A Genetic Algorithm for ANN Design, Training and Simplification

  • Daniel Rivero
  • Julian Dorado
  • Enrique Fernández-Blanco
  • Alejandro Pazos
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5517)


This paper proposes a new evolutionary method for generating ANNs. In this method, a simple real-number string is used to codify both architecture and weights of the networks. Therefore, a simple GA can be used to evolve ANNs. One of the most interesting features of the technique presented here is that the networks obtained have been optimised, and they have a low number of neurons and connections. This technique has been applied to solve one of the most used benchmark problems, and results show that this technique can obtain better results than other automatic ANN development techniques.


Genetic Algorithm Genetic Programming Hide Node Hide Neuron Simple Genetic Algorithm 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Rabuñal, J.R., Dorado, J. (eds.): Artificial Neural Networks in Real-Life Applications. Idea Group Inc. (2005)Google Scholar
  2. 2.
    Cantú-Paz, E., Kamath, C.: An Empirical Comparison of Combinations of Evolutionary Algorithms and Neural Networks for Classification Problems. IEEE Transactions on systems, Man and Cybernetics Part B: Cybernetics 35, 915–927 (2005)CrossRefGoogle Scholar
  3. 3.
    Rivero, D., Dorado, J., Rabuñal, J.R., Pazos, A.: Modifying genetic programming for artificial neural network development for data mining. Soft Computing - A Fusion of Foundations, Methodologies and Applications 13(3), 291–305 (2008)Google Scholar
  4. 4.
    Goldberg, D.E.: Genetic Algorithms in Search, Optimization and Machine Learning. Addison-Wesley, Reading (1989)MATHGoogle Scholar
  5. 5.
    Darwin, C.: On the Origin of Species by means of Natural Selection or the Preservation of Favoured Races in the Struggle for Life, 6th edn. Cambridge University Press, Cambridge (1864); originally published in 1859Google Scholar
  6. 6.
    Greenwood, G.W.: Training partially recurrent neural networks using evolutionary strategies. IEEE Trans. Speech Audio Processing 5, 192–194 (1997)CrossRefGoogle Scholar
  7. 7.
    Alba, E., Aldana, J.F., Troya, J.M.: Fully automatic ANN design: A genetic approach. In: Mira, J., Cabestany, J., Prieto, A.G. (eds.) IWANN 1993. LNCS, vol. 686, pp. 399–404. Springer, Heidelberg (1993)CrossRefGoogle Scholar
  8. 8.
    Kitano, H.: Designing neural networks using genetic algorithms with graph generation system. Complex Systems 4, 461–476 (1990)MATHGoogle Scholar
  9. 9.
    Harp, S.A., Samad, T., Guha, A.: Toward the genetic synthesis of neural networks. In: Proc. 3rd Int. Conf. Genetic Algorithms and Their Applications, pp. 360–369. Morgan Kaufmann, San Mateo (1989)Google Scholar
  10. 10.
    Turney, P., Whitley, D., Anderson, R.: Special issue on the baldwinian effect. Evolutionary Computation 4(3), 213–329 (1996)CrossRefGoogle Scholar
  11. 11.
    Werbos, P.J.: The Roots of Backpropagation: From Ordered Derivatives to Neural Networks and Political Forecasting. Wiley, New York (1994)Google Scholar
  12. 12.
    Garcia-Pedrajas, N., Ortiz-Boyer, D., Hervas-Martinez, C.: Cooperative coevolution of generalized multi-layer perceptrons. Neurocomputing 56, 257–283 (2004)CrossRefGoogle Scholar
  13. 13.
    Mertz, C.J., Murphy, P.M.: UCI repository of machine learning databases (2002),

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Daniel Rivero
    • 1
  • Julian Dorado
    • 1
  • Enrique Fernández-Blanco
    • 1
  • Alejandro Pazos
    • 1
  1. 1.Department of Information Technologies and CommunicationsSpain

Personalised recommendations