Skip to main content

Weight Training for Performance Optimization in Fuzzy Neural Network

  • Conference paper
Knowledge-Based Intelligent Information and Engineering Systems (KES 2005)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 3681))

  • 1142 Accesses

Abstract

An algorithm for improving performance by training a fuzzy neural network (FNN) based on the back-propagation (BP) algorithm and grey relations is proposed. This technique is developed by directly incorporating the grey relational coefficient (GRC) into the learning rule of the BP, and a BP with GRC technique is proposed in order to improve the performance of training the FNN. From the simulation results, we demonstrate this technique applied for controlling a nonlinear fuzzy model car system and find the result is better than the classical BP algorithm for training the FNN.

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. Rumelhart, D.E., McClelland, J.L.: Parallel Distributed Processing, vol. 1. MIT Press, Cambridge (1986)

    Google Scholar 

  2. Cheng, C.S., Hsu, Y.T., Wu, C.C.: Grey neural networks. IEICE Transactions on Fundamentals Electronics, Commun. Comput. Sci. E81-A 11, 2433–2442 (1998)

    Google Scholar 

  3. Deng, J.L.: Control problems of grey systems. Systems Control Lett. 1(5), 288–294 (1982)

    Article  MATH  Google Scholar 

  4. Hsu, Y.T., Chen, C.M.: A novel fuzzy logic system based on N-version programming. IEEE Trans. Fuzzy Systems 8(2), 155–170 (2000)

    Article  Google Scholar 

  5. Huang, Y.P., Huang, C.H.: Real-valued genetic algorithms for fuzzy grey prediction system. Fuzzy Sets Systems 87(3), 265–276 (1997)

    Article  Google Scholar 

  6. Bazaraa, M.S., Sherali, H.D., Shetty, C.M.: Nonlinear programming, theory and algorithms. Wiley, New York (1993)

    MATH  Google Scholar 

  7. Salehi, F., Lacroix, R., Wade, K.M.: Effects of learning parameters and data presentation on the performance of back-propagation networks for milk yield prediction. Transactions of the ASAE 41(1), 253–259 (1998)

    Google Scholar 

  8. Sejnowski, T.J., Rosenberg, C.R.: Parallel networks that learn to pronounce English text. Complex systems 1(1), 145–168 (1987)

    MATH  Google Scholar 

  9. Lin, C.T., Lee, C.S.: George, Neural-Network-Based Fuzzy control and Decision System. IEEE transactions on computers 40(12), 1320–1336 (1991)

    Article  MathSciNet  Google Scholar 

  10. Maeda, M., Maeda, Y., Murakami, S.: Fuzzy drive control of an autonomous mobile robot. Fuzzy sets and systems 39, 195–204 (1991)

    Article  Google Scholar 

  11. Nozaki, K., Ishibuchi, H., Tanaka, H.: A simple but powerful heuristic method for generating fuzzy rules from numerical data. Fuzzy sets and Systems 86, 251–270 (1997)

    Article  Google Scholar 

  12. Shi, K.Q., Wu, G.W., Hwang, Y.P.: Theory of Grey Information Relation, Chuan Hwa, Taiwan (1994)

    Google Scholar 

  13. Sugeno, M., Murakami, K.: An experimental study on fuzzy parking control using a model car. Industrial Application of Fuzzy Control, 125–138 (1985)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2005 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Chang, HC., Juang, YT. (2005). Weight Training for Performance Optimization in Fuzzy Neural Network. In: Khosla, R., Howlett, R.J., Jain, L.C. (eds) Knowledge-Based Intelligent Information and Engineering Systems. KES 2005. Lecture Notes in Computer Science(), vol 3681. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11552413_86

Download citation

  • DOI: https://doi.org/10.1007/11552413_86

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-28894-7

  • Online ISBN: 978-3-540-31983-2

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics