Abstract
Automatic methods for designing artificial neural nets are desired to avoid the laborious and erratically human expert’s job. Evolutionary computation has been used as a search technique to find appropriate NN architectures. Direct and indirect encoding methods are used to codify the net architecture into the chromosome. A reformulation of an indirect encoding method, based on two bi-dimensional cellular automata, and its generative capacity are presented.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Alba, E., Aldana, J. F., and Troya, J. M.: Fully automatic RNA design: a genetic approach. X. Yao: Evolutionary Artificial Neural Networks 45 In Proc. of Int’l Workshop on Artificial Neural Networks (IWRNA’93), pages 399–404. Springer-Verlag, 1993. Lecture Notes in Computer Science, Vol. 686.
D.B. Fogel, Fogel L.J. and Porto V.W. Evolving Neural Network, Biological Cybernetics, 63, 487–493, 1990.
Gruau F. “Genetic Synthesis of Boolean Neural Networks with a Cell Rewriting Developmental Process”. Proceedings of COGANN-92 International Workshop on Combinations of Genetic Algorithms and Neural Networks, pp. 55–74, IEEE Computer Society Press, 1992.
G. Gutiérrez1, P. Isasi, J.M. Molina, A. Sanchís and I. M. Galván. Evolutionary Cellular Configurations for Designing Feed-Forward Neural Networks Architectures. Connectionist Models of neurons, Learning Processes and Artificial Intelligence. 6th International Work-Conference on Artificial Neural Networks, IWANN 2001. Proceedings, Part I. LNCS 2084. J. Mira, A Prieto (Eds.) Springer.
Kitano, H.: Designing Neural Networks using Genetic Algorithms with Graph Generation System, Complex Systems, 4, 461–476, 1990.
Geoffrey F. Miller, Peter M. Todd, and Shailesh U. Hegde. Designing Neural Networks using Genetic Algorithms. In J. David Schaffer, editor, Proceedings of the Third International Conference on Genetic Algorithms, pages 379–384, San Mateo, California, 1989. Philips Laboratories, Morgan Kaufman Publishers, Inc.
Molina, J. M., Torresano, A., Galván, I. M., Isasi, P., Sanchis, A.: Evolution of Context-free Grammars for Designing Optimal Neural Networks Architectures. GECCO 2000, Workshop on Evolutionary Computation in the Development of ANN. USA. Julio, 2000
E. D. Sontag. Feedforward nets for interpolation and classification. Journal of Computer and System Sciences, 45, 1992.
S. Wolfram. Theory and applications of cellular automata. World Scientific, Singapore, 1988.
Yao, X. 1999. Evolving artificial neural networks, Proceedings of the IEEE vol. 87, no. 9, p. 1423–1447.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gutiérrez, G., Galván, I.M., Molina, J.M., Sanchis, A. (2002). Generative Capacities of Cellular Automata Codification for Evolution of NN Codification. In: Dorronsoro, J.R. (eds) Artificial Neural Networks — ICANN 2002. ICANN 2002. Lecture Notes in Computer Science, vol 2415. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-46084-5_52
Download citation
DOI: https://doi.org/10.1007/3-540-46084-5_52
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-44074-1
Online ISBN: 978-3-540-46084-8
eBook Packages: Springer Book Archive