Resource-Limited Genetic Programming: Replacing Tree Depth Limits

  • Sara Silva
  • Pedro J.N. Silva
  • Ernesto Costa


We propose replacing the traditional tree depth limit in Genetic Programming by a single limit on the amount of resources available to the whole population, where resources are the tree nodes. The resource-limited technique removes the disadvantages of using depth limits at the individual level, while introducing automatic population resizing, a natural side-effect of using an approach at the population level. The results show that the replacement of individual depth limits by a population resource limit can be done without impairing performance, thus validating this first and important step towards a new approach to improving the efficiency of GP.


Genetic Programming Tree Size Tree Node Left Plot Depth Limit 
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]
    Banzhaf, W., Nordin, P., Keller, R. E., Francone, F. D. (1998). Genetic Programming-An Introduction. Morgan Kaufmann, San Francisco, CA.Google Scholar
  2. [2]
    Koza, J. R. (1992). Genetic programming-on the programming of computers by means of natural selection. The MIT Press, Cambridge, MA.Google Scholar
  3. [3]
    Soule, T., Foster, J. A. (1999). Effects of code growth and parsimony pressure on populations in genetic programming. Evolutionary Computation 6(4):293–309Google Scholar
  4. [4]
    Poli, R. (2003). A simple but theoretically-motivated method to control bloat in genetic programming. In Ryan, C. et al. (eds.), Proceedings of EuroGP-2003. Springer, Berlin, pp. 204–217Google Scholar
  5. [5]
    Luke, S., Panait, L. (2002). Lexicographic parsimony pressure. In Langdon, W. B. et al. (eds.), Proceedings of GECCO-2002. Morgan Kaufmann, San Francisco, CA, pp. 829–836Google Scholar
  6. [6]
    Panait, L., Luke, S. (2004). Alternative bloat control methods. In Deb, K. et al. (eds.), Proceedings of GECCO-2004. Springer, Berlin, pp. 630–641Google Scholar
  7. [7]
    Wagner, N., Michalewicz, Z. (2001). Genetic programming with efficient population control for financial time series prediction. In Goodman, E. D. (ed.), GECCO-2001 LBP, pp. 458–462Google Scholar
  8. [8]
    Kennedy, C. J., Giraud-Carrier, C. (1999). A Depth Controlling Strategy for Strongly Typed Evolutionary Programming. In Banzhaf, W. et al. (eds.), Proceedings of GECCO-1999. Morgan Kaufman, San Francisco, CA, pp. 1–6Google Scholar
  9. [9]
    Langdon, W. B. (2000). Size fair and homologous tree crossovers for tree genetic programming. Genetic Programming and Evolvable Machines 1:95–119MATHCrossRefGoogle Scholar
  10. [10]
    Silva, S., Almeida, J. S. (2003). Dynamic maximum tree depth. In Cantú-Paz, E. et al. (eds.), Proceedings of GECCO-2003. Springer, Berlin, pp. 1776–1787Google Scholar
  11. [11]
    Silva, S., Costa, E. (2004). Dynamic limits for bloat control. In Deb, K. et al. (eds.), Proceedings of GECCO-2004. Springer, Berlin, pp. 666–677Google Scholar
  12. [12]
    Luke, S., Balan, G. C., Panait, L. (2003). Population implosion in genetic programming. In Cantú-Paz, E. et al. (eds.), Proceedings of GECCO-2003. Springer, Berlin, pp. 1729–1739Google Scholar
  13. [13]
    Fernandez, F., Vanneschi, L., Tomassini, M. (2003). The effect of plagues in genetic programming: A study of variable-size populations. In Ryan, C. et al. (eds.), Proceedings of EuroGP-2003. Springer, Berlin, pp. 317–326Google Scholar
  14. [14]
    Fernandez, F., Tomassini, M., Vanneschi, L. (2003). Saving computational effort in genetic programming by means of plagues. In Sarker, R. et al. (eds.), Proceedings of CEC-2003. IEEE Press, Piscataway, NJ, pp. 2042–2049Google Scholar
  15. [15]
    Tomassini, M., Vanneschi, L., Cuendet, J., Fernandez, F. (2004). A new technique for dynamic size populations in genetic programming. In Proceedings of CEC-2004. IEEE Press, Piscataway, NJ, pp. 486–493Google Scholar
  16. [16]
    Silva, S. (2004). GPLAB-a genetic programming toolbox for MATLAB. http://gplab.sourceforge.netGoogle Scholar

Copyright information

© Springer-Verlag/Wien 2005

Authors and Affiliations

  • Sara Silva
    • 1
  • Pedro J.N. Silva
    • 2
  • Ernesto Costa
    • 1
  1. 1.Dep. Engenharia Informática Polo II - Pinhal de MarrocosCentro de Informática e Sistemas da Univ. CoimbraCoimbraPortugal
  2. 2.Dep. Biologia Vegetal Fac. Ciências Univ. Lisboa, Campo GrandeCentro de Genética e Biologia MolecularLisboaPortugal

Personalised recommendations