Improving generalization in the XCSF classifier system using linear least-squares

ABSTRACT

XCSF is an extension of XCS in which classifier prediction is computed as a linear combination of classifier inputs and a weight vector associated to each classifier. XCSF can adjust the weight vector of classifiers to evolve accurate piecewise linear approximations of functions. The Widrow-Hoff rule, used to update the weight vectors, prevents (when some conditions hold) XCSF from exploiting the expected piece-wise linear approximation. In this paper we replace the Widrow-Hoff rule with linear least-squares and we show that with this improvement XCSF can fully exploit its generalization capabilities.

REFERENCES

• 1: Justin A. Boyan, Least-Squares Temporal Difference Learning, Proceedings of the Sixteenth International Conference on Machine Learning, p.49-56, June 27-30, 1999
• 2: Steven J. Bradtke , Andrew G. Barto, Linear least-squares algorithms for temporal difference learning, Machine Learning, v.22 n.1-3, p.33-57, Jan./Feb./March 1996 [doi>10.1007/BF00114723]
• 3: S. A. Glantz and B. K. Slinker. Primer of Applied Regression & Analysis of Variance. McGraw Hill, 2001. second edition.
• 4: S Haykin, Adaptive filter theory, Prentice-Hall, Inc., Upper Saddle River, NJ, 1986
• 5: J. Koza. Genetic Programming. MIT Press, 1992.
• 6: P. L. Lanzi. The xcs library. http://xcslib.sourceforge.net, 2002.
• 7: P. L. Lanzi, D. Loiacono, S. W. Wilson, and D. E. Goldberg. Generalization in the xcsf classifier system: Analysis, improvement, and extension. Technical report, Dipartimento di Elettronica e Informazione - Politecnico di Milano, 2005.
• 8: William H. Press , William T. Vetterling , Saul A. Teukolsky , Brian P. Flannery, Numerical Recipes in C++: the art of scientific computing, 2001
• 9: Stewart W. Wilson, Mining Oblique Data with XCS, Revised Papers from the Third International Workshop on Advances in Learning Classifier Systems, p.158-176, September 15-16, 2000
• 10: Stewart W. Wilson, Classifiers that approximate functions, Natural Computing: an international journal, v.1 n.2-3, p.211-234, June 2002 [doi>10.1023/A:1016535925043]
• 11: I. Zelinka. Analytic programming by means of soma algorithm. In Proceedings of the 8th International Conference on Soft Computing, Mendel'02, pages 93--101, Brno, Czech Republic, 2002.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.6 Learning

General Terms:
Algorithms, Experimentation, Theory

Keywords:
XCSF, function approximation, generalization, learning classifier systems, least-squares