Skip to main content

Fuzzy Knowledge and Recurrent Neural Networks: A Dynamical Systems Perspective

  • Conference paper
Hybrid Neural Systems (Hybrid Neural Systems 1998)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 1778))

Included in the following conference series:

Abstract

Hybrid neuro-fuzzy systems – the combination of artificial neural networks with fuzzy logic – are becoming increasingly popular. However, neuro-fuzzy systems need to be extended for applications which require context (e.g., speech, handwriting, control). Some of these applications can be modeled in the form of finite-state automata. This chapter presents a synthesis method for mapping fuzzy finite-state automata (FFAs) into recurrent neural networks. The synthesis method requires FFAs to undergo a transformation prior to being mapped into recurrent networks. Their neurons have a slightly enriched functionality in order to accommodate a fuzzy representation of FFA states. This allows fuzzy parameters of FFAs to be directly represented as parameters of the neural network. We present a proof the stability of fuzzy finite-state dynamics of constructed neural networks and through simulations give empirical validation of the proofs.

This chapter contains material reprinted from IEEE Transactions on Fuzzy Systems, Vol. 6, No. 1, p. 76-89, ©1998, Institute of Electrical and Electronics Engineers, and from Proceedings of the IEEE, Vol. 87, No. 9, p. 1623-1640, ©1999, Institute of Electrical and Electronics Engineers, by permission.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Zadeh, L.: Fuzzy sets. Information and Control 8, 338–353 (1965)

    Article  MATH  MathSciNet  Google Scholar 

  2. Bonissone, P.P., Badami, V., Chiang, K.H., Khedkar, P.S., Marcelle, K.W., Schutten, M.J.: Industrial applications of fuzzy logic at General Electric. Proceedings of the IEEE 83(3), 450–465 (1995)

    Article  Google Scholar 

  3. Chiu, S., Chand, S., Moore, D., Chaudhary, A.: Fuzzy logic for control of roll and moment for a flexible wing aircraft. IEEE Control Systems Magazine 11(4), 42–48 (1991)

    Article  Google Scholar 

  4. Corbin, J.: A fuzzy logic-based financial transaction system. Embedded Systems Programming 7(12), 24 (1994)

    Google Scholar 

  5. Franquelo, L.G., Chavez, J.: Fasy: A fuzzy-logic based tool for analog synthesis. IEEE Transactions on Computer-Aided Design of Integrated Circuits 15(7), 705 (1996)

    Article  Google Scholar 

  6. Hardy, T.L.: Multi-objective decision-making under uncertainty fuzzy logic methods, Tech. Rep. TM 106796, NASA, Washington, D.C (1994)

    Google Scholar 

  7. Kickert, W.J.M., van Nauta Lemke, H.R.: Application of a fuzzy controller in a warm water plant. Automatica 12(4), 301–308 (1976)

    Article  Google Scholar 

  8. Lee, C.C.: Fuzzy logic in control systems: fuzzy logic controller. IEEE Transactions on Man, Systems, and Cybernetics SMC-20(2), 404–435 (1990)

    Google Scholar 

  9. Pappis, C.P., Mamdani, E.H.: A fuzzy logic controller for a traffic junction. IEEE Transactions on Systems, Man, and Cybernetics SMC-7(10), 707–717 (1977)

    Google Scholar 

  10. Yang, X.M., Kalambur, G.J.: Design for machining using expert system and fuzzy logic approach. Journal of Materials Engineering and Performance 4(5), 599 (1995)

    Article  Google Scholar 

  11. Wang, L.-X.: Adaptive Fuzzy Systems and Control: Design and Stability Analysis. Prentice-Hall, Englewood Cliffs (1994)

    Google Scholar 

  12. Siegelmann, H.T., Sontag, E.D.: On the computational power of neural nets. Journal of Computer and System Sciences 50(1), 132–150 (1995)

    Article  MATH  MathSciNet  Google Scholar 

  13. Gorrini, V., Bersini, H.: Recurrent fuzzy systems. In: Proceedings of the Third IEEE Conference on Fuzzy Systems, vol. I, pp. 193–198 (1994)

    Google Scholar 

  14. Wang, L.-X.: Fuzzy systems are universal approximators. In: Proceedings of the First International Conference on Fuzzy Systems, pp. 1163–1170 (1992)

    Google Scholar 

  15. Goode, P.V., Chow, M.: A hybrid fuzzy/neural systems used to extract heuristic knowledge from a fault detection problem. In: Proceedings of the Third IEEE Conference on Fuzzy Systems, vol. III, pp. 1731–1736 (1994)

    Google Scholar 

  16. Perneel, C., Renders, J.-M., Themlin, J.-M., Acheroy, M.: Fuzzy reasoning and neural networks for decision making problems in uncertain environments. In: Proceedings of the Third IEEE Conference on Fuzzy Systems, vol. II, pp. 1111–1125 (1994)

    Google Scholar 

  17. Berenji, H.R., Khedkar, P.: Learning and fine tuning fuzzy logic controllers through reinforcement. IEEE Transactions on Neural Networks 3(5), 724–740 (1992)

    Article  Google Scholar 

  18. Thornber, K.K.: The fidelity of fuzzy-logic inference. IEEE Transactions on Fuzzy Systems 1(4), 288–297 (1993)

    Article  MathSciNet  Google Scholar 

  19. Thornber, K.K.: A key to fuzzy-logic inference. International Journal of Approximate Reasoning 8, 105–121 (1993)

    Article  MATH  MathSciNet  Google Scholar 

  20. Santos, E.S.: Maximin automata. Information and Control 13, 363–377 (1968)

    Article  MATH  MathSciNet  Google Scholar 

  21. Zadeh, L.: Fuzzy languages and their relation to human and machine intelligence, Tech. Rep. ERL-M302, Electronics Research Laboratory, University of California, Berkeley (1971)

    Google Scholar 

  22. Gaines, B., Kohout, L.: The logic of automata. International Journal of General Systems 2, 191–208 (1976)

    Article  Google Scholar 

  23. Pathak, A., Pal, S.K.: Fuzzy grammars in syntactic recognition of skeletal maturity from x-rays. IEEE Transactions on Systems, Man, and Cybernetics 16(5), 657–667 (1986)

    Article  Google Scholar 

  24. Mensch, S.I., Lipp, H.M.: Fuzzy specification of finite state machines. In: Proceedings of the European Design Automation Conference, pp. 622–626 (1990)

    Google Scholar 

  25. Senay, H.: Fuzzy command grammars for intelligent interface design. IEEE Transactions on Systems, Man, and Cybernetics 22(5), 1124–1131 (1992)

    Article  Google Scholar 

  26. Grantner, J., Patyra, M.J.: Synthesis and analysis of fuzzy logic finite state machine models. In: Proc. of the Third IEEE Conf. on Fuzzy Systems, vol. I, pp. 205–210 (1994)

    Google Scholar 

  27. Grantner, J., Patyra, M.J.: VLSI implementations of fuzzy logic finite state machines. In: Proceedings of the Fifth IFSA Congress, pp. 781–784 (1993)

    Google Scholar 

  28. Lee, S.C., Lee, E.T.: Fuzzy neural networks. Mathematical Biosciences 23, 151–177 (1975)

    Article  MATH  MathSciNet  Google Scholar 

  29. Unal, F.A., Khan, E.: A fuzzy finite state machine implementation based on a neural fuzzy system. In: Proceedings of the Third International Conference on Fuzzy Systems, vol. 3, pp. 1749–1754 (1994)

    Google Scholar 

  30. Cellier, F.E., Pan, Y.D.: Fuzzy adaptive recurrent counterpropagation neural networks: A tool for efficient implementation of qualitative models of dynamic processes. J. Systems Engineering 5(4), 207–222 (1995)

    Google Scholar 

  31. Kosmatopoulos, E.B., Christodoulou, M.A.: Neural networks for identification of fuzzy dynamical systems: an application to identification of vehicle highway systems, Tech. Rep., Dept. of Electronic and Computer Engineering, Technical U. of Crete (1995)

    Google Scholar 

  32. Kosmatopoulos, E.B., Christodoulou, M.A.: Structural properties of gradient recurrent high-order neural networks. IEEE Transactions on Circuits and Systems (1995)

    Google Scholar 

  33. Kosmatopoulos, E.B., Polycarpou, M.M., Christodoulou, M.A., Ioannou, P.A.: High-order neural networks for identification of dynamical systems. IEEE Transactions on Neural Networks 6(2), 422–431 (1995)

    Article  Google Scholar 

  34. Casey, M.P.: The dynamics of discrete-time computation, with application to recurrent neural networks and finite state machine extraction. Neural Computation 8(6), 1135–1178 (1996)

    Article  Google Scholar 

  35. Cleeremans, A., Servan-Schreiber, D., McClelland, J.: Finite state automata and simple recurrent neural networks. Neural Computation 1(3), 372–381 (1989)

    Article  Google Scholar 

  36. Elman, J.L.: Finding structure in time. Cognitive Science 14, 179–211 (1990)

    Article  Google Scholar 

  37. Frasconi, P., Gori, M., Maggini, M., Soda, G.: Representation of finite state automata in recurrent radial basis function networks. Machine Learning 23, 5–32 (1996)

    MATH  Google Scholar 

  38. Giles, C.L., Miller, C.B., Chen, D., Chen, H.H., Sun, G.Z., Lee, Y.C.: Learning and extracting finite state automata with second-order recurrent neural networks. Neural Computation 4(3), 393–405 (1992)

    Article  Google Scholar 

  39. Pollack, J.B.: The induction of dynamical recognizers. Machine Learning 7(2), 227–252 (1991)

    Google Scholar 

  40. Watrous, R.L., Kuhn, G.M.: Induction of finite-state languages using second- order recurrent networks. Neural Computation 4(3), 406 (1992)

    Article  Google Scholar 

  41. Zeng, Z., Goodman, R.M., Smyth, P.: Learning finite state machines with self- clustering recurrent networks. Neural Computation 5(6), 976–990 (1993)

    Article  Google Scholar 

  42. Omlin, C.W., Thornber, K.K., Giles, C.L.: Fuzzy finite-state automata can be deterministically encoded into recurrent neural networks. IEEE Transactions on Fuzzy Systems 6(1), 76–89 (1998)

    Google Scholar 

  43. Dubois, D., Prade, H.: Fuzzy sets and systems: theory and applications. Mathematics in Science and Engineering, vol. 144, pp. 220–226. Academic Press, London (1980)

    Book  MATH  Google Scholar 

  44. Omlin, C.W., Giles, C.L.: Constructing deterministic finite-state automata in recurrent neural networks. Journal of the ACM 43(6), 937–972 (1996)

    Article  MATH  MathSciNet  Google Scholar 

  45. Omlin, C.W., Giles, C.L.: Rule revision with recurrent neural networks. IEEE Transactions on Knowledge and Data Engineering 8(1), 183–188 (1996)

    Article  Google Scholar 

  46. Lee Giles, C., Omlin, C.W., Thornber, K.K.: Equivalence in knowledge repre- sentation: Automata, recurrent neural networks, and dynamical fuzzy systems. Proceedings of the IEEE 87(9), 1623–1640 (1999)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2000 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Omlin, C.W., Giles, L., Thornber, K.K. (2000). Fuzzy Knowledge and Recurrent Neural Networks: A Dynamical Systems Perspective. In: Wermter, S., Sun, R. (eds) Hybrid Neural Systems. Hybrid Neural Systems 1998. Lecture Notes in Computer Science(), vol 1778. Springer, Berlin, Heidelberg. https://doi.org/10.1007/10719871_9

Download citation

  • DOI: https://doi.org/10.1007/10719871_9

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-67305-7

  • Online ISBN: 978-3-540-46417-4

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics