Abstract
Bloat control and generalization pressure are very important issues in the design of Pittsburgh Approach Learning Classifier Systems (LCS), in order to achieve simple and accurate solutions in a reasonable time. In this paper we propose a method to achieve these objectives based on the Minimum Description Length (MDL) principle. This principle is a metric which combines in a smart way the accuracy and the complexity of a theory (rule set , instance set, etc.). An extensive comparison with our previous generalization pressure method across several domains and using two knowledge representations has been done. The test show that the MDL based size control method is a good and robust choice.
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
Holland, J.H.: Adaptation in Natural and Artificial Systems. University of Michigan Press, Ann Arbor (1975)
Smith, S.F.: Flexible learning of problem solving heuristics through adaptive search. In: Proceedings of the Eighth International Joint Conference on Artificial Intelligence, Los Altos, CA, pp. 421–425. Morgan Kaufmann, San Francisco (1983)
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. Volume II, pp. 593–623 (1986)
DeJong, K.A., Spears, W.M.: Learning concept classification rules using genetic algorithms. Proceedings of the International Joint Conference on Artificial Intelligence, 651–656 (1991)
Wilson, S.W.: Classifier fitness based on accuracy. Evolutionary Computation 3, 149–175 (1995)
Langdon, W.B.: Fitness causes bloat in variable size representations. Technical Report CSRP-97-14, University of Birmingham, School of Computer Science, Position paper at the Workshop on Evolutionary Computation with Variable Size Representation at ICGA-97 (1997)
Mitchell, T.M.: Machine Learning. McGraw-Hill, New York (1997)
Bacardit, J., Garrell, J.M.: Métodos de generalización para sistemas clasificadores de Pittsburgh. In: Proceedings of the “Primer Congreso Español de Algoritmos Evolutivos y Bioinspirados (AEB’02)”, pp. 486–493 (2002)
Rissanen, J.: Modeling by shortest data description. Automatica 14, 465–471 (1978)
Pfahringer, B.: Practical uses of the minimum description length principle in inductive learning (1995)
Bacardit, J., Garrell, J.M.: Evolving multiple discretizations with adaptive intervals for a pittsburgh rule-based learning classifier system. In: Proceedings of the Genetic and Evolutionary Computation Conference - GECCO2003, Springer, Heidelberg (2003)
Gao, Q., Li, M., Viányi, P.: Applying mdl to learn best model granularity. Artificial Intelligence 121, 1–29 (2000)
Iba, H., de Garis, H., Sato, T.: Genetic programming using a minimum description length principle. In: Kinnear Jr., K.E. (ed.) Advances in Genetic Programming, pp. 265–284. MIT Press, Cambridge (1994)
Quinlan, J.R.: C4.5: Programs for Machine Learning. Morgan Kaufmann, San Francisco (1993)
Luke, S., Panait, L.: Lexicographic parsimony pressure. In: GECCO 2002: Proceedings of the Genetic and Evolutionary Computation Conference, pp. 829–836 (2002)
Llorà, X., et al.: Accuracy, Parsimony, and Generality in Evolutionary Learning System a Multiobjective Selection. In: Lanzi, P.L., Stolzmann, W., Wilson, S.W. (eds.) IWLCS 2003. LNCS (LNAI), vol. 2661, Springer, Heidelberg (2003)
Bernadó, E., Garrell, J.M.: Multiobjective learning in a genetic classifier system (MOLeCS). Butlletí de l’Associació Catalana l’Intel.ligència Artificial 22, 102–111 (2000)
Bacardit, J.: Pittsburgh Genetics-Based Machine Learning in the Data Mining era: Representations, generalization, and run-time. PhD thesis, Ramon Llull University, Barcelona, Catalonia, Spain (2004)
Rivest, R.L.: Learning decision lists. Machine Learning 2(3), 229–246 (1987), citeseer.nj.nec.com/rivest87learning.html
Wolpert, D.H., Macready, W.G.: No free lunch theorems for search. Technical Report SFI-TR-95-02-010, Santa Fe, NM (1995)
Brodley, C.: Addressing the selective superiority problem: Automatic algorithm /model class selection (1993)
Goldberg, D.E., Deb, K.: A comparative analysis of selection schemes used in genetic algorithms. In: Foundations of Genetic Algorithms, pp. 69–93. Morgan Kaufmann, San Francisco (1991)
Llorà, X., Garrell, J.M.: Knowledge-independent data mining with fine-grained parallel evolutionary algorithms. In: Proceedings of the Third Genetic and Evolutionary Computation Conference, pp. 461–468. Morgan Kaufmann, San Francisco (2001)
Blake, C., Keogh, E., Merz, C.: Uci repository of machine learning databases (1998), http://www.ics.uci.edu/mlearn/MLRepository.html
Martínez Marroquín, E., Vos, C., et al.: Morphological analysis of mammary biopsy images. In: Proceedings of the IEEE International Conference on Image Processing, pp. 943–947. IEEE Computer Society Press, Los Alamitos (1996)
Martí, J., Cufí, X., Regincós, J., et al.: Shape-based feature selection for microcalcification evaluation. In: Imaging Conference on Image Processing, 3338, pp. 1215–1224 (1998)
Golobardes, E., et al.: Genetic classifier system as a heuristic weighting method for a case-based classifier system. Butlletí de l’Associació Catalana d’Intel.ligència Artificial 22, 132–141 (2000)
Kohavi, R.: A study of cross-validation and bootstrap for accuracy estimation and model selection. In: IJCAI, pp. 1137–1145 (1995), citeseer.nj.nec.com/kohavi95study.html
Witten, I.H., Frank, E.: Data Mining: practical machine learning tools and techniques with java implementations. Morgan Kaufmann, San Francisco (2000)
Aha, D.W., Kibler, D.F., Albert, M.K.: Instance-based learning algorithms. Machine Learning 6(1), 37–66 (1991)
Bernadó, E., Garrell, J.M.: Accuracy-based learning classifier systems: Models, analysis and applications to classification tasks. Special Issue of the Evolutionary Computation Journal on Learning Classifier Systems (in press, 2003)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer Berlin Heidelberg
About this paper
Cite this paper
Bacardit, J., Garrell, J.M. (2007). Bloat Control and Generalization Pressure Using the Minimum Description Length Principle for a Pittsburgh Approach Learning Classifier System. 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_5
Download citation
DOI: https://doi.org/10.1007/978-3-540-71231-2_5
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)