Advertisement

Promoting Phenotypic Diversity in Genetic Programming

  • David Jackson
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6239)

Abstract

Population diversity is generally seen as playing a crucial role in the ability of evolutionary computation techniques to discover solutions. In genetic programming, diversity metrics are usually based on structural properties of individual program trees, but are also sometimes based on the spread of fitness values in the population. We explore the use of a further interpretation of diversity, in which differences are measured in terms of the behaviour of programs when executed. Although earlier work has shown that improving behavioural diversity in initial GP populations can have a marked beneficial effect on performance, further analysis reveals that lack of behavioural diversity is a problem throughout whole runs, even when other diversity levels are high. To address this, we enhance phenotypic diversity via modifications to the crossover operator, and show that this can lead to additional performance improvements.

Keywords

Phenotypic Diversity Genetic Program Behavioural Diversity Fitness Evaluation Diversity Metrics 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    McPhee, N.F., Hopper, N.J.: Analysis of Genetic Diversity through Program History. In: Banzhaf, W., et al. (eds.) Proc. Genetic and Evolutionary Computation Conf., Florida, USA, pp. 1112–1120 (1999)Google Scholar
  2. 2.
    Daida, J.M., Ward, D.J., Hilss, A.M., Long, S.L., Hodges, M.R., Kriesel, J.T.: Visualizing the Loss of Diversity in Genetic Programming. In: Proc. IEEE Congress on Evolutionary Computation, Portland, Oregon, USA, pp. 1225–1232 (2004)Google Scholar
  3. 3.
    Jackson, D.: Phenotypic Diversity in Initial Genetic Programming Populations. In: Esparcia-Alcázar, A.I., Ekárt, A., Silva, S., Dignum, S., Uyar, A.Ş. (eds.) EuroGP 2010. LNCS, vol. 6021, pp. 98–109. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  4. 4.
    Hien, N.T., Hoai, N.X.: A Brief Overview of Population Diversity Measures in Genetic Programming. In: Pham, T.L., et al. (eds.) Proc. 3rd Asian-Pacific Workshop on Genetic Programming, Hanoi, Vietnam, pp. 128–139 (2006)Google Scholar
  5. 5.
    Burke, E., Gustafson, S., Kendall, G., Krasnogor, N.: Advanced Population Diversity Measures in Genetic Programming. In: Guervos, J.J.M., et al. (eds.) PPSN 2002. LNCS, vol. 2439, pp. 341–350. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  6. 6.
    Burke, E., Gustafson, S., Kendall, G.: Diversity in Genetic Programming: An Analysis of Measures and Correlation with Fitness. IEEE Transactions on Evolutionary Computation 8(1), 47–62 (2004)CrossRefGoogle Scholar
  7. 7.
    Koza, J.R.: Genetic Programming: On the Programming of Computers by Means of Natural Selection. MIT Press, Cambridge (1992)zbMATHGoogle Scholar
  8. 8.
    de Jong, E.D., Watson, R.A., Pollack, J.B.: Reducing Bloat and Promoting Diversity using Multi-Objective Methods. In: Spector, L., et al. (eds.) Proc. Genetic Evolutionary Computation Conf., San Francisco, CA, USA, pp. 11–18 (2001)Google Scholar
  9. 9.
    Wyns, B., de Bruyne, P., Boullart, L.: Characterizing Diversity in Genetic Programming. In: Collet, P., et al. (eds.) EuroGP 2006. LNCS, vol. 3905, pp. 250–259. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  10. 10.
    Rosca, J.P.: Genetic Programming Exploratory Power and the Discovery of Functions. In: McDonnell, J.R., et al. (eds.) Proc. 4th Conf., Evolutionary Programming, San Diego, CA, USA, pp. 719–736 (1995)Google Scholar
  11. 11.
    Rosca, J.P.: Entropy-Driven Adaptive Representation. In: Rosca, J.P. (ed.) Proc. Workshop on Genetic Programming: From Theory to Real-World Applications, Tahoe City, CA, USA, pp. 23–32 (1995)Google Scholar
  12. 12.
    D’haeseleer, P., Bluming, J.: Effects of Locality in Individual and Population Evolution. In: Kinnear, K.E., et al. (eds.) Advances in Genetic Programming, ch. 8. pp. 177–198. MIT Press, Cambridge (1994)Google Scholar
  13. 13.
    Ryan, C.: Pygmies and Civil Servants. In: Kinnear, K.E., et al. (eds.) Advances in Genetic Programming, ch.11, pp. 243–263. MIT Press, Cambridge (1994)Google Scholar
  14. 14.
    Looks, M.: On the Behavioural Diversity of Random Programs. In: Thierens, D., et al. (eds.) Proc. Genetic and Evolutionary Computing Conf. (GECCO 2007), London, England, UK, pp. 1636–1642 (2007)Google Scholar
  15. 15.
    Beadle, L., Johnson, C.G.: Semantic Analysis of Program Initialisation in Genetic Programming. Genetic Programming and Evolvable Machines 10(3), 307–337 (2009)CrossRefGoogle Scholar
  16. 16.
    Beadle, L., Johnson, C.G.: Semantically Driven Crossover in Genetic Programming. In: Proc. IEEE Congress on Evolutionary Computation (CEC), Hong Kong, pp. 111–116 (2008)Google Scholar
  17. 17.
    Soule, T.: Code Growth in Genetic Programming. PhD Thesis, University of Idaho (1998)Google Scholar
  18. 18.
    Langdon, W.B., Soule, T., Poli, R., Foster, J.A.: The Evolution of Size and Shape. In: Spector, L., et al. (eds.) Advances in Genetic Programming, vol. 3, pp. 163–190. MIT Press, Cambridge (1999)Google Scholar
  19. 19.
    Jackson, D.: Dormant Program Nodes and the Efficiency of Genetic Programming. In: Beyer, H.-G., et al. (eds.) Proc. Genetic and Evolutionary Computing Conf. (GECCO 2005), Washington DC, USA, pp. 1745–1751 (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • David Jackson
    • 1
  1. 1.Dept. of Computer ScienceUniversity of LiverpoolLiverpoolUnited Kingdom

Personalised recommendations