Feasibility of random basis function approximators for modeling and control

Proceedings of the IEEE International Conference on Control Applications

Volumn , Issue , 2009, Pages 1391-1396

  Tyukin, Ivan Yu ^a,b,c   Prokhorov, Danil V ^d  

^a UNIVERSITY OF LEICESTER   (United Kingdom)

^b SAINT PETERSBURG ELECTROTECHNICAL UNIVERSITY LETI   (Russian Federation)

^c RIKEN BRAIN SCIENCE INSTITUTE   (Japan)

^d America   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

BASIS FUNCTIONS; COMPUTATIONAL RESOURCES; ERROR RATE; MODELING AND CONTROL;

APPROXIMATION THEORY;

NEURAL NETWORKS;

EID: 74049124579     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/CCA.2009.5281061     Document Type: Conference Paper

References (20)

1. A. R. Barron. Universal approximation bounds for superposition of a sigmoidal function. IEEE Trans. on Information Theory, 39(3):930-945, 1993.
2. G. Cybenko. Approximation by superpositions of a sigmoidal function. Math. of Control, Signals and Systems, 2:303-314, 1989.
3. S. Haykin. Neural Networks: A Comprehensive Foundation. Prentice Hall, 1999.
4. K. Hornik, K. Stinchcombe, and H. White. Universal approximation of an unknown function and its derivatives using multilayer neural networks. Neural Networks, (3):551-560, 1990.
5. B. Igelnik and Y.-H. Pao. Stochastic choice of basis functions in adaptive function approximation and the functional-link net. IEEE Trans. Neural Networks, 6(6):1320-1329, 1995.
6. J.-Y. Lin and W. S. Chow. Comments on "Stochastic choice of basis functions in adaptive function approximation and the functional-link net". IEEE Trans. Neural Networks, 8(2):452-454, 1997.
7. M. French, Cs. Szepesvari and E. Rogers, Uncertainty, Performance, and Model Dependency in Approximate Adaptive Nonlinear Control. IEEE Trans. Automat. Contr., 45(2):353-358, 2000.
8. P. He and S. Jagannathan. Reinforcement learning based output feedback control of nonlinear systems with input contraints. IEEE Trans. Systems, Man and Cybernetics, 35(1):150-154, 2005.
9. O. Kuljaca and S. Tesnjak and V. Koroman. Performance Analysis of Adaptive Neural Network Frequency Controller for Thermal Power Systems. Proceedings of the 9th WSEAS International Conference on Automatic Control, Modeling & Simulation, Istanbul, Turkey, May 27-29, 2007, pp. 127-132.
10. F. Lewis and S. Ge. Neural Networks in Feedback Control Systems. In M. Kutz (Ed.) Mechanical Engineers' Handbook, Volume 2, Third Edition, Wiley, 2006.
11. J. Sarangapani. Neural Network Control of Nonlinear Discrete-Time Systems. Control Engineering Series, CRC Press, 2006.
12. F. Lewis and J. Campos and R. Selmic Neuro-fuzzy control of industrial systems with actuator nonlinearities. SIAM, 2002.
13. W. Liu and J. Sarangapani and G. Venayagamoorthy and L. Liu and D. Wunsch and M. Crow and D. Cartes. Decentralized Neural Network-based Excitation Control of Large-scale Power Systems. International Journal of Control, Automation, and Systems, vol. 5, no. 5, pp. 526-538, October 2007.
14. L. K. Jones. A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training. The Annals of Statistics, 20(1):608-613, 1992.
15. Ai-Poh Loh, A.M. Annaswamy, and F.P. Skantze. Adaptation in the presence of general nonlinear parameterization: An error model approach. IEEE Trans. on Automatic Control, 44(9):1634-1652, 1999.
16. J. Park and I. W. Sandberg. Approximation and radial basis function networks. Neural Computation, 5(2):305-316, 1993.
17. D.V. Prokhorov, V.A. Terekhov, and I.Yu. Tyukin. On the applicability conditions for the algorithms of adaptive control in nonconvex problems. Automation and Remote Control, 63(2):262-279, 2002.
18. I.Yu. Tyukin, D.V. Prokhorov, and C. van Leeuwen. Adaptation and parameter estimation in systems with unstable target dynamics and nonlinear parametrization. IEEE Trans. on Automatic Control, 52(9):1543-1559, 2007.
19. I.Yu. Tyukin, D.V. Prokhorov, and V.A. Terekhov. Adaptive control with nonconvex parameterization. IEEE Trans. on Automatic Control, 48(4):554-567, 2003.
20. L. A. Feldkamp, D. V. Prokhorov, C. F. Eagen, and F. Yuan. Enhanced multi-stream Kalman filter training for recurrent networks. In J. Suykens and J. Vandewalle (eds), Nonlinear Modeling: Advanced Black-Box Techniques, pp. 29-53. Kluwer Academic Publishers, 1998.