On Using Constructivism in Neural Classifier Systems
For artificial entities to achieve true autonomy and display complex life-like behaviour they will need to exploit appropriate adaptable learning algorithms. In this sense adaptability implies flexibility guided by the environment at any given time and an open-ended ability to learn novel behaviours. This paper explores the potential of using constructivism within the neural classifier system architecture as an approach to realise such behaviour. The system uses a rule structure in which each is represented by an artificial neural network. Results are presented which suggest it is possible to allow appropriate internal rule complexity to emerge during learning and that the structure indicates underlying features of the task.
KeywordsHide Node Classifier System Connected Node Roulette Wheel Selection Hide Layer Node
Unable to display preview. Download preview PDF.
- 3.Holland, J. H. (1976) Adaptation. In R. Rosen & F. M. Snell (eds) Progress in Theoretical Biology, 4. Plenum.Google Scholar
- 4.Bull, L. & O'Hara, T. (2001a) A Neural Rule Representation for Learning Classifier Systems. UWE Learning Classifier Systems Group Technical Report 01-002. Available from http://www.cems.uwe.ac.uk/lcsg.
- 5.Sutton, R. S. & Barto, A. G. (1998) Reinforcement Learning. MIT PressGoogle Scholar
- 7.Bull, L. & Hurst, J. (2001) ZCS: Theory and Practice. UWE Learning Classifier Systems Group Technical Report 01-001. Available from http:// www.cems.uwe.ac.uk/lcsg. To appear in Evolutionary Computation.
- 8.Bull, L. & O'Hara, T. (2001b) NCS: A Simple Neural Classifier System. UWE Learning Classifier Systems Group Technical Report 01-005. Available from http://www.cems.uwe.ac.uk/lcsg.
- 9.Sutton, R. S. (1996) Generalization in Reinforcement Learning: Successful Examples using Sparse Coarse Coding. In D. S. Touretzky, M. C. Mozer & M. Hasselmo (eds) Advances in Neural Information Processing Systems: Proceedings of the 1995 Conference, MIT Press, pp1038–1044.Google Scholar
- 10.Holland, J. H. (1975) Adaptation in Natural and Artificial Systems, University of Michigan Press.Google Scholar
- 11.Harvey, I., Husbands, P. & Cliff, D. (1994) Seeing the Light: Artificial Evolution, Real Vision. In D. Cliff, P. Husbands, J-A. Meyer & S. W. Wilson (eds) From Animals to Animats 3: Proceedings of the Third International Conference on Simulation of Adaptive Behaviour. MIT Press, pp392–401.Google Scholar
- 12.Bonarini, A. (2000) An Introduction to Fuzzy Learning Classifier Systems. In P-L. Lanzi, W. Stolzmann & S. W. Wilson (eds) Learning Classifier Systems: From Foundations to Applications. Springer, pp83–106.Google Scholar
- 13.Edelman, G. (1987) Neural Darwinism: The Theory of Neuronal Group Selection. Basic Books.Google Scholar
- 16.Bull, L., Fogarty, T. & Pipe, A. (1995) Artificial Endosymbiosis. In In F. Moran, A. Mereno, J. J. Merelo & P. Chaon (eds) Advances in Artificial Life—Proceedings of the Third European Conference on Artificial Life. Springer Verlag, pp273–289.Google Scholar
- 17.Wilson, S. W. (2000) State of XCS Classifier System Research. In P-L. Lanzi, W. Stolzmann & S. W. Wilson (eds) Learning Classifier Systems: From Foundations to Applications, Springer, pp63–82.Google Scholar
- 18.Tsoukalas, L. H. & Uhrig, R. E. (1997) Fuzzy and Neural Approaches in Engineering. Wiley.Google Scholar
- 19.Furuhashi, K., Nakaoka, K., Morikawa, K. & Uchikawa, Y. (1993) Controlling Excessive Fuzziness in a Fuzzy Classifier System. In S. Forrest (ed) Proceedings of the Fifth International Conference on Genetic Algorithms. Morgan Kaufmann, pp635.Google Scholar
- 20.Bull, L. & O'Hara, T. (2002) Accuracy-based Neuro and Neuro Fuzzy Classifier Systems. UWE Learning Classifier Systems Group Technical Report 02-001. Available from http://www.cems.uwe.ac.uk/lcsg.
- 21.Bull, L. Hurst, J. & Tomlinson, A. (2000) Self-Adaptive Mutation in Classifier System Controllers. In J-A. Meyer, A. Berthoz, D. Floreano, H. Roitblatt & S. W. Wilson (eds) From Animals to Animats 6—The Sixth International Conference on the Simulation of Adaptive Behaviour, MIT Press.Google Scholar
- 22.Hurst, J. & Bull, L. (2001) A Self-Adaptive Classifier System. In P-L. Lanzi, W. Stolzmann & S. W. Wilson (eds) Advances in Learning Classifier Systems: Proceedings of the Third International Workshop on Learning Classifier Systems. Springer, pp70–79.Google Scholar