Use of a Connection-Selection Scheme in Neural XCSF

  • Gerard David Howard
  • Larry Bull
  • Pier-Luca Lanzi
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6471)

Abstract

XCSF is a modern form of Learning Classifier System (LCS) that has proven successful in a number of problem domains. In this paper we exploit the modular nature of XCSF to include a number of extensions, namely a neural classifier representation, self-adaptive mutation rates and neural constructivism. It is shown that, via constructivism, appropriate internal rule complexity emerges during learning. It is also shown that self-adaptation allows this rule complexity to emerge at a rate controlled by the learner. We evaluate this system on both discrete and continuous-valued maze environments. The main contribution of this work is the implementation of a feature selection derivative (termed connection selection), which is applied to modify network connectivity patterns. We evaluate the effect of connection selection, in terms of both solution size and system performance, on both discrete and continuous-valued environments.

Keywords

feature selection neural network self-adaptation 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Quartz, S.R., Sejnowski, T.J.: The Neural Basis of Cognitive Development: A Constructionist Manifesto. Behavioural and Brain Sciences 20(4), 537–596 (1997)Google Scholar
  2. 2.
    Edelman, G.: Neural Darwinism: The Theory of Neuronal Group Selection. Basic Books, New York (1987)Google Scholar
  3. 3.
    Holland, J.H.: Adaptation. In: Rosen, R., Snell, F.M. (eds.) Progress in Theoretical Biology, vol. 4, pp. 263–293. Academic Press, New York (1976)CrossRefGoogle Scholar
  4. 4.
    Holland, J.H.: Adaptation in Natural and Artificial Systems. University of Michigan Press, Ann Arbor (1975)Google Scholar
  5. 5.
    Bull, L.: On Using Constructivism in Neural Classifier Systems. In: Guervós, J.J.M., Adamidis, P.A., Beyer, H.-G., Fernández-Villacañas, J.-L., Schwefel, H.-P. (eds.) PPSN 2002. LNCS, vol. 2439, pp. 558–567. Springer, Heidelberg (2002)Google Scholar
  6. 6.
    Wilson, S.W.: Function Approximation with a Classifier System. In: Spector, L.D., Wu, G.E.A., Langdon, W.B., Voight, H.M., Gen, M. (eds.) Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2001), pp. 974–981. Morgan Kaufmann, San Francisco (2001)Google Scholar
  7. 7.
    Rumelhart, D.E., McClelland, J.L.: Parallel Distributed Processing. MIT Press, Cambridge (1986)Google Scholar
  8. 8.
    Bull, L., Hurst, J.: A Neural Learning Classifier System with Self-Adaptive Constructivism. In: IEEE Congress on Evolutionary Computation. IEEE Press, Los Alamitos (2003)Google Scholar
  9. 9.
    Buhmann, M.D.: Radial Basis Functions: Theory and Implementations. Cambridge University, Cambridge (2003)CrossRefMATHGoogle Scholar
  10. 10.
    Bull, L., O’Hara, T.: Accuracy-based Neuro and Neuro-Fuzzy Classifier Systems. In: Langdon, W.B., Cantu-Paz, E., Mathias, K., Roy, R., Davis, D., Poli, R., Balakrishnan, K., Hanavar, V., Rudolph, G., Wegener, J., Bull, L., Potter, M.A., Schultz, A.C., Miller, J.F., Burke, E., Jonoska, N. (eds.) GECCO 2002: Proceedings of the Genetic and Evolutionary Computation Conference, pp. 905–911. Morgan Kaufmann, San Francisco (2002)Google Scholar
  11. 11.
    Hurst, J., Bull, L.: A Neural Learning Classifier System with Self-Adaptive Constructivism for Mobile Robot Control. Artificial Life 12(3), 353–380 (2006)CrossRefGoogle Scholar
  12. 12.
    Giani, A., Baiardi, F., Starita, A.: PANIC: A Parallel Evolutionary Rule Based System. In: Proceedings of the Fourth Annual Conference on Evolutionary Programming, EP 1995 (1995)Google Scholar
  13. 13.
    O’Hara, T., Bull, L.: Prediction Calculation in Accuracy-based Neural Learning Classifier Systems. Tech report UWELCSG04-004 (2004)Google Scholar
  14. 14.
    Lanzi, P.L., Loiacono, D.: XCSF with Neural Prediction. In: IEEE Congress on Evolutionary Computation, CEC 2006, pp. 2270–2276 (2006)Google Scholar
  15. 15.
    Dam, H.H., Abbass, H.A., Lokan, C., Yao, X.: Neural-Based Learning Classifier Systems. IEEE Trans. on Knowl. and Data Eng. 20(1), 26–39 (2008)Google Scholar
  16. 16.
    O’Hara, T., Bull, L.: Building Anticipations in an Accuracy-based Learning Classifier System by use of an Artificial Neural Network. In: Proceedings of the IEEE Congress on Evolutionary Computation, pp. 2046–2052. IEEE Press, Los Alamitos (2005)Google Scholar
  17. 17.
    Pérez-Uribe, A., Sanchez, E.: FPGA Implementation of an Adaptable-Size Neural Network. In: Vorbrüggen, J.C., von Seelen, W., Sendhoff, B. (eds.) ICANN 1996. LNCS, vol. 1112, pp. 383–388. Springer, Heidelberg (1996)CrossRefGoogle Scholar
  18. 18.
    Watkins, C.J.C.H.: Learning with Delayed Rewards. PhD thesis, Psychology Department, University of Cambridge, England (1989)Google Scholar
  19. 19.
    Wilson, S.W.: ZCS: A Zeroth-level Classifier System. Evolutionary Computation 2(1), 1–18 (1994)MathSciNetCrossRefGoogle Scholar
  20. 20.
    Bull, L., Hurst, J., Tomlinson, A.: Self-Adaptive Mutation in Classifier System Controllers. In: Meyer, J.-A., Berthoz, A., Floreano, D., Roitblatt, H., Wilson, S.W. (eds.) From Animals to Animats 6 – The Sixth International Conference on the Simulation of Adaptive Behaviour. MIT Press, Cambridge (2000)Google Scholar
  21. 21.
    Harvey, I., Husbands, P., Cliff, D.: Seeing the Light: Artificial Evolution, Real Vision. In: Cliff, D., Husbands, P., Meyer, J.-A., Wilson, S.W. (eds.) From Animals to Animats 3: Proceedings of the Third International Conference on Simulation of Adaptive Behaviour, pp. 392–401. MIT Press, Cambridge (1994)Google Scholar
  22. 22.
    Hutt, B., Warwick, K.: Synapsing Variable-Length Crossover: Meaningful Crossover for Variable-Length Genomes. IEEE Transactions on Evolutionary Computation 11(1), 118–131 (2007)CrossRefGoogle Scholar
  23. 23.
    Rocha, M., Cortez, P., Neves, J.: Evolutionary Neural Network Learning. In: Pires, F.M., Abreu, S.P. (eds.) EPIA 2003. LNCS (LNAI), vol. 2902, pp. 24–28. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  24. 24.
    Schaffer, J.D., Whitley, D., Eshelman, L.J.: Combinations of genetic algorithms and neural networks: A survey of the state of the art. In: Whitley, D., Schaffer, J. (eds.) Proceedings of the International Workshop on Combinations of Genetic Algorithms and Neural Networks (COGANN 1992), pp. 1–37. IEEE Press, Piscataway (1992)Google Scholar
  25. 25.
    Stanley, K.O., Miikkulainen, R.: Evolving Neural Networks Through Augmenting Topologies. Evolutionary Computation 10(2), 99–127 (2002)CrossRefGoogle Scholar
  26. 26.
    Stanley, K.O., Miikkulainen, R.: Competitive Coevolution through Evolutionary Complexification. Journal of Artificial Intelligence Research 2004(21), 63–100 (2002)Google Scholar
  27. 27.
    Basheer, A., Hajmeer, M.: Artificial neural networks: fundamentals, computing, design, and application. Journal of Microbiological Methods 43(1) (2000)Google Scholar
  28. 28.
    Belue, L.M., Bauer Jr., K.W.: Determining input features for multilayer perceptrons. Neurocomputing 7, 111–121 (1995)CrossRefGoogle Scholar
  29. 29.
    Basak, J., Mitra, S.: Feature selection using radial basis function networks. Neural Comput. Appl. 8, 297–302 (1999)CrossRefGoogle Scholar
  30. 30.
    Whiteson, S., Stone, P., Stanley, K.O., Miikkulainen, R., Kohl, N.: Automatic feature selection in neuroevolution. In: Proceedings of the 2005 Conference on Genetic and Evolutionary Computation, Washington DC, USA, June 25-29 (2005)Google Scholar
  31. 31.
    Tan, M., Hartley, M., Bister, M., Deklerck, R.: Automated feature selection in neuroevolution. Evolutionary Intelligence 1(4), 271–292 (2009)CrossRefGoogle Scholar
  32. 32.
    Rocha, M., Cortez, P., Neves, J.: Evolution of neural networks for classification and regression. Neurocomput. 70(16-18), 2809–2816 (2007)CrossRefGoogle Scholar
  33. 33.
    Howard, D., Bull, L., Lanzi, P.-L.: Self-Adaptive Constructivism in Neural XCS and XCSF. In: Keijzer, M., et al. (eds.) GECCO 2008: Proceedings of the Genetic and Evolutionary Computation Conference, ACM Press, New York (2008)Google Scholar
  34. 34.
    Lanzi, P.L.: An Analysis of Generalization in the XCS Classifier System. Evolutionary Computation 7(2), 125–149 (1999)CrossRefGoogle Scholar
  35. 35.
    Boyan, J.A., Moore, A.W.: Generalization in reinforcement learning: Safely approximating the value function. In: Tesauro, G., Touretzky, D.S., Leen, T.K. (eds.) Advances in Neural Information Processing Systems 7, pp. 369–376. The MIT Press, Cambridge (1995)Google Scholar
  36. 36.
    Schlessinger, E., Bentley, P.J., Lotto, R.B.: Analysing the Evolvability of Neural Network Agents through Structural Mutations. In: Capcarrère, M.S., Freitas, A.A., Bentley, P.J., Johnson, C.G., Timmis, J. (eds.) ECAL 2005. LNCS (LNAI), vol. 3630, pp. 312–321. Springer, Heidelberg (2005)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Gerard David Howard
    • 1
  • Larry Bull
    • 1
  • Pier-Luca Lanzi
    • 2
  1. 1.Department of Computer ScienceUniversity of the West of EnglandBristolUK
  2. 2.Dipartimento di Elettronica e InformazionePolitecnico di MilanoMilanItaly

Personalised recommendations