Advertisement

Semantic Geometric Initialization

  • Tomasz P. PawlakEmail author
  • Krzysztof Krawiec
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9594)

Abstract

A common approach in Geometric Semantic Genetic Programming (GSGP) is to seed initial populations using conventional, semantic-unaware methods like Ramped Half-and-Half. We formally demonstrate that this may limit GSGP’s ability to find a program with the sought semantics. To overcome this issue, we determine the desired properties of geometric-aware semantic initialization and implement them in Semantic Geometric Initialization (Sgi) algorithm, which we instantiate for symbolic regression and Boolean function synthesis problems. Properties of Sgi and its impact on GSGP search are verified experimentally on nine symbolic regression and nine Boolean function synthesis benchmarks. When assessed experimentally, Sgi leads to superior performance of GSGP search: better best-of-run fitness and higher probability of finding the optimal program.

Keywords

Geometric semantic genetic programming Semantic initialization Population 

Notes

Acknowledgements

T. Pawlak acknowledges support from grant no. DEC-2012/07/N/ST6/03066, K. Krawiec from grant no 2014/15/B/ST6/05205, both funded by the National Science Centre, Poland.

References

  1. 1.
    Beadle, L., Johnson, C.G.: Semantic analysis of program initialisation in genetic programming. Genet. Program Evolvable Mach. 10(3), 307–337 (2009)CrossRefGoogle Scholar
  2. 2.
    Burden, R., Faires, J.: Numerical Analysis. Cengage Learning, Boston (2010)zbMATHGoogle Scholar
  3. 3.
    Castelli, M., Henriques, R., Vanneschi, L.: A geometric semantic genetic programming system for the electoral redistricting problem. Neurocomputing 154, 200–207 (2015)CrossRefGoogle Scholar
  4. 4.
    Castelli, M., Vanneschi, L., Silva, S.: Prediction of the unified Parkinson’s disease rating scale assessment using a genetic programming system with geometric semantic genetic operators. Expert Syst. Appl. 41(10), 4608–4616 (2014)CrossRefGoogle Scholar
  5. 5.
    Geman, S., Bienenstock, E., Doursat, R.: Neural networks and the bias/variance dilemma. Neural Comput. 4(1), 1–58 (1992)CrossRefGoogle Scholar
  6. 6.
    Hothorn, T., Hornik, K., van de Wiel, M.A., Zeileis, A.: Package ‘coin’: conditional inference procedures in a permutation test framework (2015). http://cran.r-project.org/web/packages/coin/coin.pdf
  7. 7.
    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
  8. 8.
    Kanji, G.: 100 Statistical Tests. SAGE Publications, London (1999)Google Scholar
  9. 9.
    Koza, J.R.: Genetic Programming: On the Programming of Computers by Means of Natural Selection. MIT Press, Cambridge (1992)zbMATHGoogle Scholar
  10. 10.
    Krawiec, K.: Medial crossovers for genetic programming. In: Moraglio, A., Silva, S., Krawiec, K., Machado, P., Cotta, C. (eds.) EuroGP 2012. LNCS, vol. 7244, pp. 61–72. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  11. 11.
    Krawiec, K., Lichocki, P.: Approximating geometric crossover in semantic space. In: GECCO 2009, 8–12 July 2009, pp. 987–994. ACM, Montreal (2009)Google Scholar
  12. 12.
    Krawiec, K., Pawlak, T.: Locally geometric semantic crossover: a study on the roles of semantics and homology in recombination operators. Genet. Program Evolvable Mach. 14(1), 31–63 (2013)CrossRefGoogle Scholar
  13. 13.
    Looks, M.: On the behavioral diversity of random programs. In: GECCO 2007, 7–11 July 2007, vol. 2, pp. 1636–1642. ACM Press, London (2007)Google Scholar
  14. 14.
    Luke, S.: The ECJ Owner’s Manual - A User Manual for the ECJ Evolutionary Computation Library, zeroth edition, October 2010. http://cs.gmu.edu/~eclab/projects/ecj/docs/
  15. 15.
    McDermott, J., White, D.R., Luke, S., Manzoni, L., Castelli, M., Vanneschi, L., Jaskowski, W., Krawiec, K., Harper, R., De Jong, K., O’Reilly, U.M.: Genetic programming needs better benchmarks. In: GECCO 2012, 7–11 July 2012, pp. 791–798. ACM, Philadelphia, Pennsylvania, USA (2012)Google Scholar
  16. 16.
    Moraglio, A., Krawiec, K., Johnson, C.G.: Geometric semantic genetic programming. In: Coello, C.A.C., Cutello, V., Deb, K., Forrest, S., Nicosia, G., Pavone, M. (eds.) PPSN 2012, Part I. LNCS, vol. 7491, pp. 21–31. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  17. 17.
    Moraglio, A., Mambrini, A.: Runtime analysis of mutation-based geometric semantic genetic programming for basis functions regression. In: GECCO 2013, 6–10 July 2013, pp. 989–996. ACM, Amsterdam, The Netherlands (2013)Google Scholar
  18. 18.
    Moraglio, A., Mambrini, A., Manzoni, L.: Runtime analysis of mutation-based geometric semantic genetic programming on Boolean functions. In: FOGA, 16–20 Jan 2013, pp. 119–132. ACM, Adelaide, Australia (2013)Google Scholar
  19. 19.
    Moraglio, A., Sudholt, D.: Runtime analysis of convex evolutionary search. In: Soule, T., Moore, J.H. (eds.) GECCO, pp. 649–656. ACM (2012)Google Scholar
  20. 20.
    Pawlak, T.P.: Competent algorithms for geometric semantic genetic programming. Ph.D. thesis, Poznan University of Technology, Poznan, Poland, 21 September 2015. http://www.cs.put.poznan.pl/tpawlak/link/?PhD
  21. 21.
    Pawlak, T.P.: Geometric semantic genetic programming is overkill. In: Heywood, M., McDermott, J., Castelli, M., Costa, E., Sim, K. (eds.) EuroGP 2016. LNCS, vol. 9594, pp. 246–260. Springer, Switzerland (2016)Google Scholar
  22. 22.
    Pawlak, T.P., Krawiec, K.: Properties of progress and fitness bounds for geometric semantic genetic programming. Genet. Program Evolvable Mach., 1–19 (2015) (Online first)Google Scholar
  23. 23.
    Pawlak, T.P., Wieloch, B., Krawiec, K.: Review and comparative analysis of geometric semantic crossovers. Genet. Program Evolvable Mach. 16(3), 351–386 (2015)CrossRefGoogle Scholar
  24. 24.
    Pawlak, T.P., Wieloch, B., Krawiec, K.: Semantic backpropagation for designing search operators in genetic programming. IEEE Trans. Evol. Comput. 19(3), 326–340 (2015)CrossRefGoogle Scholar
  25. 25.
    Runge, C.: Über empirische funktionen und die interpolation zwischen äquidistanten ordinaten. Zeitschrift für Mathematik und Physik 46, 224–243 (1901)zbMATHGoogle Scholar
  26. 26.
    Saniee, K.: A Simple Expression for Multivariate Lagrange Interpolation, pp. 1–9. Society for Industrial and Applied Mathematics (2007)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  1. 1.Institute of Computing SciencePoznan University of TechnologyPoznanPoland

Personalised recommendations