorithms have been shown to be successful in evolving optimal neural network topologies and also novel learning rules. Genetic programming is a new paradigm that has proved to solve a number of complex problems in various domains. In this paper, I have suggested a novel approach to show how genetic programming can be an effective tool in evolving neural networks that work on the principles of interaction, competition, selforganization and adaptation, that is a self-organizing neural network. Can we evolve new learning algorithms with this approach? Can we extend this approach to evolve complex selforganizing systems? Can we employ this approach to evolve and simulate the mechanisms that are found in various sub-systems in the brain and hence for biological modelling? In this work, I have attempted to answer some of these questions.
KeywordsGenetic programming connectionist learning rules micro-macro dynamics self-organizing feature maps quantization error
Unable to display preview. Download preview PDF.
- J. Branke, Evolutionary algorithms for Neural Network Design and Training. In: Proceedings of the First workshop on Genetic Algorithms and its Applications, Vaasa, Finland, 1995.Google Scholar
- T. Kohonen, Self-organization and Associative Memory, volume 8 of Springer Series in: Information Sciences. Springer-Verlag, Berlin, Heidelberg, New York, third edition, May 1989.Google Scholar
- Frederic Gruau, Efficient Computer Morphogenesis: A Pictorial Demonstration, Report No. 94-04-027, Santa Fe Institute, April 29, 1994.Google Scholar
- John. R. Koza, Genetic Programming: On the Programming of Computers by Means of Natural Selection. The MIT Press, Massachusetts Institute of Technology, Cambridge, Massachusetts, 1992.Google Scholar
- D.J. Chalmers, The Evolution of Learning: An experiment on Genetic Connectionism. In: Proceedings of the 1990 Connectionist Models Summer School, CA: Morgan Kaufmann.Google Scholar
- A. Dasdan and K. Oflazar, Genetic Synthesis of Unsupervised Learning Algorithms. In: Proceedings of the Second Turkish Symposium on Artificial Intelligence and Artificial Neural Networks, Istambul, June 1993.Google Scholar
- J. Vaario, Modelling Adaptive Self-Organization, ATR Laboratories, Kyoto, Japan.Google Scholar
- K.G. Char, Emergence of Structures With Genetic Programming and Cellular Encoding, Tainn96, Turkey.Google Scholar