A local linearized least squares algorithm for training feedforward neural networks

IEEE Transactions on Neural Networks

Volumn 11, Issue 2, 2000, Pages 487-495

  Stan, Octavian ^a   Kamen, Edward ^a  

^a GEORGIA INSTITUTE OF TECHNOLOGY   (United States)

Author keywords

Extended Kalman filter; Feedforward multilayer perceptrons; Least squares algorithms; Localized algorithms; Neural networks

Indexed keywords

ALGORITHMS; BACKPROPAGATION; CONVERGENCE OF NUMERICAL METHODS; IDENTIFICATION (CONTROL SYSTEMS); KALMAN FILTERING; LEARNING SYSTEMS; LEAST SQUARES APPROXIMATIONS; LINEAR CONTROL SYSTEMS;

DECOUPLED EXTENDED KALMAN FILTER ALGORITHM (DEKF); GLOBAL EXTENDED KALMAN FILTER (GEKF) ALGORITHMS; LOCAL LINEARIZED LEAST SQUARES (LLLS); MULTIPLE EXTENDED KALMAN ALGORITHMS (MEKA);

FEEDFORWARD NEURAL NETWORKS;

EID: 0033748613     PISSN: 10459227     EISSN: None     Source Type: Journal    
DOI: 10.1109/72.839017     Document Type: Article

References (13)

1. S. Singhal and L. Wu, "Training feedforward networks with the extended Kalman algorithm," in ICASSP-89: 1989 Int. Conf. Acoust., Speech, Signal Processing, vol. 2, 1989, pp. 1187-1190.
2. S. Shah and F. Palmieri, "MEKA - A fast, local algorithm for training feedforward neural networks," in IJCNN Int. Joint Conf. Neural Networks, vol. 3, 1990, pp. 41-46.
3. S. Shah, F. Palmieri, and M. Datum, "Optimal filtering algorithms for fast learning in feedforward neural networks," Neural Networks, vol. 5, pp. 779-787, 1991.
4. G. V. Puskorius and L. A. Feldkamp, "Decoupled extended Kalman filter training of feedforward layered networks," in Int. Joint Conf. Neural Networks, vol. 1, 1991, pp. 771-777.
5. S. C. Douglas and T. H.-Y. Meng, "Linearized least-squares training of multilayer feedforward neural networks," in Int. Joint Conf. Neural Networks, vol. 1, 1991, pp. 307-312.
6. G. V. Puskorius and L. A. Feldkamp, "Neurocontrol of nonlinear dynamical systems with Kalman filter trained recurrent networks," IEEE Trans. Neural Networks, vol. 5, pp. 279-297, Mar. 1994.
7. F. Yuan, G. V. Puskorius, L. A. Feldkamp, L. I. Davis Jr., M. A. Bayoumi, and W. K. Jenkins, "Neural-network control of a four-wheel ABS model," in Proc. 37th Midwest Symp. Circuits Syst., vol. 2, 1994, pp. 1503-1506.
8. G. V. Puskorius and L. A. Feldkamp, "Extensions and enhancements of decoupled extended Kalman filter training," in IEEE Int. Conf. Neural Networks, vol. 3, 1997, pp. 1879-1883.
9. T. L. Ruchti, R. H. Brown, and J. J. Garside, "A parameter estimation approach to artificial neural-network weight selection for nonlinear system identification," in 1st IEEE Conf. Contr. Applicat., vol. 1, 1992, pp. 565-570.
10. F. Fnaiech, D. Bastard, V. Buzenac, R. Settineri, M. Najim, M. J. J. Holt, C. F. N. Cowan, P. M. Grant, and W. A. Sandham, "A fast Kalman filter-based new algorithm for training feedforward neural networks," in Proc. EUSIPCO'94. 7th European Signal Processing Conf. Signal Processing VII, Theories Applicat., 1994.
11. S. Murtuza and S. F. Chorian, "Node decoupled extended Kalman filter based learning algorithm for neural networks," in Proc. 1994 IEEE Int. Symp. Intell. Contr., 1994, pp. 364-369.
12. T. Kailath, Linear Systems. Englewood Cliffs, NJ: Prentice-Hall, p. 656.
13. Y. Li, R. L. Mahajan, and N. Kimanesh, "Fine pitch stencil printing process modeling and optimization," J. Electron. Packaging, pp. 1-6, Mar. 1996.