FORMING EVOLUTIONARY DESIGN OF NEURAL NETWORKS WITH DIFFERENT NODES

Authors

  • Eva Volna

DOI:

https://doi.org/10.47839/ijc.8.1.652

Keywords:

Neuroevolution, multilayer feedforward network, pattern recognition problem, alphabet coding problem.

Abstract

Evolution in artificial neural networks (e.g. neuroevolution) searches through the space of behaviours for a network that performs well at a given task. Here is presented a neuroevolution system evolving populations of neurons that are combined to form the fully connected multilayer feedforward neural network with fixed architecture. In this article, the transfer function has been shown to be an important part of architecture of the artificial neural network and have significant impact on an artificial neural network’s performance. In order to test the efficiency of described method, we applied it to the pattern recognition problem and to the alphabet coding problem.

References

D. B. Fogel. Evolutionary Computation: Toward a New Philosophy of Machine Intelligence. IEEE Press. New York, 1995.

P. Hammerstein, E. H. Hagen, A.V. Herz, M.H. Herzel. Robustness: A key to evolutionary design. Biol. Theory 1(1) 90–93, 2006.

G. Mani. Learning by gradient descent in function space. Proc. of the IEEE Int. Conf. “System, Man, and Cybernetics”, Los Angeles, CA, 1990, pp. 242–247.

D. R. Lovell. A. C. Tsoi. The Performance of the Neocognitron with Various S-Cell and C-Cell Transfer Functions, Intell. Machines Lab., Dep. Elect. Eng., Univ. Queensland, Tech. Rep., Apr. 1992.

D. G. Stork. S. Walker. M. Burns. B. Jackson. Preadaptation in neural circuits. Proc. Int. Joint Conf. “Neural Networks”, vol. I, Washington, DC, 1990, pp. 202–205.

D. White. P. Ligomenides. GANNet: A genetic algorithm for optimizing topology and weights in neural network design. Proc. Int. Workshop “Artificial Neural Networks (IWANN’93)”, Lecture Notes in Computer Science, vol. 686. Berlin, Germany: Springer-Verlag, 1993, pp. 322–327.

Y.Liu. X. Yao. Evolutionary design of artificial neural networks with different nodes. Proc. 1996 IEEE Int. Conf. “Evolutionary Computation (ICEC’96)”, Nagoya, Japan, pp. 670–675.

A. Abraham. Meta learning evolutionary artificial neural networks. Neurocomputing, vol. (56) 1-38, 2004.

F. H. F. Leung, H. K. Lam, S. H. Ling, P. K. S. Tam. Tuning of the structure and parameters of a neural network using an improved genetic algorithm. IEEE Transactions on Neural Neworks. Vol. 14 (1) 79- 88, 2003.

P. Palmes, S. Usui. Robustness, Evolvability and Optimality in Evolutionary Neural Networks”. Biosystems, vol. 82 (2) 168-188, 2005.

A. V. Sebald, K. Chellapilla. On making problems evolutionarily friendly, part I: Evolving the most convenient representations. In V. W. Porto. N.Saravanan, D. Waagen. A. E. Eiben. (Eds.) Evolutionary Programming VII: Proc. 7th Annu Conf. “Evolutionary Programming”, vol. 1447 of Lecture Notes in Computer Science, Berlin, Germany: Springer-Verlag, 1998, pp. 271–280.

R. Miikkulainen. Evolving neural networks. In Proceedings of the 2007 GECCO Conference Companion on Genetic and Evolutionary Computation GECCO '07. ACM, New York, NY, 2007, pp. 3415-3434.

F. J. Gomez. R. Miikkulainen. Active guidance for a finless rocket through neuroevolution. Proceedings of the Conference “Genetic and Evolutionary Computation (GECCO-2003)”. Berlin: Springer Verlag. 2003.

C. Igel. Neuroevolution for reinforcement learning using evolution strategies. In R. Sarker R.Reynolds. H. Abbass. K. C. Tan. B. McKay. D. Essam. T.Gedeon (eds.) “Congress on Evolutionary Computation 2003 (CEC 2003)” Piscataway, NJ: IEEE Press. 2003. pp. 2588–2595.

E. Volna. Forming neural network design through evolution“.. In K. Madani (ed.). Proceedings of the 3th International Workshop on “Artificial Neural Networks and Intelligent Information Processing (ANNIIP 2007)”. In conjunction with ICINCO 2007. Angers, France 2007, pp. 13-20.

Volna, E. “Learning algorithm which learns both architectures and weights of feedforward neural networks“. Neural Network World. Int. Journal on Neural & Mass-Parallel Comp. and Inf. Systems. 8 (6): 653-664, 1998.

S. Garfinger. PGP: Pretty Good Privacy. Computer Press, Praha 1998.

E. Cantu-Paz. Adaptive sampling for noisy problems. In Genetic and Evolutionary Computation Conference, pages 947--958, Springer 2004.

P. A., Castillo, J.J. Merelo, M. G. Arenas, and G. Romero. Comparing evolutionary hybrid systems for design and optimization of multilayer perceptron structure along training parameters. In Information Sciences, Vol 177 (14) 2884-2905, 2007.

Downloads

Published

2014-08-01

How to Cite

Volna, E. (2014). FORMING EVOLUTIONARY DESIGN OF NEURAL NETWORKS WITH DIFFERENT NODES. International Journal of Computing, 8(1), 16-23. https://doi.org/10.47839/ijc.8.1.652

Issue

Section

Articles