Abstract
This paper discusses the problem of applying sigmoidal neural networks to identification of nonlinear dynamical systems. When using sigmoidal neural networks directly as nonlinear models, one often meets problems such as model parameters lack of physical meaning, sensitivity to noise in model training. In this paper, we introduce an embedded sigmoidal neural network model, in which the neural network is not used directly as a model, but is embedded in a shield such that part of the model parameters become meaningful. Corresponding to the meaningful part and the meaningless part of model parameters, a hierarchical training algorithm consisting of two learning loops is then introduced to train the model. Simulation results show that such a dual loop learning algorithm can solve the noise sensitivity and local minimum problems to some extent.
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
J. Hu, K. Hirasawa, and K. Kumamaru. Adaptive predictor for control of nonlinear systems based on neurofuzzy models. In Proc. of European Control Conference (ECC’99) (Karlsruhe), 8 1999.
J. Hu, K. Kumamaru, and K. Hirasawa. A quasi-ARMAX approach to modeling of nonlinear systems. International Journal of Control, 2001. (to appear in the special issue on nonlinear estimation).
M. Ishikawa. Structure learning with forgetting. Neural Networks, 9(3):509–521, 1996.
L. Ljung and T. Söderström. Theory and Practice of Recursive Identification. MIT press, Cambridge, Mass, 1983.
W.T. Miller III, R.S. Sutton, and P.J. Werbos, editors. Neural Networks for Control. The MIT Press, Massachusetts, 1990.
K.S. Narendra and K. Parthasathy. Identification and control of dynamical systems using neural networks. IEEE Trans. on Neural Networks, 1(1):4–27, 1990.
J. Sjöberg and L. Ljung. Overtraining, regularization and searching for a minimum, with application to neural networks. INT. J. Control, 62(6):1391–1407, 1995.
J. Sjöberg, Q. Zhang, L. Ljung, A. Benveniste, B. Deglon, P.Y. Glorennec, H. Hjal-marsson, and A. Juditsky. Nonlinear black-box modeling in system identification: a unified overview. Automatica, 31(12):1691–1724, 1995.
A.S. Weigend, D.E. Rumelhart, and B.A. Huberman. Generalization by weight-elimination with application to forgetting. Advances in Neural Information Processing Systems, 3:875–882, 1991.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hu, J., Hirasawa, K. (2001). A Hierarchical Method for Training Embedded Sigmoidal Neural Networks. In: Dorffner, G., Bischof, H., Hornik, K. (eds) Artificial Neural Networks — ICANN 2001. ICANN 2001. Lecture Notes in Computer Science, vol 2130. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44668-0_129
Download citation
DOI: https://doi.org/10.1007/3-540-44668-0_129
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42486-4
Online ISBN: 978-3-540-44668-2
eBook Packages: Springer Book Archive