Abstract
The paper deals with a discrete-time recurrent neural network designed with dynamic neural models. Dynamics is reproduced within each single neuron, hence the considered network is a locally recurrent globally feed-forward. In the paper, conditions for global stability of the considered neural network are derived using the pole placement and Lyapunov second method.
This work was supported by the State Committee for Scientific Research in Poland (KBN) under the grant No. 4T11A01425
An erratum to this chapter can be found at http://dx.doi.org/10.1007/11550907_163 .
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Tsoi, A.C., Back, A.D.: Locally recurrent globally feedforward networks: A critical review of architectures. IEEE Transactions on Neural Networks 5, 229–239 (1994)
Gori, M., Bengio, Y., Mori, R.D.: BPS: A learning algorithm for capturing the dynamic nature of spech. In: International Joint Conference on Neural Networks, vol. II, pp. 417–423 (1989)
Patan, K., Parisini, T.: Identification of neural dynamic models for fault detection and isolation: the case of a real sugar evaporation process. Journal of Process Control 15, 67–79 (2005)
Korbicz, J., Patan, K., Obuchowicz, A.: Dynamic neural networks for process modelling in fault detection and isolation systems. International Journal of Applied Mathematics and Computer Science 9, 519–546 (1999)
Patan, K.: Training of the dynamic neural networks via constrained optimization. In: Proc. IEEE Int. Joint Conference on Neural Networks, IJCNN 2004, Budapest, Hungary (2004); published on CD-ROM.
Gupta, M.M., Jin, L., Homma, N.: Static and Dynamic Neural Neetworks. From Fundamentals to Advanced Theory. John Wiley & Sons, New Jersey (2003)
Narendra, K.S., Parthasarathy, K.: Identification and control of dynamical systems using neural networks. IEEE Transactions on Neural Networks 1, 12–18 (1990)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Patan, K., Korbicz, J., Prętki, P. (2005). Global Stability Conditions of Locally Recurrent Neural Networks. In: Duch, W., Kacprzyk, J., Oja, E., Zadrożny, S. (eds) Artificial Neural Networks: Formal Models and Their Applications – ICANN 2005. ICANN 2005. Lecture Notes in Computer Science, vol 3697. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11550907_31
Download citation
DOI: https://doi.org/10.1007/11550907_31
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28755-1
Online ISBN: 978-3-540-28756-8
eBook Packages: Computer ScienceComputer Science (R0)