Neuro-fuzzy Systems: A Short Historical Review

  • Detlef D. NauckEmail author
  • Andreas Nürnberger
Part of the Studies in Computational Intelligence book series (SCI, volume 445)


When the popularity of fuzzy systems in the guise of fuzzy controllers began to rise in the beginning of the 1990s researchers became interested in supporting the development process by an automatic learning process. Just a few years earlier the backpropagation learning rule for multi-layer neural networks had been rediscovered and triggered a massive new interest in neural networks. The approach of combining fuzzy systems with neural networks into neuro-fuzzy systems therefore was an obvious choice for making fuzzy systems learn. In this chapter we briefly recall some milestones on the evolution of neuro-fuzzy systems.


Fuzzy System Fuzzy Rule Fuzzy Controller Fuzzy Inference System Radial Basis Function Network 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Asaithambi, M., Manoharan, S.C., Subramanian, S.: Classification of Respiratory Abnormalities Using Adaptive Neuro Fuzzy Inference System. In: Pan, J.-S., Chen, S.-M., Nguyen, N.T. (eds.) ACIIDS 2012, Part III. LNCS, vol. 7198, pp. 65–73. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  2. 2.
    Atsalakis, G., Valavanis, K.: Forecasting stock market short-term trends using a neuro-fuzzy based methodology. Expert Systems with Applications 36(7), 10,696–10,707 (2009)Google Scholar
  3. 3.
    Barto, A.G., Sutton, R.S., Anderson, C.W.: Neuronlike adaptive elements that can solve difficult learning control problems. IEEE Transactions on Systems, Man, and Cybernetics 13, 834–846 (1983)CrossRefGoogle Scholar
  4. 4.
    Berenji, H.R., Khedkar, P.: Fuzzy rules for guiding reinforcement learning. In: Int. Conf. on Information Processing and Management of Uncertainty in Knowledge-Based Systems (IPMU 1992), Mallorca, pp. 511–514 (1992a)Google Scholar
  5. 5.
    Berenji, H.R., Khedkar, P.: Learning and tuning fuzzy logic controllers through reinforcements. IEEE Transactions on Neural Networks 3, 724–740 (1992)CrossRefGoogle Scholar
  6. 6.
    Berenji, H.R., Lea, R.N., Jani, Y., Khedkar, P., Malkani, A., Hoblit, J.: Space shuttle attitude control by reinforcement learning and fuzzy logic. In: Proc. IEEE Int. Conf. on Neural Networks 1993, San Francisco, pp. 1396–1401 (1993)Google Scholar
  7. 7.
    Berthold, M.: Mixed fuzzy rule formation. Int. J. Approximate Reasoning 32, 67–84 (2003)zbMATHCrossRefGoogle Scholar
  8. 8.
    Berthold, M., Huber, K.P.: Tolerating missing values in a fuzzy environment. In: Mares, M., Mesiar, R., Novak, V., Ramik, J., Stupnanova, A. (eds.) Proc. of 7th Intl. Fuzzy Systems Association World Congress (IFSA 1997), vol. I, pp. 359–362. Academia, Prague (1997)Google Scholar
  9. 9.
    Berthold, M., Huber, K.P.: Constructing fuzzy graphs from examples. Int J Intelligent Data Analysis 3(1), 37–57 (1999)zbMATHCrossRefGoogle Scholar
  10. 10.
    Berthold, M.R., Huber, K.P.: Neural network based construction of fuzzy graphs. In: Proceedings of the Fourth Annual Conference on Fuzzy Theory and Technology, North Carolina, pp. 170–173 (1995) (invited paper)Google Scholar
  11. 11.
    Casillas, J., Cordon, O., Herrera, F., Magdalena, L. (eds.): Trade-off between Accuracy and Interpretability in Fuzzy Rule-Based Modelling. STUDFUZZ. Physica-Verlag, Heidelberg (2002)Google Scholar
  12. 12.
    Dabija, V., Tschichold Gürman, N.: A framework for combining symbolic and connectionist learning with equivalent concept descriptions. In: Proc. 1993 Int. Joint Conf. on Neural Networks (IJCNN 1993), Nagoya (1993)Google Scholar
  13. 13.
    Dias, P., Figueiredo, K., Vellasco, M., Pacheco, M.A., Barbosa, C.H.: Reinforcement learning hierarchical neuro-fuzzy model for autonomous robots. In: Proc. of 2nd Int. Conf. on Autonomous Robots and Agents (ICARA 2004), Palmerston, New Zealand, pp. 107–112 (2004)Google Scholar
  14. 14.
    Eklund, P., Klawonn, F.: Neural fuzzy logic programming. IEEE Trans. Neural Networks 3, 815–818 (1992)CrossRefGoogle Scholar
  15. 15.
    Figueiredo, K., Vellasco, M., Pacheco, M., Souza, F.: Reinforcement learning hierarchical neuro-fuzzy politree model for control of autonomous agents. In: Proc. of 4th Int. Conf. on Hybrid Intelligent Systems (HIS 2004), Kitakyushu, Japan, pp. 107–112 (2004)Google Scholar
  16. 16.
    Figueiredo, K., Campos, L.C.D., Vellasco, M.B.R., Pacheco, M.A.C.: Reinforcement learning-hierarchical neuro-fuzzy politree model for autonomous agents–evaluation in a multi-obstacle environment. In: Proc. of 5th Intl. Conf. on Hybrid Intelligent Systems (HIS 2005), pp. 551–554 (2005)Google Scholar
  17. 17.
    Gorrini, V., Bersini, H.: Recurrent fuzzy systems. In: Proc. of the 3rd Conference on Fuzzy Systems (FUZZ-IEEE 1994). IEEE, Orlando (1994)Google Scholar
  18. 18.
    Gupta, M., Rao, D.: On the principles of fuzzy neural networks. Fuzzy Sets and Systems 61, 1–18 (1994)MathSciNetCrossRefGoogle Scholar
  19. 19.
    Halgamuge, S.K.: Advanced methods for fusion of fuzzy systems and neural networks in intelligent data processing, PhD thesis, Technische Hochschule Darmstadt (1995)Google Scholar
  20. 20.
    Halgamuge, S.K., Glesner, M.: A fuzzy-neural approach for pattern classification with the generation of rules based on supervised learning. In: Proc. Neuro-Nimes 1992, Nanterre, pp. 167–173 (1992)Google Scholar
  21. 21.
    Halgamuge, S.K., Glesner, M.: Neural networks in designing fuzzy systems for real world applications. Fuzzy Sets and Systems 65, 1–12 (1994)CrossRefGoogle Scholar
  22. 22.
    Hammell II, R.J., Sudkamp, T.: A two level architecture for fuzzy learning. Journal of Intelligent and Fuzzy Systems 3(4), 273–286 (1995)Google Scholar
  23. 23.
    Jang, J.S.R.: Fuzzy modeling using generalized neural networks and kalman filter algorithm. In: Proc. Ninth National Conf. on Artificial Intelligence (AAAI 1991), pp. 762–767 (1991)Google Scholar
  24. 24.
    Jang, J.S.R.: Self-learning fuzzy controller based on temporal back-propagation. IEEE Transactions on Neural Networks 3, 714–723 (1992)CrossRefGoogle Scholar
  25. 25.
    Jang, J.S.R.: Anfis: Adaptive-network-based fuzzy inference systems. IEEE Transactions on Systems, Man, and Cybernetics 23, 665–685 (1993)CrossRefGoogle Scholar
  26. 26.
    Jang, J.S.R., Mizutani, E.: Levenberg-marquardt method for anfis learning. In: Proc. Biennial Conference of the North American Fuzzy Information Processing Society, NAFIPS 1996, pp. 87–91. IEEE, Berkeley (1996)Google Scholar
  27. 27.
    Jang, J.S.R., Sun, C.T.: Functional equivalence between radial basis function networks and fuzzy inference systems. IEEE Trans. Neural Networks 4, 156–163 (1993)CrossRefGoogle Scholar
  28. 28.
    Keller, J.M.: Experiments on neural network architectures for fuzzy logic. In: Lea, R.N., Villareal, J. (eds.) Proc. Second Joint Technology Workshop on Neural Networks and Fuzzy Logic, NASA, Lyndon B, pp. 201–216. Johnson Space Center, Houston (1991)Google Scholar
  29. 29.
    Keller, J.M., Hunt, D.J.: Incorporating fuzzy membership function into the perceptron algorithm. IEEE Transactions on Pattern Analysis and Machine Intelligence 7, 693–699 (1985)CrossRefGoogle Scholar
  30. 30.
    Keller, J.M., Tahani, H.: Backpropagation neural networks for fuzzy logic. Information Sciences 62, 205–221 (1992)CrossRefGoogle Scholar
  31. 31.
    Keller, J.M., Tahani, H.: Implementation of conjunctive and disjunctive fuzzy logic rules with neural networks. Int. J. Approximate Reasoning 6, 221–240 (1992)zbMATHCrossRefGoogle Scholar
  32. 32.
    Keller, J.M., Yager, R.R., Tahani, H.: Neural network implementation of fuzzy logic. Fuzzy Sets and Systems 45, 1–12 (1992)MathSciNetzbMATHCrossRefGoogle Scholar
  33. 33.
    Kempf, R., Adamy, J.: Equilibria of recurrent fuzzy systems. Fuzzy Sets and Systems 140(2), 231–257 (2003)MathSciNetzbMATHCrossRefGoogle Scholar
  34. 34.
    Kuremoto, T., Yamano, Y., Feng, L.-B., Kobayashi, K., Obayashi, M.: A Neuro-fuzzy Network with Reinforcement Learning Algorithms for Swarm Learning. In: Zhang, Y. (ed.) Future Wireless Networks and Information Systems. LNEE, vol. 144, pp. 101–108. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  35. 35.
    Lee, C.H., Teng, C.C.: Indentification and control of dynamic systems using recurrent fuzzy neural networks. IEEE Transactions on Fuzzy Systems 8(4), 349–366 (2000)CrossRefGoogle Scholar
  36. 36.
    Lin, C.M., Hsu, C.F.: Identification of dynamic systems using recurrent fuzzy neural network. In: Proc. of Joint 9th IFSA World Congress and 20th NAFIPS International Conference, pp. 2671–2675 (2001)Google Scholar
  37. 37.
    Medsker, L.R., Jain, L.C.: Recurrent Neural Networks: Design and Applications. CRC Press (1999)Google Scholar
  38. 38.
    Mitra, S., Hayashi, Y.: Neuro-fuzzy rule generation: survey in soft computing framework. IEEE Trans. Neural Netw. Learning Syst. 11(3), 748–768 (2000)Google Scholar
  39. 39.
    Miyoshi, T., Tano, S., Kato, Y., Arnould, T.: Operator tuning in fuzzy production rules using neural networks. In: Proc. IEEE Int. Conf. on Fuzzy Systems 1993, San Francisco, pp. 641–646 (1993)Google Scholar
  40. 40.
    Nauck, D.: Adaptive rule weights in neuro-fuzzy systems. Neural Computing & Applications 9(1), 60–70 (2000)CrossRefGoogle Scholar
  41. 41.
    Nauck, D.: Fuzzy data analysis with NEFCLASS. Int. J. Approximate Reasoning 32, 103–130 (2003)MathSciNetzbMATHCrossRefGoogle Scholar
  42. 42.
    Nauck, D.: Measuring interpretability in rule-based classification systems. In: Proc. IEEE Int. Conf. on Fuzzy Systems 2003, pp. 196–201. IEEE, St. Louis (2003)Google Scholar
  43. 43.
    Nauck, D.: Neuro-fuzzy learning with symbolic and numeric data. Soft Computing 8(6), 383–396 (2004)CrossRefGoogle Scholar
  44. 44.
    Nauck, D., Kruse, R.: Nefcon-i: An x-window based simulator for neural fuzzy controllers. In: Proc. IEEE Int. Conf. Neural Networks 1994 at IEEE WCCI 1994, Orlando, FL, pp. 1638–1643 (1994)Google Scholar
  45. 45.
    Nauck, D., Kruse, R.: Nefclass–a neuro-fuzzy approach for the classification of data. In: George, K.M., Carrol, J.H., Deaton, E., Oppenheim, D., Hightower, J. (eds.) Proc. 1995 ACM Symposium on Applied Computing, Applied Computing 1995, Nashville, February 26-28, pp. 461–465. ACM Press, New York (1995)CrossRefGoogle Scholar
  46. 46.
    Nauck, D., Kruse, R.: A neuro-fuzzy method to learn fuzzy classification rules from data. Fuzzy Sets and Systems 89, 277–288 (1997)MathSciNetCrossRefGoogle Scholar
  47. 47.
    Nauck, D., Kruse, R.: How the learning of rule weights affects the interpretability of fuzzy systems. In: Proc. 7th IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 1998), Anchorage, pp. 1235–1240 (1998)Google Scholar
  48. 48.
    Nauck, D., Kruse, R.: Neuro-fuzzy systems for function approximation. Fuzzy Sets and Systems 101, 261–271 (1999)MathSciNetzbMATHCrossRefGoogle Scholar
  49. 49.
    Nauck, D., Nürnberger, A.: The evolution of neuro-fuzzy systems. In: Proc. 24th International Conf. of the North American Fuzzy Information Processing Society (NAFIPS 2005), pp. 98–103. IEEE (2005)Google Scholar
  50. 50.
    Nauck, D., Klawonn, F., Kruse, R.: Foundations of Neuro-Fuzzy Systems. Wiley, Chichester (1997)Google Scholar
  51. 51.
    Nürnberger, A.: A hierarchical recurrent neuro-fuzzy system. In: Proc. of Joint 9th IFSA World Congress and 20th NAFIPS International Conference, pp. 1407–1412. IEEE (2001)Google Scholar
  52. 52.
    Nürnberger, A.: Approximation of dynamic systems using recurrent neuro-fuzzy techniques. Soft Computing 8(6), 428–442 (2004)CrossRefGoogle Scholar
  53. 53.
    Nürnberger, A., Nauck, D., Kruse, R.: Neuro-fuzzy control based on the nefcon-model. Soft Computing 2(4), 182–186 (1999)Google Scholar
  54. 54.
    Pal, S.K., Mitra, S.: Multi-layer perceptron, fuzzy sets and classification. IEEE Trans. Neural Networks 3, 683–697 (1992)CrossRefGoogle Scholar
  55. 55.
    Park, I., Choi, J., Lee, M.J., Lee, S.: Application of an adaptive neuro-fuzzy inference system to ground subsidence hazard mapping. Computers and Geosciences (2012) (online first) Google Scholar
  56. 56.
    Pedrycz, W.: Neurocomputations in relational systems. IEEE Transactions on Pattern Analysis and Machine Intelligence 13, 289–297 (1991)CrossRefGoogle Scholar
  57. 57.
    Pedrycz, W.: A referential scheme of fuzzy decision making and its neural network structure. IEEE Transactions on Systems, Man, and Cybernetics 21, 1593–1604 (1991)CrossRefGoogle Scholar
  58. 58.
    Pedrycz, W., Kandel, A., Zhang, Y.Q.: Neurofuzzy systems. In: Nguyen, H.T., Sugeno, M. (eds.) Fuzzy Systems Modeling and Control. The Handbooks on Fuzzy Sets ch. 9, pp. 311–380. Kluwer Academic Publishers, Norwell (1998)Google Scholar
  59. 59.
    Pineda, F.J.: Recurrent backpropagation networks. In: Chauvin, Y., Rumelhart, D.E. (eds.) Backpropagation: Theory, Architectures and Applications, pp. 99–135. Lawrence Erlbaum Associates, Hillsdale (1995)Google Scholar
  60. 60.
    Riedmiller, M.: Selbständig lernende neuronale Steuerungen. VDI-Verlag GmbH, Düsseldorf (1997)Google Scholar
  61. 61.
    Sarma, K.K., Mitra, A.: Recurrent fuzzy-neural mimo channel modeling. Journal of Intelligent Systems (2012)Google Scholar
  62. 62.
    Simpson, P.K.: Fuzzy min-max neural networks–part 1: Classification. IEEE Transactions on Neural Networks 3, 776–786 (1992a)CrossRefGoogle Scholar
  63. 63.
    Simpson, P.K.: Fuzzy min-max neural networks–part 2: Clustering. IEEE Transactions on Fuzzy Systems 1, 32–45 (1992)CrossRefGoogle Scholar
  64. 64.
    Sudkamp, T., Hammell II, R.J.: Scalability in fuzzy rule-based learning. Information Sciences 199, 135–147 (1998)CrossRefGoogle Scholar
  65. 65.
    Surmann, H., Maniadakis, M.: Learning feed-forward and recurrent fuzzy systems: A genetic approach. Journal of Systems Architecture 47(7), 649–662 (2001)CrossRefGoogle Scholar
  66. 66.
    Takagi, H., Hayashi, I.: NN-driven fuzzy reasoning. Int. J. Approximate Reasoning 5, 191–212 (1991)zbMATHCrossRefGoogle Scholar
  67. 67.
    Taylan, O., Darrab, I.A.: Fuzzy control charts for process quality improvement and product assessment in tip shear carpet industry. Journal of Manufacturing Technology Management 23(3), 402–420 (2012)CrossRefGoogle Scholar
  68. 68.
    Theocharis, J.B., Vachtsevanos, G.: Recursive learning algorithms for training fuzzy recurrent models. International Journal of Intelligence Systems 11(12), 1059–1098 (1996)zbMATHCrossRefGoogle Scholar
  69. 69.
    Tschichold-Gürman, N.: Generation and improvement of fuzzy classifiers with incremental learning using fuzzy rulenet. In: George, K.M., Carrol, J.H., Deaton, E., Oppenheim, D., Hightower, J. (eds.) Proc. 1995 ACM Symposium on Applied Computing, Applied Computing, Nashville, February 26-28, pp. 466–470. ACM Press, New York (1995)CrossRefGoogle Scholar
  70. 70.
    Tschichold-Gürman, N.: Rulenet–a new knowledge-based artificial neural network model with application examples in robotics. PhD thesis, ETH Zürich, Zürich (1996)Google Scholar
  71. 71.
    Vatankhah, R., Etemadi, S., Alasty, A., Vossoughi, G.: Adaptive critic-based neuro-fuzzy controller in multi-agents: Distributed behavioral control and path tracking. Neurocomput. 88, 24–35 (2012)CrossRefGoogle Scholar
  72. 72.
    Wang, J.S., Lee, C.S.G.: Self-adaptive recurrent neuro-fuzzy control of an autonomous underwater vehicle. IEEE Transactions on Robotics and Automation 19(2), 283–295 (2003)zbMATHCrossRefGoogle Scholar
  73. 73.
    Wang, L.X., Mendel, J.M.: Generating fuzzy rules by learning from examples. IEEE Trans Syst., Man, Cybern. 22(6), 1414–1427 (1992)MathSciNetCrossRefGoogle Scholar
  74. 74.
    Wermter, S.: Neural fuzzy preference integration using neural preference moore machines. International Journal of Neural Systems 10(4), 287–310 (2000)zbMATHGoogle Scholar
  75. 75.
    White, D.A., Sofge, D.A. (eds.): Handbook of Intelligent Control. Neural, Fuzzy, and Adaptive Approaches. Van Nostrand Reinhold, New York (1992)Google Scholar
  76. 76.
    Williams, R.J., Zipser, D.: Experimental analysis of the real time recurrent learning algorithm. Connection Science 1, 87–111 (1989)CrossRefGoogle Scholar
  77. 77.
    Yager, R.R., Filev, D.P.: Adaptive defuzzification for fuzzy logic controllers. BUSEFAL 49, 50–57 (1992)Google Scholar
  78. 78.
    Yager, R.R., Filev, D.P.: Adaptive defuzzification for fuzzy system modelling. In: Proc. Workshop of the North American Fuzzy Information Processing Society (NAFIPS 1992), pp. 135–142. Puerto Vallarta (1992)Google Scholar
  79. 79.
    Zhang, C., Qiu, F.: Hyperspectral image classification using an unsupervised neuro-fuzzy system. Journal of Applied Remote Sensing 6(1), 063, 515 (2012)Google Scholar
  80. 80.
    Zhang, J., Morris, A.J.: Recurrent neuro-fuzzy networks for nonlinear process modelling. IEEE Transactions on Neural Networks 10(2), 313–326 (1999)CrossRefGoogle Scholar
  81. 81.
    Ziaii, M., Ardejani, F.D., Ziaei, M., Soleymani, A.A.: Neuro-fuzzy modeling based genetic algorithms for identification of geochemical anomalies in mining geochemistry. Applied Geochemistry 27(3), 663–676 (2012)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  1. 1.Research and VenturingBTIpswichUK
  2. 2.Faculty of Computer ScienceOtto-von-Guericke University of MagdeburgMagdeburgGermany

Personalised recommendations