Abstract
Genetic algorithms are employed in classifier systems in order to discover new classifiers. The paper formalises this rule discovery or learning problem for classifier systems and uses methods of computational complexity theory to analyse its inherent difficulty. It is proved that two distinct learning problems are NP-complete, i.e. not likely to be solvable efficiently. The practical relevance of these theoretical results is briefly discussed.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
J.L. Balcàzar, J. Díaz, and J. Gabarró. Structural Complexity I. EATCS, Monographs on Theoretical Computer Science. Springer-Verlag, Berlin, 1st edition, 1988.
L.B. Booker, D.E. Goldberg, and J.H. Holland. Classifier Systems and Genetic Algorithms. Artificial Intelligence, 40:235–282, 1989.
M.R. Garey and D.S. Johnson. Computers and Intractability. Freeman and Company, New York, 1979.
D.E. Goldberg. Genetic Algorithmis in Search, Optimizations & Machine Learning. Addison-Wesley Publishing Company, Reading, Massachusetts.
A. Gibbons and W. Rytter. Efficient Parallel Algorithms. Cambridge University Press, Cambridge, UK, 1988.
W.E. Hart and R.K. Belew. Optimizing an Arbitrary Function is Hard for the Genetic Algorithm. In Proceedings of the fourth International Conference on Genetic Algorithms, R.K. Belew, L.B. Booker (eds.), Morgan Kaufmann Publishers, San Mateo, CA, pp. 318–323, 1991
U. Hartmann. Computational Complexity of Neural Networks and Classifier Systems. Diplomarbeit, University of Dortmund, Germany, July 1992.
U. Hartmann. Efficient Parallel Learning in Classifier Systems. In Proceedings of the International Conference on Neural Networks and Genetic Algortihms, Insbruck, R.F. Albrecht, C.R. Reeves, N.C. Steele (eds.), Springer-Verlag, Wien, pp. 515–521, 1993.
J.H. Holland. Adaptation. In R. Rosen and F.M. Snell, editors, Progress in Theoretical Biology IV, pages 263–293. Academic Press, New York, 1976.
S. Judd. Neural Network Design and the Complexity of Learning. Neural Network Modeling and Connectionism. The MIT Press, Cambridge, MA, 1990.
G.E. Liepins and L.A. Wang. Classifier System Learning Boolean Concepts. In Proceedings of the fourth International Conference on Genetic Algorithms, R.K. Belew, L.B. Booker (eds.), Morgan Kaufmann Publishers, San Mateo, CA, pp. 318–323, 1991
L. Pitt and L. Valiant. Computational Limitations on Learning from Examples. Journal of the Association of Computing Machinery, 35(4):965–984, October 1988.
H. Ros. Some Results on Boolean Concept Learning by Genetic Algorithms. In Proceedings of the third International Conference on Genetic Algorithms, J.D. Schaffer (ed.), Morgan Kaufmann Publishers, San Mateo, CA, pp. 28–33, 1989
L.G. Valiant. A Theory of the Learnable. Communications of the ACM, 27(11):1134–1142, November 1984.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1994 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hartmann, U. (1994). On the complexity of learning in classifier systems. In: Davidor, Y., Schwefel, HP., Männer, R. (eds) Parallel Problem Solving from Nature — PPSN III. PPSN 1994. Lecture Notes in Computer Science, vol 866. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-58484-6_272
Download citation
DOI: https://doi.org/10.1007/3-540-58484-6_272
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-58484-1
Online ISBN: 978-3-540-49001-2
eBook Packages: Springer Book Archive