Abstract
In the past few years, there has been increased interest in the modeling and control of non-linear systems using Neural Networks (NNs) [1–12]. Applications of NNs published in literature dealt with I/O mappings. Recently, however, there has been increased interest in Input — state — Output mapping representation using Dynamic Recurrent Neural Networks (DRNNs) [13–16]. DRNNs are Feed Forward Neural Networks (FFNNs) [17,18] with feedback connections, which enable the description of temporal behavior to be stored in the neurons, allowing the NNs to account for the nonlinear dynamics. Funahashi and Nakamura [19] have shown that finite time trajectories of an n dimensional system can be approximated by the states of a Hopfield network, with n output nodes, N hidden nodes, and appropriate initial states.
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
Haykin S. Neural networks: A comprehensive foundation. Macmillan college publishing company.
Michel, A. N. and Farrell J. A. Associative memories via artificial neural networks.. IEEE control systems, 1990.
Guez A.,. Eilbert J. L. and Kam M.. Neural network architecture for control. IEEE control systems, 1988.
Antsaklis P. J. Neural networks in control systems.. IEEE control systems, 1990.
Hunt K. J., Sbarbaro D., Zbikowski R., and P. J. Gawthrop Neural networks for control systems: A survey. Automatica, 1992., vol. 28, no. 6, pp. 1083–1112
Bavarian B. Introduction to neural networks for intelligent control. IEEE control systems, 1988.
Warwick K. A critique of neural networks for discrete time linear control. Int. J. control, 1995, vol. 61, no. 6, pp. 1253–1264.
Warwick K. Neural networks for control: counter arguments. Control 94, 21–24 March 1994, conference publication no. 389.
Warwick K., Ball N. Self–organizing neural networks for adaptive–control. Journal of Intelligent & Robotic systems. 1996, vol. 15, no. 2, pp. 153–163.
Kiernan L., Mason J. D., Warwick K. Robust initialization of Gaussian radial basis function networks, using partitioned k–means clustering. Electronics letters, 1996, vol. 32, no. 7, pp. 671–673.
Hunt K. J., Irwin G. R., and Warwick K. Neural network engineering in dynamic control systems. Springer.
Warwick K., Irwin G. W., and Hunt K. Neural networks for control and systems. IEE control engineering series 46.
Delgado A, Kambhampati C., Warwick K. Zero dynamics and relative order of dynamic recurrent neural networks. Proceedings Of International Conference on Mathematics of Artificial Neural Networks and applications 95. Oxford July 3–7, 1995.
Delgado A., Kambhampati C., and Warwick K. Dynamic recurrent neural network for system identification and control. WEE pros. control theory appl 1995, vol. 142, no. 4, July.
Kambhampati C., Delgado A., Mason J. D., Warwick K.. Stable Receding Horizon Control Based on Recurrent Networks. IEEE Proceedings on Control theory and applications, May 1997, vol. 144, no. 3, pp. 249–254.
Jin L., Nikiforuk P. N., and Gupta M. Approximation of discrete time state space trajectories using dynamic recurrent neural networks. IEEE transactions in automatic control July 1995, vol. 40, no 7.
Kambhampati C., Mayson J. D. and Warwick. K. Stable one step ahead predictive control of non - linear systems. Under review AUTOMATICA. Also available as an international technical memorandum of the Dept. of Cybernetics, University Of Reading, UK.
Hornik K., Stinchcombe M., and White H. Multilayer feed forward networks are universal approximators. Neural networks 1989, vol. 2, pp. 359–366.
Funahashi K., Nakamura Y. Approximation of Dynamic Systems by Continuous Time Recurrent Neural Networks. Neural networks 1993, vol. 6, pp. 801–806.
Kravaris C., and Kantor J. Geometric methods for nonlinear process control. L. Background. Ind. Eng. Chem. Res 1990., vol. 29, pp. 2295–2310.
Fliess M., Lamnabhi M., and Lamnabhi - Lagarrigue F. An algebraic approach to nonlinear functional expansions. IEEE transactions on circuits and systems August 1983, vol. CAS - 30, no. 8,.
Kambhampati C., Manchanda S., Delgado A. et. al. The relative order and inverses of recurrent networks. Automatica, 1995, vol. 32, no. 1, pp. 117–123.
Albertini F., Sontag E. D., and Maillot V.. Uniqueness of weights for neural networks. In R. Mammon (Ed.), Artificial neural networks with applications in speech and vision. London: Chapman and Hall.Van de Vusse J., Plug flow type reactor versus tank reactor. Chem. Eng. Sci., 19, 994–997, 1964
Kandor J. Stability of state feedback transformations for non–linear systems some practical considerations. Proc. American Control Conf., 1986, pp. 1014–1016.
H. J. Bremermann How the brain adjusts synapses - maybe. In Automated reasoning.pp.119–147.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1998 Springer-Verlag London Limited
About this chapter
Cite this chapter
Kárný, M., Warwick, K., Kůrková, V. (1998). A Priori Information in Network Design. In: Kárný, M., Warwick, K., Kůrková, V. (eds) Dealing with Complexity. Perspectives in Neural Computing. Springer, London. https://doi.org/10.1007/978-1-4471-1523-6_7
Download citation
DOI: https://doi.org/10.1007/978-1-4471-1523-6_7
Publisher Name: Springer, London
Print ISBN: 978-3-540-76160-0
Online ISBN: 978-1-4471-1523-6
eBook Packages: Springer Book Archive