On-line learning in recurrent neural networks using nonlinear Kalman filters

Proceedings of the 3rd IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2003

Volumn , Issue , 2003, Pages 802-805

  Todorovic B ^a   Stankovic M ^a   Moraga, C ^b  

^a UNIVERSITY OF NI   (Serbia)

^b TU DORTMUND UNIVERSITY   (Germany)

Author keywords

Electronic mail; Feedforward neural networks; Filters; Intelligent networks; Jacobian matrices; Neural networks; Neurons; Parameter estimation; Recurrent neural networks; State estimation

Indexed keywords

ELECTRONIC MAIL; ELECTRONIC MAIL FILTERS; EXTENDED KALMAN FILTERS; FEEDFORWARD NEURAL NETWORKS; FILTERS (FOR FLUIDS); INTELLIGENT NETWORKS; JACOBIAN MATRICES; KALMAN FILTERS; NEURAL NETWORKS; NEURONS; PARAMETER ESTIMATION; SIGNAL PROCESSING; STATE ESTIMATION;

AUTO-REGRESSIVE; DIVIDED DIFFERENCE FILTER; EXOGENOUS INPUT; NONLINEAR KALMAN FILTER; NONLINEAR STATE ESTIMATION; ONLINE LEARNING; REPRESENTATIONAL CAPABILITIES; UNSCENTED KALMAN FILTER;

RECURRENT NEURAL NETWORKS;

EID: 29744437810     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ISSPIT.2003.1341242     Document Type: Conference Paper

References (9)

1. de Freitas, J. F. G., Niranjan, M. and Gee, A.H.: "Hierarchical Bayesian-Kalman models for regularization and ARD in sequential learning," Technical Report CUED/F-INFENG/TR 307, Cambridge University., 1997.
2. th international symposium on aerospace/defence sensing, simulation and controls, Orlando, FL, 1997.
3. Julier, S. J., & Uhlmann, J. K., The Scaled Unscented Transformation, Proceedings of the IEEE American Control Conference, 8-10 May, 2002
4. Lin, T., Home, B. G., Tino, P., Lee Giles, C., Learning long-term dependencies in NARX recurrent neural networks, IEEE Transactions on Neural Networks, vol. 7. no 6, 1996
5. Nørgaard, M., Poulsen, N. K., & Ravn, O., Advances in derivative free state estimation for nonlinear systems, Technical Report, IMM-REP-1998-15, Department of Mathematical Modelling, DTU, revised April 2000.
6. Todorović, B., Stanković, M, Todorović-Zarkula, S.: Structurally adaptive RBF network in non-stationary time series prediction, In Proc. IEEE AS-SPCC, Lake Louise, Alberta, Canada, Oct. 1-4 (2000) pp. 224-229
7. Todorović, B., Stanković, M., Moraga, C.: "Extended Kalman Filter trained Recurrent Radial Basis Function Network in Nonlinear System Identification," Proc. of ICANN 2002, Spain, LNCS 2415, pp 819-824, Springer, August 2002
8. van der Merwe, R. & Wan, E. AS., Efficient Derivative-Free Kalman Filters for Online Learning, Proceedings of ESSAN, Bruges, Belgium, April 2001.
9. Williams, R.J.: "Some observations on the use of the extended Kalman filter as a recurrent network learning algorithm," Technical Report NU-CCS-92-1. Boston: Northeastern University, College of Computer Sci., 1992