Skip to main content
SpringerLink
Log in

Stable Learning Algorithm of Global Neural Network for Identification of Dynamic Complex Systems

  • Conference paper
Artificial Intelligence and Soft Computing – ICAISC 2008 (ICAISC 2008)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 5097))

Included in the following conference series:

  • 1598 Accesses

Abstract

Novel convergence properties of identification algorithm for complex input-output systems, which uses recurrent neural networks, are derived. By the term “complex system” we understand a system containing interconnected sub processes (elementary processes), which can operate separately. Each element of the complex system is modeled by a multi-input, multi-output neural network. A model of the whole system is obtained by composing all neural networks into one global network. Stable learning algorithm of such a neural network is proposed. We derived sufficient condition of stability using the second Lyapunov method and proved that algorithm is stable even if stability conditions for some individual neural networks are not satisfied.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 189.00
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Bazaraa, M.S., Sherali, H.D., Shetty, C.M.: Nonlinear Programming - Theory and Algorithms. Wiley-Interscience, A John Wiley & Sons Inc, Hoboken, New Jersey (2006)

    MATH  Google Scholar 

  2. Bubnicki, Z.: Identification of Control Plants. (in polish) PWN, Warsaw (1980)

    Google Scholar 

  3. Chao-Chee, K., Kwang, Y.L.: Diagonal Recurrent Neural Networks for Dynamic Systems Control. IEEE Transactions on Neural Networks 6(1), 144–155 (1995)

    Article  Google Scholar 

  4. Drapała, J., Świątek, J.: Algorithm of Recurrent Multilayer Perceptrons Learning for Global Modeling of Complex Systems. In: Proc. of 16th International Conference on Systems Science ICSS 2007, Wrocław University of Technology, Wrocław, Poland, pp. 351–358 (2007)

    Google Scholar 

  5. Drapała, J., Świątek, J.: Global and Local Approach to Complex Systems Modeling Using Dynamic Neural Networks– Analogy with Multiagent Systems. In: Apolloni, B., Howlett, R.J., Jain, L. (eds.) KES 2007, Part II. LNCS (LNAI), vol. 4693, pp. 279–286. Springer, Heidelberg (2007)

    Chapter  Google Scholar 

  6. Gupta, M.M., Jin, L., Homma, N.: Static and Dynamic Neural Networks - From Fundamentals to Advanced Theory. IEEE Press, Wiley-Interscience, A John Wiley & Sons Inc (2003)

    Google Scholar 

  7. Kaczorek, T., Dzieliński, A., Dąbrowski, W., Łopatka, R.: The Basics of Control Theory (in polish). WNT, Warsaw (2006)

    Google Scholar 

  8. Narendra, K.S., Parthasarathy, K.: Identification and Control of Dynamical Systems Using Neural Networks. IEEE Transactions on Neural Networks 1(1), 4–27 (1990)

    Article  Google Scholar 

  9. Nelles, O.: Nonlinear System Identification - From Classical Approaches to Neural Networks and Fuzzy Models. Springer, Heidelberg (2001)

    MATH  Google Scholar 

  10. Parlos, A.G., Chong, K.T., Atiya, A.M.: Application of the Recurrent Multilayer Perceptron in Modeling Complex Process Dynamics. IEEE Transactions on Neural Networks 5(2), 255–266 (1994)

    Article  Google Scholar 

  11. Świątek, J.: Global and Local Modeling of Complex Input-Output Systems. In: Proc. of 16th International Conference on Systems Engineering ICSE 2003, Coventry University, England, pp. 669–671 (2003)

    Google Scholar 

  12. Świątek, J.: Global Identification of Complex Systems with Cascade Structure. In: Rutkowski, L., Siekmann, J.H., Tadeusiewicz, R., Zadeh, L.A. (eds.) ICAISC 2004. LNCS (LNAI), vol. 3070, pp. 990–995. Springer, Heidelberg (2004)

    Google Scholar 

  13. Wen, Y.: Nonlinear System Identification using Discrete-Time Recurrent Neural Networks with Stable Learning Algorithms. International Journal of Information Sciences 158, 131–147 (2004)

    MATH  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Institute of Information Science and Engineering, Wrocław University of Technology, Wyb. Wyspiañskiego 27, 50-370, Wrocław, Poland

    Jarosław Drapała, Jerzy Świa̧tek & Krzysztof Brzostowski

Authors
  1. Jarosław Drapała
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jerzy Świa̧tek
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Krzysztof Brzostowski
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Leszek Rutkowski Ryszard Tadeusiewicz Lotfi A. Zadeh Jacek M. Zurada

Rights and permissions

Reprints and permissions

Copyright information

© 2008 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Drapała, J., Świa̧tek, J., Brzostowski, K. (2008). Stable Learning Algorithm of Global Neural Network for Identification of Dynamic Complex Systems. In: Rutkowski, L., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds) Artificial Intelligence and Soft Computing – ICAISC 2008. ICAISC 2008. Lecture Notes in Computer Science(), vol 5097. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-69731-2_3

Download citation

  • DOI: https://doi.org/10.1007/978-3-540-69731-2_3

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-69572-1

  • Online ISBN: 978-3-540-69731-2

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation