Advertisement

An Introduction to Learning Fuzzy Classifier Systems

  • Andrea Bonarini
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1813)

Abstract

We present a class of Learning Classifier Systems that learn fuzzy rule-based models, instead of interval-based or Boolean models. We discuss some motivations to consider Learning Fuzzy Classifier Systems (LFCS) as a promising approach to learn mappings from real-valued input to real-valued output, basing on data interpretation implemented by fuzzy sets. We describe some of the approaches explicitly or implicitly referring to this research area, presented in literature since the beginning of the last decade. We also show how the general LFCS model can be considered as a framework for a wide range of systems, each implementing in a different way the modules composing the basic architecture. We also mention some of the applications of LFCS presented in literature, which show the potentialities of this type of systems. Finally, we introduce a general methodology to extend reinforcement distribution algorithms usually not designed to learn fuzzy models. This opens new application possibilities.

Keywords

Genetic Algorithm Membership Function Mobile Robot Fuzzy System Fuzzy Rule 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    H. Berenji. Fuzzy q-learning: a new approach for fuzzy dynamic programming. In Proceedings Third IEEE International Conference on Fuzzy Systems, pages 486–491, Piscataway, NJ, 1994. IEEE Computer Press.Google Scholar
  2. [2]
    A. Bonarini. ELF: Learning incomplete fuzzy rule sets for an autonomous robot. In H.-J. Zimmermann, editor, First European Congress on Fuzzy and Intelligent Technologies — EUFIT’93, volume 1, pages 69–75, Aachen, 1993. Verlag der Augustinus Buchhandlung.Google Scholar
  3. [3]
    A. Bonarini. Delayed reinforcement, fuzzy Q-learning and fuzzy logic controllers. In J.L. Verdegay, editors. Genetic Algorithms and Soft Computing (Studies in Fuzziness, 8). Physica Verlag (Springer Verlag), Heidelberg, D, 1996 Herrera and Verdegay [26], pages 447–466.Google Scholar
  4. [4]
    A. Bonarini. Evolutionary learning of fuzzy rules: competition and cooperation. In W. Pedrycz, editor, Fuzzy Modelling: Paradigms and Practice, pages 265–284. Kluwer Academic Press, Norwell, MA, 1996.Google Scholar
  5. [5]
    A. Bonarini. Anytime learning and adaptation of hierarchical fuzzy logic behaviors. Adaptive Behavior Journal,5(3–4):281–315, 1997.CrossRefGoogle Scholar
  6. [6]
    A. Bonarini. Reinforcement distribution to fuzzy classifiers: a methodology to extend crisp algorithms. In IEEE International Conference on Evolutionary Computation — WCCI-ICEC’98, volume 1, pages 51–56, Piscataway, NJ, 1998. IEEE Computer Press.Google Scholar
  7. [7]
    A. Bonarini. Comparing reinforcement learning algorithms applied to crisp and fuzzy learning classifier systems. In Proceedings of the Genetic and Evolutonary Computation Conference-GECCO99, pages 52–59, San Francisco, CA, 1999. Morgan Kaufmann.Google Scholar
  8. [8]
    A. Bonarini and F. Basso. Learning to to coordinate fuzzy behaviors for autonomous agents. International Journal of Approximate Reasoning, 17(4):409–432, 1997.zbMATHCrossRefGoogle Scholar
  9. [9]
    A. Bonarini, C. Bonacina, and M. Matteucci. A framework to support the reinforcement function design in real-world agent-based applications. Technical Report 99-73, Politecnico di Milano-Department of Electronics and Information, Milan, I, 1999.Google Scholar
  10. [10]
    A. Bonarini, C. Bonacina, and M. Matteucci. Fuzzy and crisp representation of real-valued input for learning classifier systems. In this book, 2000.Google Scholar
  11. [11]
    L. Booker. Classifier systems that learn internal world models. Machine Learning, 1(2):161–192, 1988.Google Scholar
  12. [12]
    L. Booker, D. E. Goldberg, and J. H. Holland. Classifier systems and genetic algorithms. Artificial Intelligence, 40(1–3):235–282, 1989.CrossRefGoogle Scholar
  13. [13]
    B. Carse, T. Fogarty, and A. Munro. Evolving fuzzy rule based controllers using genetic algorithms. Fuzzy Sets and Systems, 80(3):273–293, 1996.CrossRefGoogle Scholar
  14. [14]
    K. C. C. Chan, V. Lee, and H. Leung. Generating fuzzy rules for target tracking using a steady-state genetic algorithm. IEEE Transactions on Evolutionary Computation, 1(3):189–200, 1997.CrossRefGoogle Scholar
  15. [15]
    Sinn-Cheng Lin; Yung-Yaw Chen. A ga-based fuzzy controller with sliding mode. In Proceedings of the IEEE International Conference on Fuzzy Systems, pages 1103–1110, Piscataway, NJ, 1995. IEEE Computer Press.Google Scholar
  16. [16]
    Sinn-Cheng Lin; Yung-Yaw Chen. On ga-based optimal fuzzy control. In Proceedings of the IEEE International Conference on Evolutionary Computation, pages 846–851, Piscataway, NJ, 1995. IEEE Computer Press.Google Scholar
  17. [17]
    M. Cooper and J. Vidal. Genetic design of fuzzy controllers: The cart and jointed-pole problem. In Proceedings Third IEEE International Conference on Fuzzy Systems, pages 1332–1337, Piscataway, NJ, 1994. IEEE Computer Press.Google Scholar
  18. [18]
    M. Dorigo and M. Colombetti. Robot shaping: an experiment in behavior engineering. MIT Press / Bradford Books, Cambridge, MA, 1997.Google Scholar
  19. [19]
    D. Dubois and H. Prade. Fuzzy Sets and Systems: Theory and Applications. Academic Press, London, 1980.zbMATHGoogle Scholar
  20. [20]
    T. Furuhashi, K. Nakaoka, K. Morikawa, and Y. Uchikawa. Controlling execessive fuzziness in a fuzzy classifier system. In Proceedings of the Fifth International Conference on Genetic Algorithms, pages 635–642, San Mateo, CA, 1993. Morgan Kaufmann.Google Scholar
  21. [21]
    T. Furuhashi, K. Nakaoka, and Y. Uchikawa. An efficient finding of fuzzy rules using a new approach to genetic based machine learning. In Proceedings Fourth IEEE International Conference on Fuzzy Systems, pages 715–722, Piscataway, NJ, 1995. IEEE Computer Press.Google Scholar
  22. [22]
    P.-Y. Glorennec. Fuzzy Q-learning and evolutionary strategy for adaptive fuzzy control. In H.-J. Zimmermann, editor, Second European Congress on Intelligent Techniques and Soft Computing-EUFIT’94, volume 1, pages 35–40, Aachen, D, 1994. Verlag der Augustinus Buchhandlung.Google Scholar
  23. [23]
    P. Y. Glorennec. Constrained optimization ofFIS using an evolutionary method. In J.L. Verdegay, editors. Genetic Algorithms and Soft Computing (Studies in Fuzziness, 8). Physica Verlag (Springer Verlag), Heidelberg, D, 1996 Herrera and Verdegay [26], pages 349–368.Google Scholar
  24. [24]
    P.Y. Glorennec. Fuzzy Q-learning and dynamical fuzzy Q-learning. In Proceedings Third IEEE International Conference on Fuzzy Systems, Piscataway, NJ, 1994. IEEE Computer Press.Google Scholar
  25. [25]
    D. Goldberg, B. Korb, and K. Deb. Messy genetic algorithms: Motivation, analysis, and first results. Complex Systems, 3(5):493–530, 1989.zbMATHMathSciNetGoogle Scholar
  26. [26]
    F. Herrera and J.L. Verdegay, editors. Genetic Algorithms and Soft Computing (Studies in Fuzziness, 8). Physica Verlag (Springer Verlag), Heidelberg, D, 1996.zbMATHGoogle Scholar
  27. [27]
    F. Hoffmann and G. Pfister. Learning of a fuzzy control rule base using messy genetic algorithms. In J.L. Verdegay, editors. Genetic Algorithms and Soft Computing (Studies in Fuzziness, 8). Physica Verlag (Springer Verlag), Heidelberg, D, 1996 Herrera and Verdegay [26], pages 279–305.Google Scholar
  28. [28]
    Frank Hoffmann, Oliver Malki, and Gerd Pfister. Evolutionary algorithms for learning of mobile robot controllers. In H.-J. Zimmermann, editor, Fourth European Congress on Fuzzy and Intelligent Technologies — EUFIT’96, volume 2, pages 1105–1109, Aachen, D, 1996. Verlag der Augustinus Buchhandlung.Google Scholar
  29. [29]
    Frank Hoffmann and Gerd Pfister. Automatic design of hierarchical fuzzy controllers using genetic algorithm. In H.-J. Zimmermann, editor, Second European Congress on Fuzzy and Intelligent Technologies — EUFIT’94, volume 3, pages 1516–1522, Aachen, September 1994. Verlag der Augustinus Buchhandlung.Google Scholar
  30. [30]
    J. Holland. Properties of the bucket-brigade algorithm. In J. J. Grefenstette, editor, Proceedings of the First International Conference on Genetic Algorithms and Their Applications, pages 1–7., Hillsdale, NJ, 1985. Lawrence Erlbaum Associates.Google Scholar
  31. [31]
    J. Holland and J. Reitman. Cognitive systems based on adaptive algorithms. In D. A. Waterman and F. Hayes-Roth, editors, Pattern-directed inference systems, New York, NY, 1978. Academic Press.Google Scholar
  32. [32]
    H.-S. Hwang and K.-B. Woo. Linguistic fuzzy model identification. IEE Proceedings on control theory applications, 142(6):537–545, 1995.zbMATHCrossRefGoogle Scholar
  33. [33]
    W. Hwang and W. Thompson. Design of fuzzy logic controllers using genetic algorithms. In Proceedings of the Third IEEE International Conference on Fuzzy Systems (FUZZ-IEEE’94), pages 1383–1388, Piscataway, NJ, 1994. IEEE Computer Press.Google Scholar
  34. [34]
    H. Ishibuchi, T. Nakashima, and T. Murata. A fuzzy classifier system for generating linguistic classification rules. In Proceedings IEEE/Nagoya University WWW’95, pages 22–27, Nagoya, J, 1995.Google Scholar
  35. [35]
    L. P. Kaelbling, M. L. Littman, and A. W. Moore. Reinforcement learning: a survey. Journal of Artificial Intelligence Research, 4:237–285, 1996.Google Scholar
  36. [36]
    C. L. Karr. Applying genetics to fuzzy logic. AI Expert, 6(3):38–43, 1991.MathSciNetGoogle Scholar
  37. [37]
    C. L. Karr. Design of a cart-pole balancing fuzzy logic controller using a genetic algorithm. In Proceedings SPIE Conference on the Applications of Artificial Intelligence, pages 26–36, 1991.Google Scholar
  38. [38]
    C. L. Karr. Adaptive process control with fuzzy logic and genetic algorithms. Sci. Comput. Autom., 9(10):23–30, 1993.Google Scholar
  39. [39]
    C. L. Karr. Real time process control with fuzzy logic and genetic algorithms. Proceedings of the Symposium on Emerging Computer Techniques for the Minerals Industry, pages 31–37, 1993.Google Scholar
  40. [40]
    C. L. Karr, L. M. Freeman, and D. L. Meredith. Improved fuzzy process control of spacecraft autonomous rendezvous using a genetic algorithm. In G. Rodriguez, editor, Intelligent Control and Adaptive Systems, volume 1196, pages 274–288, Philadelphia, 1989. The International Society of Photo-Optics Instrumentation Engineers (SPIE).Google Scholar
  41. [41]
    C. L. Karr and E. J. Gentry. Fuzzy control of pH using genetic algorithms. IEEE Transactions on Fuzzy Systems, 1(1):46–53, 1993.CrossRefGoogle Scholar
  42. [42]
    C. L. Karr, S. K. Sharma, W. J. Hatcher, and T. R. Harper. Fuzzy control of an exothermic chemical reaction using genetic algorithms. In Engineering Applications of Artificial Intelligence 6, volume 6, pages 575–582, 1993.CrossRefGoogle Scholar
  43. [43]
    J. Y. Ke, K. S. Tang, and K. F. Man. Genetic fuzzy classifier for benchmark cancer diagnosis. In Proceedings of the 23rd International Conference on Industrial Electronics, Control and Instrumentation (IECON97, volume 3, pages 1063–1067, 1997.CrossRefGoogle Scholar
  44. [44]
    M. Kingham and M. Mohammadian. Financial modelling and prediction of interest rate using fuzzy logic and genetic algorithms. In Proceedings of the Australian and New Zealand Conference on Intelligent Information Systems, volume 2, pages 233–236, Piscataway, NJ, 1996. IEEE Computer Press.CrossRefGoogle Scholar
  45. [45]
    J. Kinzel, F. Klawonn, and R. Kruse. Modifications of genetic algorithms for designing and optimizing fuzzy controllers. In Proceedings of the First IEEE Conference on Evolutionary Computation, volume 1, pages 28–33, Piscataway, NJ, 1994. IEEE Computer Press.CrossRefGoogle Scholar
  46. [46]
    G. J. Klir, B. Yuan, and U. St. Clair. Fuzzy set theory: foundations and applicatons. Prentice-Hall, Upper Saddle River, NY, 1997.Google Scholar
  47. [47]
    M. Lee and H. Takagi. Hybrid genetic-fuzzy systems for intelligent systems design. In J.L. Verdegay, editors. Genetic Algorithms and Soft Computing (Studies in Fuzziness, 8). Physica Verlag (Springer Verlag), Heidelberg, D, 1996 Herrera and Verdegay [26], pages 226–250.Google Scholar
  48. [48]
    M. A. Lee and H. Takagi. Dynamic control of genetic algorithms using fuzzy logic techniques. In J. D. Schaffer, editor, Proceedings of the Third International Conference on Genetic Algorithms, pages 76–93, San Mateo, CA, 1993. Morgan Kaufman.Google Scholar
  49. [49]
    M. A. Lee and H. Takagi. Integrating design stages of fuzzy systems using genetic algorithms. In Proceedings of the IEEE International Conference on Fuzzy Systems (FUZZ-IEEE’93), pages 612–617, Piscataway, NJ, 1993. IEEE Computer Press.Google Scholar
  50. [50]
    D. Leitch. Genetic algorithms for the evolution of behaviors in robotics. InJ.L. Verdegay, editors. Genetic Algorithms and Soft Computing (Studies in Fuzziness, 8). Physica Verlag (Springer Verlag), Heidelberg, D, 1996 Herrera and Verdegay [26], pages 306–328.Google Scholar
  51. [51]
    D. Leitch and P. Probert. Genetic algorithms for the development of fuzzy controllers for autonomous guided vehicles. In H.-J. Zimmermann, editor, Second European Congress on Fuzzy and Intelligent Technologies — EUFIT’94, volume 1, pages 464–469, Aachen, September 1994. Verlag der Augustinus Buchhandlung.Google Scholar
  52. [52]
    D. Leitch and P. Probert. Genetic algorithms for the development of fuzzy controllers for mobile robots. In Lecture Notes in Computer Science, volume 1011, pages 148–162, 1995.Google Scholar
  53. [53]
    D. Leitch and P. Probert. New techniques for genetic development of fuzzy controllers. IEEE Transactions on Systems, Man and Cybernetics, 28(1):112–123, 1998.CrossRefGoogle Scholar
  54. [54]
    J. Liska and S. Melsheimer. Complete design of fuzzy logic systems using genetic algorithms. In Proceedings of the Third IEEE International Conference on Fuzzy Systems (FUZZ-IEEE’94), volume II, pages 1377–1382, Piscataway, NJ, 1994. IEEE Computer Press.CrossRefGoogle Scholar
  55. [55]
    E. Mamdani and S. Assilian. An experiment in linguistic synthesis with a fuzzy logic controller. International Journal of Man-Machine Studies, 7:1–13, 1975.zbMATHCrossRefGoogle Scholar
  56. [56]
    M. Mohammadian and R. J. Stonier. Adaptive two layer fuzzy control of a mobile robot system. In Proceedings of the IEEE International Conference on Evolutionary Computation, page 204, Piscataway, NJ, 1995. IEEE Computer Press.Google Scholar
  57. [57]
    H. Nomura, I. Hayashi, and N. Wakami. A self-tuning method of fuzzy reasoning by genetic algorithm. In Proceedings of the International Fuzzy Systems and Intelligent Control Conference (IFSICC’92), pages 236–245, Louisville, KY, 1992.Google Scholar
  58. [58]
    J. Ohwi, S.V. Ulyanov, and K. Yamafuji. Ga in continuous space and fuzzy classifier system for opening of door with manipulator of mobile robot: new benchmark of evolutionary intelligent computing. In Proceedings of the IEEE International Conference on Evolutionary Computation, pages 257–261, Piscataway, NJ, 1995. IEEE Computer Press.Google Scholar
  59. [59]
    G. Ortega and J.M. Giron-Sierra. Genetic algorithms for fuzzy control of automatic docking with a space station. In Proceedings of the IEEE International Conference on Evolutionary Computation, pages 157–161, Piscataway, NJ, 1995. IEEE Computer Press.Google Scholar
  60. [60]
    D. Park, A. Kandel, and G. Langholz. Genetic-based new fuzzy reasoning models with application to fuzzy control. IEEE Transactions on Systems, Man and Cybernetics, 24(1):39–47, 1994.CrossRefGoogle Scholar
  61. [61]
    A. Parodi and P. Bonelli. A new approach to fuzzy classifier systems. In S. Forrest, editor, Proceedings of the Fifth International Conference on Genetic Algorithms, pages 223–230, San Mateo, CA, 1993. Morgan Kaufman.Google Scholar
  62. [62]
    A. Rahmoun and M. Benmohamed. Genetic algorithm methodology to generate optimal fuzzy systems. IEE Proceedings on control theory applications, 145(6):583–587, 1998.CrossRefGoogle Scholar
  63. [63]
    S. P. Singh and R. S. Sutton. Reinforcement learning with replacing eligibility traces. Machine Learning, 22:123–158, 1996.zbMATHGoogle Scholar
  64. [64]
    S. F. Smith. A learning system based on genetic adaptive algorithms. PhD thesis, University of Pittsburgh, Pittsburgh, PE, 1980.Google Scholar
  65. [65]
    R. S. Sutton. Learning to predict by the method of temporal differences. Machine Learning, 3(1):9–44, 1988.Google Scholar
  66. [66]
    R. S. Sutton and A. G. Barto. Reinforcement Learning An Introduction. MIT Press, Cambridge, Massachusetts, 1999.Google Scholar
  67. [67]
    T. Takagi and M. Sugeno. Fuzzy identification of systems and its applications to modelling and control. IEEE Transactions on Systems, Man and Cybernetics, 15(1):116–132, 1985.zbMATHGoogle Scholar
  68. [68]
    K. Tang, K. Man, Z. Liu, and S. Kwong. Minimal fuzzy memberships and rules using hierarchical genetic algorithm. IEEE Transactions on Industrial Electronics, 45(1):162–169, 1998.CrossRefGoogle Scholar
  69. [69]
    P. Thrift. Fuzzy logic synthesis with genetic algorithms. In J. D. Schaffer, editor, Proceedings of the Third International Conference on Genetic Algorithms, pages 509–513, San Mateo, CA, 1993. Morgan Kaufman.Google Scholar
  70. [70]
    Manuel Valenzuela-Rendón. The fuzzy classifier system: A classifier system for continuously varying variables. In R. Belew and L. Booker, editors, Proceedings of the Fourth International Conference on Genetic Algorithms, pages 346–353, San Mateo, CA, 1991. Morgan Kaufman.Google Scholar
  71. [71]
    C. Watkins and P. Dayan. Q-learning. Machine Learning, 8:279–292, 1992.zbMATHGoogle Scholar
  72. [72]
    S. W. Wilson. Classifier fitness based on accuracy. Evolutionary Computation, 3(2):149–175, 1995.CrossRefGoogle Scholar
  73. [73]
    L. A. Zadeh. Fuzzy sets. Information and Control, 8:338–353, 1965.zbMATHCrossRefMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2000

Authors and Affiliations

  • Andrea Bonarini
    • 1
  1. 1.Politecnico di Milano AI and Robotics Project, Dipartimento di Elettronica e InformazionePolitecnico di MilanoMilanoItaly

Personalised recommendations