On the Intrinsic Relation of Linear Dynamical Systems and Higher Order Neural Units

Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 466)

Abstract

This paper summarizes the fundamental construction of higher-order-neural-units (HONU) as a class of polynomial function based neural units, which are though non-linear discrete time models, are linear in their parameters. From this a relation will be developed, ultimately leading to a new definition for analysing the global stability of a HONU, not only as a model itself, but further as a means of justifying the global dynamic stability of the whole control loop under HONU feedback control. This paper is organised to develop the fundamentals behind this intrinsic relation of linear dynamic systems and HONUs accompanied by a theoretical example to illustrate the functionality and principles of the concept.

Keywords

Adaptive control Higher-order neural units (HONUs) Gradient descent (GD) Levenberg-Marquardt (LM) Batch propagation through time (BPTT) 

References

  1. 1.
    Nikolaev, N.Y., Iba, H.: Adaptive Learning of Polynomial Networks Genetic Programming, Backpropagation and Bayesian Methods. Springer, New York (2006)MATHGoogle Scholar
  2. 2.
    Bukovsky, I., Hou, Z.-G., Bila, J., Gupta, M.M.: Foundation of notation and classification of nonconventional static and dynamic neural units. In: 6th IEEE International Conference on Cognitive Informatics, pp. 401–407 (2007)Google Scholar
  3. 3.
    Solo, G.M.: Fundamentals of higher order neural networks for modeling and simulation. Artif. High. Order Neural Netw. Model. Simul. (2012)Google Scholar
  4. 4.
    Song, K.-Y., Redlapalli, S., Gupta, M.M.: Cubic neural unit for control applications. In: Fourth International Symposium on Uncertainty Modeling and Analysis, ISUMA 2003, pp. 324–329 (2003)Google Scholar
  5. 5.
    Bukovsky, I., Redlapalli, S., Gupta, M.M.: Quadratic and cubic neural units for identification and fast state feedback control of unknown nonlinear dynamic systems. In: Fourth International Symposium on Uncertainty Modeling and Analysis, ISUMA 2003, pp. 330–334 (2003)Google Scholar
  6. 6.
    Williams, R.J., Zipser, D.: A learning algorithm for continually running fully recurrent neural networks. Neural Comput. 1(2), 270–280 (1989)CrossRefGoogle Scholar
  7. 7.
    Werbos, P.J.: Backpropagation through time: what it does and how to do it. Proc. IEEE 78(10), 1550–1560 (1990)CrossRefGoogle Scholar
  8. 8.
    Benes, P., Bukovsky, I.: Neural network approach to hoist deceleration control. In: 2014 International Joint Conference on Neural Networks (IJCNN), pp. 1864–1869 (2014)Google Scholar
  9. 9.
    Bukovsky, I., Benes, P., Slama M.: Laboratory systems control with adaptively tuned higher order neural units. In: Silhavy, R., Senkerik, R., Oplatkova, Z.K., Prokopova, Z., Silhavy, P. (eds.) Intelligent Systems in Cybernetics and Automation Theory. Springer International Publishing, pp. 275–284 (2015)Google Scholar
  10. 10.
    Chu, T.: An exponential convergence estimate for analog neural networks with delay. Phys. Lett. A 283(1–2), 113–118 (2001)MathSciNetCrossRefMATHGoogle Scholar
  11. 11.
    Zhang, Z.: Global exponential stability and periodic solutions of delay Hopfield neural networks. Int. J. Syst. Sci. 27(2), 227–231 (1996)CrossRefMATHGoogle Scholar
  12. 12.
    Zhao, W., Zhu, Q.: New results of global robust exponential stability of neural networks with delays. Nonlinear Anal. Real World Appl. 11(2), 1190–1197 (2010)MathSciNetCrossRefMATHGoogle Scholar
  13. 13.
    Wu, Z.-G., Lam, J., Su, H., Chu, J.: Stability and dissipativity analysis of static neural networks with time delay. IEEE Trans. Neural Netw. Learn. Syst. 23(2), 199–210 (2012)CrossRefGoogle Scholar
  14. 14.
    Arik, S.: Global asymptotic stability of a class of dynamical neural networks. IEEE Trans. Circuits Syst. Fundam. Theory Appl. 47(4), 568–571 (2000)MathSciNetCrossRefMATHGoogle Scholar
  15. 15.
    Liao, X., Chen, G., Sanchez, E.N.: LMI-based approach for asymptotically stability analysis of delayed neural networks. IEEE Trans. Circuits Syst. Fundam. Theory Appl. 49(7), 1033–1039 (2002)MathSciNetCrossRefGoogle Scholar
  16. 16.
    Liao, X., Chen, G., Sanchez, E.N.: Delay-dependent exponential stability analysis of delayed neural networks: an LMI approach. Neural Netw. 15(7), 855–866 (2002)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  1. 1.Department of Instrumentation and Control EngineeringCzech Technical University in PraguePragueCzech Republic

Personalised recommendations