Abstract
An Evolutionary Algorithm is used to optimize the architecture and activation functions of an Artificial Neural Networks (ANN). It will be shown that it is possible, with the help of a graph-database and Genetic Engineering, to find modular structures for these networks. Some new graph-rewritings are used to construct families of architectures from these modular structures. Simulation results for two problems are given. An analysis of the data in the database suggest the usage of symmetric activation functions.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
L. Altenberg. The evolution of evolvability in genetic programming. In K. E. Kinnear, editor, Advances in Genetic Programming. MIT Press, 1994. http://pueo.mhpcc.edu/ altenber/PAPERS/Papers2.html.
J. Branke. Evolutionary algorithms for neural network design and training. In Proceedings of the 1st Nordic Workshop on Genetic Algorithms and its Applications, 1995. ftp://ftp.aifb.uni-karlsruhe.de/pub/jbr/Vaasa.ps.
S. Fahlmann and C. Lebiere. The cascade-correlation learning architecture. In Advances in Neural Information Systems-2, pages 525–532. Morgan Kaufmann, 1990.
C. M. Friedrich and C. Moraga. An evolutionary method to find good building-blocks for architectures of artificial neural networks. In Proceedings of the Sixth International Conference on Information Processing and Management of Uncertainty in Knowledge Based Systems (IPMU '96), pages 951–956, Granada, Spain, 1996. ftp://archive.cis.ohio-state.edu/pub/neuroprose/friedrich.ipmu96.ps.Z.
F. Gruau. Cellular encoding of genetic neural networks. Technical Report 92-21, Ecole Normale Superieure de Lyon, Institut IMAG, 1992. ftp://lip.enslyon.fr/pub/Rapports/RR/RR92/RR92-21.ps.Z.
F. Gruau. Genetic synthesis of modular neural networks. In Stephanie Forrest, editor, Proceedings of the Fifth International Conference on Genetic Algorithms, pages 318–325. Morgan Kaufmann, 1993.
R. A. Jacobs, M. I. Jordan, and A. G. Barto. Task decomposition through competition in a modular connectionist architecture: The what and where vision tasks. Technical Report COINS Technical Report 90-27, University of Massachusetts, Amherst, MA, 1990. ftp://archive.cis.ohio-state.edu/pub/neuroprose/jacobs.modular.ps.Z.
J. R. Koza. Genetic programming, on the programming of Computers by means of natural selection. MIT Press, 1992.
K. J. Lang and M. J. Witbrock. Learning to tell two spirals apart. In Proceedings of the 1988 Connectionist Models Summer School, 1988.
D. Michie, D. J. Spiegelhalter, and C. C. Taylor. Machine Learning, neural and statistical classification. Ellis Horwood Ltd., 1994.
Lutz Prechelt. PROBEN1 — A set of benchmarks and benchmarking rules for neural network training algorithms. Technical Report 21/94, Fakultät für Informatik, Universität Karlsruhe, D-76128 Karlsruhe, Germany, September 1994. ftp://ftp.ira.uka.de/pub/papers/techreports/1994/1994-21.ps.Z.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Friedrich, C.M., Moraga, C. (1997). Using Genetic Engineering to find modular structures and activation functions for architectures of Artificial Neural Networks. In: Reusch, B. (eds) Computational Intelligence Theory and Applications. Fuzzy Days 1997. Lecture Notes in Computer Science, vol 1226. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-62868-1_107
Download citation
DOI: https://doi.org/10.1007/3-540-62868-1_107
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-62868-2
Online ISBN: 978-3-540-69031-3
eBook Packages: Springer Book Archive