Abstract
A study is performed to investigate the state evolution of a kind of recurrent neural network. The state variable in the neural system summarize the information of external excitation and initial state, and determine its future response. The recurrent neural network is trained by the data from a dynamic system so that it can behave like the dynamic system. The dynamic systems include both input-output black-box system and autonomous chaotic system. It is found that the state variables in neural system differ from the state variable in the black-box system identified, this case often appears when the network is trained with input-output data of the system. The recurrent neural system learning from chaotic system exhibits an expected chaotic character, its state variable is the same as the system identified at the first period of evolution and its state evolution is sensitive to its initial state.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Narendra, K.S., Parthasarathy, K.: Identification and Control of Dynamical Systems Using Neural Networks. IEEE Transactions on Neural networks 1, 4–27 (1990)
Suykens, J.A.K., Vandewalle, J.: Recurrent Least Squares Support Vector Machines. IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications 47, 1109–1114 (2000)
Elman, J.L.: Finding Structure in Time. Cognitive Science 14, 179–211 (1990)
Pham, D.T., Liu, X.: Training of Elman Networks and Dynamic System Modeling. International Journal of Systems Science 27, 221–226 (1996)
Rivals, I., Personnaz, L.: Black-box Modeling with State-space Neural Networks. In: Zbikowski, R., Hunt, K.J. (eds.) Neural Adaptive Control Technology, pp. 237–264. World Scientific, Singapore (1996)
Zamarreno, J.M., Vega, P.: State Space Neural Network. Properties and Application. Neural Networks 11, 1099–1112 (1998)
Suykens, J.A., De Moor, B.L.R., Vandewalle, J.: Nonlinear System Identification Using Neural State Space Models, Applicable to Robust Control Design. International Journal of Control 62, 129–152 (1995)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Han, M., Shi, Z., Wang, W. (2004). Modeling Dynamic System by Recurrent Neural Network with State Variables. In: Yin, FL., Wang, J., Guo, C. (eds) Advances in Neural Networks - ISNN 2004. ISNN 2004. Lecture Notes in Computer Science, vol 3174. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-28648-6_31
Download citation
DOI: https://doi.org/10.1007/978-3-540-28648-6_31
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22843-1
Online ISBN: 978-3-540-28648-6
eBook Packages: Springer Book Archive