Locality in Continuous Fitness-Valued Cases and Genetic Programming Difficulty

  • Edgar Galvan
  • Leonardo Trujillo
  • James McDermott
  • Ahmed Kattan
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 175)

Abstract

It is commonly accepted that a mapping is local if it preserves neighbourhood. In Evolutionary Computation, locality is generally described as the property that neighbouring genotypes correspond to neighbouring phenotypes. Locality has been classified in one of two categories: high and low locality. It is said that a representation has high locality if most genotypic neighbours correspond to phenotypic neighbours. The opposite is true for a representation that has low locality. It is argued that a representation with high locality performs better in evolutionary search compared to a representation that has low locality. In this work, we explore, for the first time, a study on Genetic Programming (GP) locality in continuous fitnessvalued cases. For this, we extended the original definition of locality (first defined and used in Genetic Algorithms using bitstrings) from genotype-phenotype mapping to the genotype-fitness mapping. Then, we defined three possible variants of locality in GP regarding neighbourhood. The experimental tests presented here use a set of symbolic regression problems, two different encoding and two different mutation operators. We show how locality can be studied in this type of scenarios (continuous fitness-valued cases) and that locality can successfully been used as a performance prediction tool.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Altenberg, L.: Fitness Distance Correlation Analysis: An Instructive Counterexample. In: Back, T. (ed.) Proceedings of the Seventh International Conference on Genetic Algorithms, San Francisco, CA, USA, pp. 57–64 (1997)Google Scholar
  2. 2.
    Beyer, H., Schwefel, H.: Evolution strategies - A comprehensive introduction. Natural Computing 1(1), 3–52 (2002)MathSciNetMATHCrossRefGoogle Scholar
  3. 3.
    D’haeseleer, P., Bluming, J.: Effects of locality in individual and population evolution. In: Kinnear, K.E. (ed.) Advances in Genetic Programming, pp. 177–198 (1994)Google Scholar
  4. 4.
    Galván-López, E., McDermott, J., O’Neill, M., Brabazon, A.: Defining locality in genetic programming to predict performance. In: 2010 IEEE Congress on Evolutionary Computation (CEC), pp. 1–8 (2010)Google Scholar
  5. 5.
    Galván-López, E., McDermott, J., O’Neill, M., Brabazon, A.: Towards an understanding of locality in genetic programming. In: Proceedings of the 12th Annual Conference on Genetic and Evolutionary Computation, GECCO 2010, New York, NY, USA, pp. 901–908 (2010)Google Scholar
  6. 6.
    Galván-López, E., McDermott, J., O’Neill, M., Brabazon, A.: Defining locality as a problem difficulty measure in genetic programming. Genetic Programming and Evolvable Machines 12(4), 365–401 (2011)CrossRefGoogle Scholar
  7. 7.
    Galván-López, E., Poli, R.: An empirical investigation of how degree neutrality affects GP search. In: Aguirre, A.H., Borja, R.M., Garciá, C.A.R. (eds.) MICAI 2009. LNCS, vol. 5845, pp. 728–739. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  8. 8.
    Galván-López, E., Poli, R., Kattan, A., O’Neill, M., Brabazon, A.: Neutrality in evolutionary algorithms... what do we know? Evolving Systems 2(3), 145–163 (2011)CrossRefGoogle Scholar
  9. 9.
    Goldberg, D.E.: Genetic Algorithms in Search, Optimization and Machine Learning. Addison-Wesley, Reading (1989)MATHGoogle Scholar
  10. 10.
    Jones, T.: Evolutionary Algorithms, Fitness Landscapes and Search. PhD thesis, University of New Mexico, Albuquerque (1995)Google Scholar
  11. 11.
    Koza, J.R.: Genetic Programming: On the Programming of Computers by Means of Natural Selection. The MIT Press, Cambridge (1992)MATHGoogle Scholar
  12. 12.
    Naudts, B., Kallel, L.: A comparison of predictive measures of problem difficulty in evolutionary algorithms. IEEE Transactions on Evolutionary Computation 4(1), 1–15 (2000)CrossRefGoogle Scholar
  13. 13.
    Poli, R., Galván-López, E.: The effects of constant and bit-wise neutrality on problem hardness, fitness distance correlation and phenotypic mutation rates. IEEE Trans. Evolutionary Computation 16(2), 279–300 (2012)CrossRefGoogle Scholar
  14. 14.
    Rothlauf, F.: Representations for Genetic and Evolutionary Algorithms, 2nd edn. Physica-Verlag (2006)Google Scholar
  15. 15.
    Stadler, P.F., Stephens, C.R.: Landscapes and Effective Fitness. Comments on Theoretical Biology 8(4), 389–431 (2003)CrossRefGoogle Scholar
  16. 16.
    Tomassini, M., Vanneschi, L., Collard, P., Clergue, M.: A study of fitness distance correlation as a difficulty measure in genetic programming. Evolutionary Computation 13(2), 213–239 (2005)CrossRefGoogle Scholar
  17. 17.
    Trujillo, L., Martínez, Y., Galván-López, E., Legrand, P.: Predicting problem difficulty for genetic programming applied to data classification. In: Proceedings of the 13th Annual Conference on Genetic and Evolutionary Computation, GECCO 2011, New York, NY, USA, pp. 1355–1362 (2011)Google Scholar
  18. 18.
    Vanneschi, L., Clergue, M., Collard, P., Tomassini, M., Vérel, S.: Fitness clouds and problem hardness in genetic programming. In: Deb, K., Tari, Z. (eds.) GECCO 2004. LNCS, vol. 3103, pp. 690–701. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  19. 19.
    Vanneschi, L., Tomassini, M., Collard, P., Clergue, M.: Fitness Distance Correlation in Structural Mutation Genetic Programming. In: Ryan, C., Soule, T., Keijzer, M., Tsang, E.P.K., Poli, R., Costa, E. (eds.) EuroGP 2003. LNCS, vol. 2610, pp. 455–464. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  20. 20.
    Wright, S.: The Roles of Mutation, Inbreeding, Crossbreeding and Selection in Evolution. In: Jones, D.F. (ed.) Proceedings of the Sixth International Congress on Genetics, vol. 1, pp. 356–366 (1932)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Edgar Galvan
    • 1
  • Leonardo Trujillo
    • 2
  • James McDermott
    • 3
  • Ahmed Kattan
    • 4
  1. 1.Distributed Systems Group, School of Computer Science and StatisticsTrinity CollegeDublinIreland
  2. 2.Departamento de Ingeniería Eléctrica y ElectrónicaInstituto Tecnológico de TijuanaTijuanaMéxico
  3. 3.EvoDesignOptMIT CSAILCambridgeUSA
  4. 4.Computer Science DepartmentLoughborough UniversityLoughboroughUnited Kingdom

Personalised recommendations