Abstract
This paper addresses stability issues of the learning process when the distal-in-space approach is used to learn inverse models of dynamical systems. Both direct and indirect versions of this approach are analysed for linear plants. It is shown that none of them is suitable when the plant is an unstable non-minimum phase system. When the plant is unstable, an additional problem must be solved: stability of the control system must be guaranteed at the beginning of the learning process. We do not deal with this additional problem but concentrate on the stability and the speed of the learning process. We propose solutions in the case of the direct version, applied to non-minimum phase stable plants. These solutions are compared on a linear plant control problem. Extensions to nonlinear systems are briefly discussed.
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
K.J. Astrom and B. Wittenmark. Adaptive Control Addison-Wesley, Reading, MA, 1989.
M.I. Jordan and D.E. Rumelhart. Forward models: Supervised learning with a distal teacher. Cognitive Science, 16:307–354, 1992.
M. Saerens, J-M. Renders, and H. Bersini. Neural controllers based on backpropagation algorithm. In M. Gupta and N. Sinha, editors, IEEE Press Book on Intelligent Control IEEE Press, 1993.
W.H. Schiffman and H.W. Geffers. Adaptive control of dynamic systems by back propagation networks. Neural Networks, 6:517–524, 1993.
A. Toudeft. Neural control of nonlinear non-minimum phase dynamical systems. In D.W. Pearson, N.C. Steele, and R.F. Albrecht, editors, Artificial Neural Networks and Genetic Algorithms, Springer-Verlag, Wien New York, 1995.
A. Toudeft, P. Kosuth, and P. Gallinari. A PID neural controller for unstable delayed linear systems. In Proc. ICANN’94, 1994.
D.A. White and D.A. Sofge. Handbook of Intelligent Control: Neural, Fuzzy and Adaptive Approaches. Van Nostrand Reinhold, 1992.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 1998 Springer-Verlag Wien
About this paper
Cite this paper
Toudeft, A., Gallinari, P. (1998). Distal Learning for Inverse Modeling of Dynamical Systems. In: Artificial Neural Nets and Genetic Algorithms. Springer, Vienna. https://doi.org/10.1007/978-3-7091-6492-1_131
Download citation
DOI: https://doi.org/10.1007/978-3-7091-6492-1_131
Publisher Name: Springer, Vienna
Print ISBN: 978-3-211-83087-1
Online ISBN: 978-3-7091-6492-1
eBook Packages: Springer Book Archive