Abstract
It is proposed a way of increasing the cardinality of an alphabet used to write rules in a learning classifier system that extends the idea of relational schemata. Theoretical justifications regarding the possible reduction in the amount of rules for the solution of problems such extended alphabets (st-alphabets) imply are shown. It is shown that when expressed as bipolar neural networks, the matching process of rules over st-alphabets strongly resembles a gene expression mechanism applied to a system over {0,1,#}. In spite of the apparent drawbacks the explicit use of such relational alphabets would imply, their successful implementation in an information gain based classifier system (IGCS) is presented.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
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
Booker, L.B.: Representing Attribute-Based Concepts in a Classifier System. In: Rawlins, G.J.E. (ed.) Foundations of Genetic Algorithms, pp. 115–127. Elsevier, Amsterdam (1991)
Browne, W.N., Ioannides, C.: Investigating Scaling of an Abstracted LCS Utilising Ternary and S-Expression Alphabets. In: Proceedings of the 2007 GECCO Conference Companion on Genetic and Evolutionary Computation, pp. 2759–2764. ACM, New York (2007)
Collard, P., Escazut, C.: Relational Schemata: A Way to Improve the Expressiveness of Classifiers. In: Proceedings of the 6th International Conference on Genetic Algorithms (ICGA 1995), pp. 397–404. Morgan Kaufmann, Pittsburgh (1995)
Cordon, O., Gomide, F., Herrera, F., Hoffmann, F., Magdalena, L.: Ten Years of Genetic Fuzzy Systems: Current Framework and New Trends. Fuzzy Sets and Systems 141, 5–31 (2004)
Flach, P.A., Lavrac, N.: The Role of Feature Construction in Inductive Rule Learning. In: Proceedings of the ICML2000 workshop on Attribute-Value and Relational Learning: crossing the boundaries, pp. 1–11. Morgan Kaufmann, San Francisco (2000)
Gelly, S., Teytaud, O., Bredeche, N., Schoenauer, M.: Universal Consistency and Bloat in GP. Revue d’Intelligence Artificielle 20(6), 805–827 (2006)
Goldberg, D.E.: Genetic Algorithms in Search, Optimization and Machine Learning. Addison Wesley, Reading (1989)
Holland, J.H.: Escaping Brittleness: The Possibilities of General-Purpose Learning Algorithms Applied to Parallel Rule-Based Systems. In: Machine Learning: An Artificial Intelligence Approach, 2nd edn., pp. 593–623. Morgan Kaufmann, Los Altos (1986)
Kovacs, T., Bull, L.: Toward a Better Understanding of Rule Initialisation and Deletion. In: Proceedings of the 2007 GECCO Conference Companion on Genetic and Evolutionary Computation, pp. 2777–2780. ACM, New York (2007)
Lanzi, P.L.: Extending the Representation of Classifier Conditions Part II: From Messy Coding to S-Expressions. In: Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 1999), pp. 345–352. Morgan Kaufmann, San Francisco (1999)
Lanzi, P.L., Riolo, R.L.: A Roadmap to the Last Decade of Learning Classifier System Research (from 1989 to 1999). In: Lanzi, P.L., Stolzmann, W., Wilson, S.W. (eds.) IWLCS 1999. LNCS (LNAI), vol. 1813, pp. 33–62. Springer, Heidelberg (2000)
Lanzi, P.L., Rocca, S., Solari, S.: An Approach to Analyze the Evolution of Symbolic Conditions in Learning Classifier Systems. In: Proceedings of the 2007 GECCO Conference Companion on Genetic and Evolutionary Computation, pp. 2795–2800. ACM, New York (2007)
Lanzi, P.L., Wilson, S.W.: Using Convex Hulls to Represent Classifier Conditions. In: GECCO 2006: Proceedings of the 8th Annual Conference on Genetic and Evolutionary Computation, pp. 1481–1488. ACM, New York (2006)
Orriols-Puig, A., Casillas, J., Bernadó-Mansilla, E.: Fuzzy-UCS: Preliminary Results. In: Proceedings of the 2007 GECCO Conference Companion on Genetic and Evolutionary Computation, pp. 2871–2874. ACM, New York (2007)
Poli, R.: General Schema Theory for Genetic Programming with Subtree-Swapping Crossover. In: Miller, J., Tomassini, M., Lanzi, P.L., Ryan, C., Tetamanzi, A.G.B., Langdon, W.B. (eds.) EuroGP 2001. LNCS, vol. 2038, pp. 143–159. Springer, Heidelberg (2001)
Poli, R., McPhee, N.F.: Exact Schema Theory for GP and Variable-length GAs with Homologous Crossover. In: Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2001), pp. 104–111. Morgan Kaufmann, San Francisco (2001)
Radcliffe, N.: Forma Analysis and Random Respectful Recombination. In: Proceedings of the Fourth International Conference on Genetic Algorithms, pp. 222–229. Morgan Kaufmann, San Mateo (1991)
Schuurmans, D., Schaeffer, J.: Representational Difficulties with Classifier Systems. In: Proceedings of the 3rd International Conference on Genetic Algorithms (ICGA 1989), pp. 328–333. Morgan Kaufmann, San Francisco (1989)
Sen, S.: A Tale of Two Representations. In: Proceedings of the Seventh International Conference on Industrial and Engineering Applications of Articial Intelligence and Expert Systems, pp. 245–254. Gordon and Breach Science Publishers (1994)
Shu, L., Schaeffer, J.: VCS: Variable Classifier System. In: Proceedings of the 3rd International Conference on Genetic Algorithms (ICGA 1989), pp. 334–339. Morgan Kaufmann, San Francisco (1989)
Smith, R.E., Cribbs, H.B.: Combined Biological Paradigms: a Neural, Genetics-Based Autonomous System Strategy. Robotics and Autonomous Systems 22(1), 65–74 (1997)
Stone, C., Bull, L.: For Real! XCS with Continuous-Valued Inputs. Evolutionary Computation 11, 299–336 (2003)
Valenzuela-Rendón, M.: Two Analysis Tools to Describe the Operation of Classifier Systems. PhD Thesis, University of Alabama (1989)
Wilson, S.W.: Bid Competition and Specificity Reconsidered. Complex Systems 2(6), 705–723 (1988)
Wilson, S.W.: Generalization in the XCS Classifier System. In: Genetic Programming 1998: Proceedings of the Third Annual Conference, pp. 665–674. Morgan Kaufmann, San Francisco (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Toledo-Suárez, C.D. (2009). st-Alphabets: On the Feasibility in the Explicit Use of Extended Relational Alphabets in Classifier Systems. In: Aguirre, A.H., Borja, R.M., Garciá, C.A.R. (eds) MICAI 2009: Advances in Artificial Intelligence. MICAI 2009. Lecture Notes in Computer Science(), vol 5845. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-05258-3_41
Download citation
DOI: https://doi.org/10.1007/978-3-642-05258-3_41
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-05257-6
Online ISBN: 978-3-642-05258-3
eBook Packages: Computer ScienceComputer Science (R0)