For Sale or Wanted: Directed Crossover in Adjudicated Space

Jeannie M. Fitzgerald, Conor Ryan

Abstract

Significant recent effort in genetic programming has focused on selecting and combining candidate solutions according to a notion of behaviour defined in semantic space and has also highlighted disadvantages of relying on a single scalar measure to capture the complexity of program performance in evolutionary search. In this paper, we take an alternative, yet complementary approach which directs crossover in what we call adjudicated space, where adjudicated space represents an abstraction of program behaviour that focuses on the success or failure of candidate solutions in solving problem sub-components. We investigate the effectiveness of several possible adjudicated strategies on a variety of classification and symbolic regression problems, and show that both of our novel pillage and barter tactics significantly outperform both a standard genetic programming and an enhanced genetic programming configuration on the fourteen problems studied.

References

  1. Bache, K. and Lichman, M. (2013). UCI machine learning repository.
  2. Bassett, J., Kamath, U., and De Jong, K. (2012). A new methodology for the GP theory toolbox. In Soule, T. et al., editors, GECCO 7812: Proceedings of the fourteenth international conference on Genetic and evolutionary computation conference, pages 719-726, Philadelphia, Pennsylvania, USA. ACM.
  3. Beadle, L. and Johnson, C. (2008). Semantically driven crossover in genetic programming. In Wang, J., editor, Proceedings of the IEEE World Congress on Computational Intelligence, pages 111-116, Hong Kong. IEEE Computational Intelligence Society, IEEE Press.
  4. Brooks, R. A. (1999). Cambrian intelligence: the early history of the new AI. Mit Press.
  5. Krawiec, K. (2012). Medial crossovers for genetic programming. In Moraglio, A., et al., editors, Proceedings of the 15th European Conference on Genetic Programming, EuroGP 2012, volume 7244 of LNCS, pages 61-72, Malaga, Spain. Springer Verlag.
  6. Krawiec, K. and Lichocki, P. (2009). Approximating geometric crossover in semantic space. In Raidl, G., et al., editors, GECCO 7809: Proceedings of the 11th Annual conference on Genetic and evolutionary computation, pages 987-994, Montreal. ACM.
  7. Krawiec, K. and Liskowski, P. (2015). Automatic derivation of search objectives for test-based genetic programming. In Genetic Programming, pages 53-65. Springer.
  8. Krawiec, K. and O'Reilly, U.-M. (2014). Behavioral programming: a broader and more detailed take on semantic gp. In Proceedings of the 2014 conference on Genetic and evolutionary computation, pages 935- 942. ACM.
  9. Langdon, W. B. (1995). Directed crossover within genetic programming. Research Note RN/95/71, University College London, Gower Street, London WC1E 6BT, UK.
  10. Langdon, W. B. (1999). Size fair and homologous tree genetic programming crossovers. In Banzhaf, W., et al., editors, Proceedings of the Genetic and Evolutionary Computation Conference, volume 2, pages 1092- 1097, Orlando, Florida, USA. Morgan Kaufmann.
  11. Lehman, J. and Stanley, K. O. (2008). Exploiting openendedness to solve problems through the search for novelty. In ALIFE, pages 329-336.
  12. Lehman, J. and Stanley, K. O. (2010). Efficiently evolving programs through the search for novelty. In Branke, J., et al., editors, GECCO 7810: Proceedings of the 12th annual conference on Genetic and evolutionary computation, pages 837-844, Portland, Oregon, USA. ACM.
  13. Majeed, H. and Ryan, C. (2006). Using context-aware crossover to improve the performance of GP. In Keijzer, M., et al., editors, GECCO 2006: Proceedings of the 8th annual conference on Genetic and evolutionary computation, volume 1, pages 847-854, Seattle, Washington, USA. ACM Press.
  14. Moraglio, A., Krawiec, K., and Johnson, C. G. (2012). Geometric semantic genetic programming. In Coello Coello, C. A., et al., editors, Parallel Problem Solving from Nature, PPSN XII (part 1), volume 7491 of Lecture Notes in Computer Science, pages 21-31, Taormina, Italy. Springer.
  15. Moraglio, A. and Poli, R. (2004). Topological interpretation of crossover. In Deb, K., et al., editors, Genetic and Evolutionary Computation - GECCO-2004, Part I, volume 3102 of Lecture Notes in Computer Science, pages 1377-1388, Seattle, WA, USA. SpringerVerlag.
  16. CEC Moraglio, A. and Poli, R. (2005). Geometric landscape of homologous crossover for syntactic trees. In Proceedings of the 2005 IEEE Congress on Evolutionary Computation (CEC-2005), volume 1, pages 427- 434, Edinburgh. IEEE.
  17. Moraglio, A., Poli, R., and Seehuus, R. (2006). Geometric crossover for biological sequences. In Collet, P., et al., editors, Proceedings of the 9th European Conference on Genetic Programming, volume 3905 of Lecture Notes in Computer Science, pages 121-132, Budapest, Hungary. Springer.
  18. Naredo, E., Trujillo, L., and Martinez, Y. (2013). Searching for novel classifiers. In Krawiec, K., et al., editors, Proceedings of the 16th European Conference on Genetic Programming, EuroGP 2013, volume 7831 of LNCS, pages 145-156, Vienna, Austria. Springer Verlag.
  19. Nguyen, Q. U., Nguyen, X. H., and O'Neill, M. (2009). Semantic aware crossover for genetic programming: The case for real-valued function regression. In Vanneschi, L., et al., editors, Proceedings of the 12th European Conference on Genetic Programming, EuroGP 2009, volume 5481 of LNCS, pages 292-302, Tuebingen. Springer.
  20. Pawlak, T. P., Wieloch, B., and Krawiec, K. (2014). Review and comparative analysis of geometric semantic crossovers. Genetic Programming and Evolvable Machines, pages 1-36.
  21. Ruberto, S., Vanneschi, L., Castelli, M., and Silva, S. (2014). ESAGP - A semantic GP framework based on alignment in the error space. In Nicolau, M., et al., editors, 17th European Conference on Genetic Programming, volume 8599 of LNCS, pages 150-161, Granada, Spain. Springer.
  22. Trujillo, L., Mun˜oz, L., Naredo, E., and Martínez, Y. (2014). Neat, theres no bloat. In Genetic Programming, pages 174-185. Springer.
  23. Trujillo, L., Naredo, E., and Martinez, Y. (2013). Preliminary study of bloat in genetic programming with behavior-based search. In Emmerich, M., et al., editors, EVOLVE - A Bridge between Probability, Set Oriented Numerics, and Evolutionary Computation IV, volume 227 of Advances in Intelligent Systems and Computing, pages 293-305, Leiden, Holland. Springer.
  24. Uy, N. Q., Hoai, N. X., O'Neill, M., McKay, B., and Galvan-Lopez, E. (2009). An analysis of semantic aware crossover. In Cai, Z., et al., editors, Proceedings of the International Symposium on Intelligent Computation and Applications, volume 51 of Communications in Computer and Information Science, pages 56-65. Springer.
  25. Uy, N. Q., Hoai, N. X., ONeill, M., McKay, R. I., and Galván-López, E. (2011). Semantically-based crossover in genetic programming: application to realvalued symbolic regression. Genetic Programming and Evolvable Machines, 12(2):91-119.
  26. Vanneschi, L., Castelli, M., and Silva, S. (2014). A survey of semantic methods in genetic programming. Genetic Programming and Evolvable Machines, 15(2):195- 214.
Download


Paper Citation


in Harvard Style

Fitzgerald J. and Ryan C. (2015). For Sale or Wanted: Directed Crossover in Adjudicated Space . In Proceedings of the 7th International Joint Conference on Computational Intelligence - Volume 1: ECTA, ISBN 978-989-758-157-1, pages 95-105. DOI: 10.5220/0005599100950105


in Bibtex Style

@conference{ecta15,
author={Jeannie M. Fitzgerald and Conor Ryan},
title={For Sale or Wanted: Directed Crossover in Adjudicated Space},
booktitle={Proceedings of the 7th International Joint Conference on Computational Intelligence - Volume 1: ECTA,},
year={2015},
pages={95-105},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005599100950105},
isbn={978-989-758-157-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 7th International Joint Conference on Computational Intelligence - Volume 1: ECTA,
TI - For Sale or Wanted: Directed Crossover in Adjudicated Space
SN - 978-989-758-157-1
AU - Fitzgerald J.
AU - Ryan C.
PY - 2015
SP - 95
EP - 105
DO - 10.5220/0005599100950105