Designing Neural Networks Using Gene Expression Programming
An artificial neural network with all its elements is a rather complex structure, not easily constructed and/or trained to perform a particular task. Consequently, several researchers used genetic algorithms to evolve partial aspects of neural networks, such as the weights, the thresholds, and the network architecture. Indeed, over the last decade many systems have been developed that perform total network induction. In this work it is shown how the chromosomes of Gene Expression Programming can be modified so that a complete neural network, including the architecture, the weights and thresholds, could be totally encoded in a linear chromosome. It is also shown how this chromosomal organization allows the training/adaptation of the network using the evolutionary mechanisms of selection and modification, thus providing an approach to the automatic design of neural networks. The workings and performance of this new algorithm are tested on the 6-multiplexer and on the classical exclusive-or problems.
KeywordsNeural Network Boolean Function Genetic Operator Gene Expression Programming Chromosomal Organization
Unable to display preview. Download preview PDF.
- Anderson, J. A. (1995), An Introduction to Neural Networks, MIT Press.Google Scholar
- Braun, H. and J. Weisbrod (1993), “Evolving feedforward neural networks,” In Proceedings of the International Conference on Artificial Neural Networks and Genetic Algorithms, Innsbruck, Springer-Verlag.Google Scholar
- Dasgupta, D. and D. McGregor (1992), “Designing application-specific neural networks using the structured genetic algorithm,” In Proceedings of the International Conference on Combinations of Genetic Algorithms and Artificial Neural Networks, pp. 87–96.Google Scholar
- Ferreira, C. (2003), “Function finding and the creation of numerical constants in gene expression programming,” In J. M. Benitez, O. Cordon, F. Hoffmann, and R. Roy, eds, Advances in Soft Computing: Engineering Design and Manufacturing, pp. 257–266, Springer-Verlag.Google Scholar
- Gruau, F., D. Whitley, and L. Pyeatt (1996), “A comparison between cellular encoding and direct encoding for genetic neural networks,” In J. R. Koza, D. E. Goldberg, D. B. Fogel, and R. L. Riolo, eds, Genetic Programming: Proceedings of the First Annual Conference, pp. 81–89, Cambridge, MA, MIT Press.Google Scholar
- Koza, J. R. and J. P. Rice (1991), “Genetic generation of both the weights and architecture for a neural network,” In Proceedings of the International Joint Conference on Neural Networks, Volume II, IEEE Press.Google Scholar
- Lee, C.-H. and J.-H. Kim (1996), “Evolutionary ordered neural network with a linked-list encoding scheme,” In Proceedings of the 1996 IEEE International Conference on Evolutionary Computation, pp. 665–669.Google Scholar
- Mandischer, M. (1993), “Representation and evolution of neural networks,” In R. F. Albrecht, C. R. Reeves, and U. C. Steele, eds, Artificial Neural Nets and Genetic Algorithms, pp. 643–649, Springer Verlag.Google Scholar
- Pujol, J. C. F. and R. Poli (1998), “Evolving the topology and the weights of neural networks using a dual representation,” Applied Intelligence Journal, Special Issue on Evolutionary Learning, 8(1): 73–84.Google Scholar
- Zhang, B.-T. and H. Muhlenbein (1993), “Evolving optimal neural networks using genetic algorithms with Occam’s razor,” Complex Systems, 7: 199–220.Google Scholar