Advertisement

On the Life-Long Learning Capabilities of a NELLI*: A Hyper-Heuristic Optimisation System

  • Emma Hart
  • Kevin Sim
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8672)

Abstract

Real-world applications of optimisation techniques place more importance on finding approaches that result in acceptable quality solutions in a short time-frame and can provide robust solutions, capable of being modified in response to changes in the environment than seeking elusive global optima. We demonstrate that a hyper-heuristic approach NELLI* that takes inspiration from artifical immune systems is capable of life-long learning in an environment where problems are presented in a continuous stream and change over time. Experiments using 1370 bin-packing problems show excellent performance on unseen problems and that the system maintains memory, enabling it to exploit previously learnt heuristics to solve new problems with similar characteristics to ones solved in the past.

Keywords

Hyper-heuristics artificial immune systems 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Burke, E.K., Gendreau, M., Hyde, M., Kendall, G., Ochoa, G., Ozcan, E., Qu, R.: Hyper-heuristics: A survey of the state of the art. J. Oper. Res. Soc. (July 2013)Google Scholar
  2. 2.
    Burke, E.K., Hyde, M.R., Kendall, G., Woodward, J.: Automating the packing heuristic design process with genetic programming. Evol. Comput. 20(1), 63–89 (2012)CrossRefGoogle Scholar
  3. 3.
    Falkenauer, E.: A hybrid grouping genetic algorithm for bin packing. Journal of Heuristics 2, 5–30 (1996)CrossRefGoogle Scholar
  4. 4.
    Garrido, P., Riff, M.C.: Collaboration between hyperheuristics to solve strip-packing problems. In: Melin, P., Castillo, O., Aguilar, L.T., Kacprzyk, J., Pedrycz, W. (eds.) IFSA 2007. LNCS (LNAI), vol. 4529, pp. 698–707. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  5. 5.
    Gent, I.P.: Heuristic solution of open bin packing problems. Journal of Heuristics 3(4), 299–304 (1998)CrossRefzbMATHGoogle Scholar
  6. 6.
    Jackson, D.: Single node genetic programming on problems with side effects. In: Coello, C.A.C., Cutello, V., Deb, K., Forrest, S., Nicosia, G., Pavone, M. (eds.) PPSN 2012, Part I. LNCS, vol. 7491, pp. 327–336. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  7. 7.
    Maturana, J., Lardeux, F., Saubion, F.: Autonomous operator management for evolutionary algorithms. Journal of Heuristics 16, 881–909 (2010)CrossRefzbMATHGoogle Scholar
  8. 8.
    Michalewicz, Z.: Ubiquity symposium: Evolutionary computation and the processes of life: The emperor is naked: Evolutionary algorithms for real-world applications. Ubiquity 2012(November), 3:1–3:13 (2012)Google Scholar
  9. 9.
    Remde, S., Cowling, P., Dahal, K., Colledge, N., Selensky, E.: An empirical study of hyperheuristics for managing very large sets of low level heuristics. J. Oper. Res. Soc. 63(3), 392–405 (2012)CrossRefGoogle Scholar
  10. 10.
    Ross, P., Schulenburg, S., Marin-Blazquez, J.G., Hart, E.: Hyper-heuristics: Learning to combine simple heuristics in bin-packing problems. In: Proceedings of the Genetic and Evolutionary Computation Conference, GECCO 2002, pp. 942–948 (2002)Google Scholar
  11. 11.
    Scholl, A., Klein, R., Jürgens, C.: Bison: a fast hybrid procedure for exactly solving the one-dimensional bin packing problem. Comput. Oper. Res. 24(7), 627–645 (1997)CrossRefzbMATHGoogle Scholar
  12. 12.
    Silver, D., Yang, Q., Li, L.: Lifelong machine learning systems: Beyond learning algorithms. AAAI Spring Symposium Series (2013)Google Scholar
  13. 13.
    Sim, K., Hart, E., Paechter, B.: A lifelong learning hyper-heuristic method for bin packing. Evolutionary Computation Journal (in press, January 2014)Google Scholar
  14. 14.
    Sim, K., Hart, E.: Generating single and multiple cooperative heuristics for the one dimensional bin packing problem using a single node genetic programming island model. In: Blum, C. (ed.) GECCO 2013: Proceeding of the Fifteenth Annual Conference on Genetic and Evolutionary Computation Conference, ACM, New York (2013)Google Scholar
  15. 15.
    Sim, K., Hart, E.: An improved immune inspired hyper-heuristic for combinatorial optimisation problems. In: GECCO 2014: Proceeding of the Sixteenth Annual Conference on Genetic and Evolutionary Computation Conference (in press, 2014)Google Scholar
  16. 16.
    Sim, K., Hart, E., Paechter, B.: A hyper-heuristic classifier for one dimensional bin packing problems: Improving classification accuracy by attribute evolution. In: Coello, C.A.C., Cutello, V., Deb, K., Forrest, S., Nicosia, G., Pavone, M. (eds.) PPSN 2012, Part II. LNCS, vol. 7492, pp. 348–357. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  17. 17.
    Sim, K., Hart, E., Paechter, B.: Learning to solve bin packing problems with an immune inspired hyper-heuristic. In: Advances in Artificial Life, ECAL 2013: Proceedings of the Twelfth European Conference on the Synthesis and Simulation of Living Systems, pp. 856–863. MIT Press (2013)Google Scholar
  18. 18.
    Thabtah, F., Cowling, P.: Mining the data from a hyperheuristic approach using associative classification. Expert Systems with Applications 34(2), 1093–1101 (2008)CrossRefGoogle Scholar
  19. 19.
    Trojanowski, K., Wierzchon, S.T.: Immune-based algorithms for dynamic optimization. Information Sciences 179(10), 1495–1515 (2009)CrossRefGoogle Scholar
  20. 20.
    Whitbrook, A.M., Aickelin, U., Garibaldi, J.M.: Two-timescale learning using idiotypic behaviour mediation for a navigating mobile robot. Appl. Soft Comput. 10(3), 876–887 (2010)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Emma Hart
    • 1
  • Kevin Sim
    • 1
  1. 1.Institute for Informatics and Digital InnovationEdinburgh Napier UniversityEdinburghUK

Personalised recommendations