Abstract
Learning Classifier Systems traditionally use a binary string rule representation with wildcards added to allow for generalizations over the problem encoding. We have presented a neural network-based representation to aid their use in complex problem domains. Here each rule’s condition and action are represented by a small neural network, evolved through the actions of the genetic algorithm. In this paper we present results from the use of backpropagation in conjunction with the genetic algorithm within XCS. After describing the minor changes required to the standard production system functionality, performance is presented from using backpropagation in a number of ways within the system. Results from both continuous and discrete action tasks indicate that significant decreases in the time taken to reach optimal behaviour can be obtained from the incorporation of the local learning algorithm.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Ahluwalia, M., Bull, L.: A Genetic Programming Classifier System. In: Banzhaf, W., et al. (eds.) Proceedings of the Genetic and Evolutionary Computation Conference - GECCO-99, pp. 11–18. Morgan Kaufmann, San Francisco (1999)
Belew, R.K., McInerney, J., Schraudolph, N.N.: Evolving Networks: Using the Genetic Algorithm with Connectionist Learning. In: Langton, C.G., et al. (eds.) Artificial Life II, pp. 511–548. Addison-Wesley, Reading (1991)
Bonarini, A.: An Introduction to Learning Fuzzy Classifier Systems. In: Lanzi, P.-L., Stolzmann, W., Wilson, S.W. (eds.) Learning Classifier Systems: From Foundations to Applications, pp. 83–106. Springer, Heidelberg (2000)
Bull, L., O’Hara, T.: Accuracy-based Neuro and Neuro-Fuzzy Classifier Systems. In: Banzhaf, W., et al. (eds.) Proceedings of the Genetic and Evolutionary Computation Conference - GECCO-2003, pp. 11–18. Morgan Kaufmann, San Francisco (2002)
Butz, M., Wilson, S.W.: An Algorithmic Description of XCS. In: Lanzi, P.L., Stolzmann, W., Wilson, S.W. (eds.) IWLCS 2000. LNCS (LNAI), vol. 1996, pp. 253–272. Springer, Heidelberg (2001)
Davis, L.: Mapping Neural Networks into Classifier Systems. In: Schaffer, J.D. (ed.) Proceedings of the Third International Conference on Genetic Algorithms, pp. 375–378. Morgan Kaufmann, San Francisco (1989)
Dorigo, M., Bersini, H.: A comparison of Q-learning and classifier systems. In: Cliff, D., et al. (eds.) From Animals to Animats 3: Proceedings of the Third International Conference on Simulation of Adaptive Behaviour, pp. 248–255 (1994)
Farmer, D.: A Rosetta Stone for Connectionism. Physica D 42, 153–187 (1989)
Hinton, G.E., Nowlan, S.J.: How learning can guide evolution. In: Complex Systems, pp. 495-502 (June 1987)
Holland, J.H.: Adaptation in Natural and Artificial Systems. University of Michigan Press (1975)
Holland, J.H.: Escaping Brittleness. In: Michalski, R.S., Carnoell, J.G., Mitchell, T.M. (eds.) Machine Learning: An Artificial Intelligence Approach 2, pp. 48–78. Morgan Kaufmann, San Francisco (1986)
Hornick, K., Stinchombe, M., White, H.: Multiayer Feedforward Networks are Universal Approximators. Neural Networks 2(5), 359–366 (1989)
Lanzi, P.-L.: A Model of the Environment to Avoid Local Learning. Technical Report N. 97. Politecnico di Milano (1997)
Lanzi, P.-L.: Extending the Representation of Classifier Conditions Part I: From Binary to Messy Coding. In: Banzhaf, W., et al. (eds.) Proceedings of the Genetic and Evolutionary Computation Conference - GECCO-99, pp. 11–18. Morgan Kaufmann, San Francisco (1999a)
Lanzi, P.-L.: Extending the Representation of Classifier Conditions Part II: From Messy Coding to S-Expressions. In: Banzhaf, W., et al. (eds.) Proceedings of the Genetic and Evolutionary Computation Conference - GECCO-99, pp. 11–18. Morgan Kaufmann, San Francisco (1999b)
Lee, S.W.: Off-line Recognition of Totally Unconstrained Handwritten Numerals using Multilayer Cluster Neural Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence 18(6), 648–652 (1996)
Moriarty, D.E., Miikulainen, R.: Forming Neural Networks Through Efficient and Adaptive Coevolution. Evolutionary Computation 5(2), 373–399 (1997)
Omatu, S., Yoshioka, M.: Self-tuning Neuro-IPD Control and Applications. In: Proceedings of the 1997 IEEE Conference on Man, Systems and Cybernetics, pp. 1985–1989. IEEE Computer Society Press, Los Alamitos (1997)
Rumelhart, D.E., McClelland, J.L.: Explorations in Parallel Distributed Processing. MIT Press, Cambridge (1986)
Schuurmans, D., Schaeffer, J.: Representational Difficulties with Classifier Systems. In: Schaffer, J.D. (ed.) Proceedings of the Third International Conference on Genetic Algorithms, pp. 328–333. Morgan Kaufmann, San Francisco (1989)
Smith, R.E., Cribbs, H.B.: Is a Learning Classifier System a Type of Neural Network? Evolutionary Computation 2(1), 19–36 (1994)
Valenzuela-Rendon, M.: The Fuzzy Classifier System: a Classifier System for Continuously Varying Variables. In: Booker, L., Belew, R. (eds.) Proceedings of the Fourth International Conference on Genetic Algorithms, pp. 346–353. Morgan Kaufmann, San Francisco (1991)
Whitley, D.W., Scott-Gordon, V., Mathias, K.: Lamarckian Evolution, the Baldwin Effect and Functional Optimisation. In: Davidor, Y., Männer, R., Schwefel, H.-P. (eds.) PPSN 1994. LNCS, vol. 866, pp. 6–15. Springer, Heidelberg (1994)
Wilson, S.W.: Classifier fitness based on accuracy. Evolutionary Computation 3(2), 149–175 (1995)
Wilson, S.W.: Get Real! XCS with Continuous-Valued Inputs. In: Lanzi, P.-L., Stolzmann, W., Wilson, S.W. (eds.) Learning Classifier Systems: From Foundations to Applications, pp. 209–222. Springer, Heidelberg (2000)
Wilson, S.W.: Mining oblique data with XCS. In: Lanzi, P.L., Stolzmann, W., Wilson, S.W. (eds.) IWLCS 2000. LNCS (LNAI), vol. 1996, Springer, Heidelberg (2001a)
Wilson, S.W.: Function Approximation with a Classifier System. In: Spector, L., et al. (eds.) Proceedings of the Genetic and Evolutionary Computation Conference - GECCO-2001, pp. 974–984. Morgan Kaufmann, San Francisco (2001b)
Yao, X.: Evolving Artificial Neural Networks. Proceedings of the IEEE 87(9), 1423–1447 (1999)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer Berlin Heidelberg
About this paper
Cite this paper
O’Hara, T., Bull, L. (2007). Backpropagation in Accuracy-Based Neural Learning Classifier Systems. In: Kovacs, T., Llorà, X., Takadama, K., Lanzi, P.L., Stolzmann, W., Wilson, S.W. (eds) Learning Classifier Systems. IWLCS IWLCS IWLCS 2003 2004 2005. Lecture Notes in Computer Science(), vol 4399. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-71231-2_3
Download citation
DOI: https://doi.org/10.1007/978-3-540-71231-2_3
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-71230-5
Online ISBN: 978-3-540-71231-2
eBook Packages: Computer ScienceComputer Science (R0)