On a neural approximator to ODEs

IEEE Transactions on Neural Networks

Volumn 19, Issue 3, 2008, Pages 539-543

  Filici, Cristian ^a,b  

^a Facultad de Ciencias Exactas Físicas y Naturales   (Argentina)

^b UNIVERSIDAD DE BUENOS AIRES   (Argentina)

Author keywords

Error bound; Neural network; Ordinary differential equation (ODE); Stability

Indexed keywords

APPROXIMATION THEORY; ASYMPTOTIC STABILITY; ORDINARY DIFFERENTIAL EQUATIONS; PROBLEM SOLVING;

ERROR BOUND; NEURAL APPROXIMATOR;

NEURAL NETWORKS;

ALGORITHM; ANIMAL; ARTICLE; ARTIFICIAL NEURAL NETWORK; BIOLOGICAL MODEL; HUMAN; NONLINEAR SYSTEM;

ALGORITHMS; ANIMALS; HUMANS; MODELS, NEUROLOGICAL; NEURAL NETWORKS (COMPUTER); NONLINEAR DYNAMICS;

EID: 40949086430     PISSN: 10459227     EISSN: None     Source Type: Journal    
DOI: 10.1109/TNN.2007.915109     Document Type: Article

References (20)

1. P. Henrici, Discrete Variable Methods in Ordinary Differential Equations. New York: Wiley, 1962.
2. K. Hornik, M. Stinchcombe, and H. White, "Multilayer feedforwad networks are universal approximators," Neural Netw., no. 2, 1989.
3. K. Hornik, M. Stinchcombe, and H. White, "Universal approx. of an unknown mapping and its derivatives using multilayer feedforward networks," Neural Netw., no. 3, 1990.
4. K. Hornik, "Approximation capabilities of multilayer feedforward networks," Neural Netw., no. 4, pp. 251-257, 1991.
5. K. O. Funahashi, "On the approximate realization of continuous mappings by neural networks," Neural Netw., no. 2, pp. 183-192, 1989.
6. G. Cybenko, "Approximation by superpositions of a sigmoidal function," Math. Control Signal Syst., no. 2, pp. 303-314, 1989.
7. I. Lagaris, A. Likas, and D. Fotiadis, "Artificial neural networks for solving ordinary and partial differential equations," IEEE Trans. Neural Netw., vol. 9, no. 5, pp. 987-1000, Sep. 1998.
8. I. Lagaris, A. Likas, and D. Papageorgiou, "Neural-network methods for solving boundary value problems with irregular boundaries," IEEE Trans. Neural Netw., vol. 11, no. 5, pp. 1041-1049, Sep. 2000.
9. Y. Tassa and T. Erez, "Least squares solutions of the HJB equation with neural network value-function approximators," IEEE Trans. Neural Netw., vol. 18, no. 4, pp. 1031-1041, Jul. 2007.
10. P. Ramuhalli, L. Upda, and S. S. Upda, "Finite-element neural networks for solving differential equations," IEEE Trans. Neural Netw., vol. 16, no. 6, pp. 1381-1392, Nov. 2006.
11. J. Nocedal and S. Wright, Numerical Optimization, ser. Series in Operations Research. New York: Springer-Verlag, 1999.
12. B. Garbow, K. Hillstrom, and J. More, "Documentation for MINPACK subroutine LMDER," Argonne N. Lab., Mar. 1980, Tech. Rep..
13. T. Chen, D. Han, F. Au, and L. Tham, "Acceleration of Levenberg-Marquardt training of neural networks with variable decay rate," in Proc. Int. Joint Conf. Neural Netw., Jul. 2003, vol. 3, pp. 1873-1878.
14. L. Behera, S. Kumar, and A. Patnaik, "On adaptive learning rate that guarantees convergence in feedforward networks," IEEE Trans. Neural Netw., vol. 17, no. 5, pp. 1116-1125, Sep. 2006.
15. J. Slotine and Y. Li, Applied Non Linear Control. Englewood Cliffs, NJ: Prentice-Hall, 1991.
16. E. Fehlberg, "Classical fifth-, sixth-, seventh- and eighth-order Runge-Kutta," NASA, Washington, DC, Tech. Rep. 287, 1968.
17. E. Hairer, S. Norsett, and G. Wanner, Solving Ordinary Differential Equations I: Nonstiff Problems, ser. Springer Series in Computational Mathematics. Berlin, Germany: Springer-Verlag, 1987.
18. L. Shampinea and M. Gordon, Computer Solution of Ordinary Differential Equations: The Initial Value Problem. San Francisco, CA: W. H. Freeman, 1975.
19. H. Khalil, Nonlinear Systems, 2nd ed. Upper Saddle River, NJ: Prentice-Hall, 1996.
20. P. Zadunaisky, "On the estimation of errors propagated in the numerical integration of ordinary differential equations," Numer. Math., vol. 27, pp. 21-39, 1976.