Pacific national university Main page Bulletin of Pacific national university

UDC 62-50:61

© Korolev D.A., Sufiyanov V. G., 2007

The neuroevolutionary approach to optimization of inner structure of neural nets

In the article application of genetic algorithm for optimization of topology of an artificial neural net is considered. Carried out research on test tasks of approximation and extrapolation has shown the efficiency of application of the evolutionary approach for finding the optimum quantity of neurons in the "latent" layers and a number of bonds between net neurons.

References:

  1. Osovskiy S. Neyronnye seti dlya obrabotki informatsii. M., 2002.
  2. Yao X. Evolving artificial neural networks // Proceedings of the IEEE. 1999. ¹. 9(87).
  3. Rutkovskaya D. Neyronnye seti, geneticheskie algoritmy i nechetkie sistemy. M., 2006.
  4. Whitley D., Starkweather T., Bogart C. Genetic Algorithms and Neural Networks: Optimization Connections and Connectivity // Parallel Computing. 1990. Vol. 14.
  5. Montana D. J., Davis L. Training feedforward neural networks using genetic algorithms // Proceedings of 11th International Joint Conference on Artificial Intelligence. 1989.
  6. Korning P. G. Training Neural Networks by Means of Genetic Algorithms Working on Very Long Chromosomes // International Journal of Neural Systems. 1995. Vol. 6. ¹. 3.
  7. Belew R. K., McInerney J., Schraudolph N. N. Evolving networks: Using Genetic algorithms with connectionist learning. La Jolla, CA: Universiry of California at San Diego, 1990.
  8. Schaffer J. D., Whitley L., Eshelman J. Combinations of Genetic Algorithms and Neural Networks // Proceedings of the International Workshop on Combination of Genetic Algorithms and Neural Networks (COGANN-92). 1992.
  9. Mandisher M. Representation and evolution of neural networks // Proceedings of the International Conference at Innsbruck. Austria. 1993.
  10. Koehn P. Combining Genetic Algorithms and Neural Networks: The Encoding Problem // Masters Thesis, University of Tennessee. Knoxville. 1994.
  11. Koza J. R., Rice J. P. Genetic generation of both the weight and architecture for a Neural Network // Proceedings of International Joint Conference on Neural Networks. 1991.
  12. Guo Z., Uhrig R.. E. Use of genetic algorithms to select inputs for neural networks // Proceedings of the International Workshop on Combination of Genetic Algorithms and Neural Networks (COGANN-92). 1992.
  13. http://www-optima.amp.i.kyoto-u.ac.jp/member/student/hedar/Hedar_files/ TestGO_files/Page1905.htm

Download Download article (429.2 Kb)

Сontents Сontents