Evaluation of Chess Position by Modular Neural Network Generated by Genetic Algorithm
Conference paper
- 2 Citations
- 630 Downloads
Abstract
In this article we present our chess engine Tempo. One of the major difficulties for this type of program lies in the function for evaluating game positions. This function is composed of a large number of parameters which have to be determined and then adjusted. We propose an alternative which consists in replacing this function by an artificial neuron network (ANN). Without topological knowledge of this complex network, we use the evolutionist methods for its inception, thus enabling us to obtain, among other things, a modular network. Finally, we present our results:
-
reproduction of the XOR function which validates the method used
-
generation of an evaluation function
Keywords
Genetic Algorithm Evaluation Function Modular Network Modular Neural Network Chess Position
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
Preview
Unable to display preview. Download preview PDF.
References
- 1.Berliner, H.J.: Construction of evaluation function for large domains. Artificial Intelligence 14, 205–220 (1979)CrossRefMathSciNetGoogle Scholar
- 2.Boers, E.J.W., Kuiper, H.: Biological metaphors and the design of modular artificial neural networks, Leiden University (1992)Google Scholar
- 3.Boers, E.J.W., Kuiper, H.: Designing Modular Artificial Neural Networks, Leiden University (1993)Google Scholar
- 4.Boers, E.J.W.: Using L-Systems as Graph Grammar: G2L-Systems, Leiden University (1995)Google Scholar
- 5.Boers, E.J.W., Kuiper, H.: Combined Biological Metaphors, Leiden University (2001)Google Scholar
- 6.Gruau, F.: Neural Network Synthesis using Cellular Encoding and the Genetic Algorithm, École Normale Supérieure de Lyon (1994)Google Scholar
- 7.Happel, B.L.M., Murre, J.M.J.: The Design and Evolution of Modular Neural Network Architectures, Leiden University (1994)Google Scholar
- 8.Holland, J.H.: Adaptation in natural and artificial systems. University of Michigan Press, Ann Harbor (1975)Google Scholar
- 9.Kitano, H.: Designing neural networks using genetic algorithms with graph generation system. Complex Systems 4, 461–476 (1990)zbMATHGoogle Scholar
- 10.Knuth, D.E., Moore, R.W.: An analysis of alpha-beta pruning. Artificial Intelligence, vol 6(4), 293–326 (1975)zbMATHCrossRefMathSciNetGoogle Scholar
- 11.Lindenmayer, A.: Mathematical models for celluar interaction and development, parts I and II. Journal of theoritical biology 18, 280–315 (1968)CrossRefGoogle Scholar
- 12.Mc Culloch, W.S., Pitts, W.: A logical calculus of the ideas immanent in nervous activity. Bull. Mathem. Biophys. 5, 115–133 (1943)CrossRefMathSciNetGoogle Scholar
- 13.Siddiqi, A.A., and S.M. Lucas. A comparison of matrix rewriting versus direct encoding for evolving neural networks. In: International Conference on Evolutionary Computation, pp. 392–397 (1998)Google Scholar
- 14.Yao, X., Liu, Y.: New Evolutionary System for Evolving Artificial Neural Networks. IEEE Transactions on Neural Networks 8, 694–713 (1997)CrossRefGoogle Scholar
Copyright information
© Springer-Verlag Berlin Heidelberg 2004