The Development of Kalman Filter Learning Technique for Artificial Neural Networks

Authors

DOI:

https://doi.org/10.26636/jtit.2013.4.1235

Keywords:

Artificial Neural Networks, Kalman Filter

Abstract

The paper presents an idea of using the Kalman Filtering (KF) for learning the Artificial Neural Networks (ANN). It is shown that KF can be fully competitive or more beneficial method with comparison standard Artificial Neural Networks learning techniques. The development of the method is presented respecting selective learning of chosen part of ANN. Another issue presented in this paper is the author’s concept of automatic selection of architecture of ANN learned by means of KF based on removing unnecessary connection inside the network. The effectiveness of presented ideas is illustrated on the examples of time series modeling and prediction. Considered data came from the experiments and situ measurements in the field of structural mechanics and materials.

Downloads

Download data is not yet available.

References

[1] S. Haykin, Neural Networks: A Comprehensive Foundation. 2nd ed. New Jersey: Prentice-Hall, 1999.
View in Google Scholar

[2] S. Haykin (Ed.), Kalman Filtering and Neural Networks. New York: Wiley, 2001.
View in Google Scholar

[3] R. M. García-Gimeno, C. Hervás-Martínez, and M. I. de Silóniz, „Improving artificial neural networks with a pruning methodology and genetic algorithms for their application in microbial growth prediction in food”, Int. J. Food Microbiol., vol. 72, iss. 1-2, pp. 19-30, 2002.
View in Google Scholar

[4] P. Trebatický and J. Pospichal, „Neural Network training with extended Kalman Filter using graphics processing unit”, in Proc. 18th Int. Conf. Artif. Neural Netw. ICANN 2008, Prague, Czech Republic, 2008, LNCS 5164. Berlin-Heidelberg: Springer, 2008, pp. 198-207.
View in Google Scholar

[5] M. Aparecido de Oliveira, „An application of Neural Networks trained with Kalman Filter variants (EKF and UKF) to heteroscedastic time series forecasting”, Appl. Math. Sci., vol. 6, no. 74, pp. 3675-3686, 2012.
View in Google Scholar

[6] R. E. Kalman, „A new approach to linear filtering and prediction problems”, Trans. ASME J. Basic Eng., vol. 82, no. 1, pp. 35-45, 1960.
View in Google Scholar

[7] A. Krok, „Analysis of selected problems of structural mechanics and materials by using Artificial Neural Networks and Kalman filters”, Ph.D. Thesis, Cracow University of Technology, Cracow, Poland, 2007 (in Polish).
View in Google Scholar

[8] C. M. Bishop, Neural Networks for Pattern Recognition. New York: Oxford University Press, 1995.
View in Google Scholar

[9] L. Prechelt, „Connection pruning with static and adaptive pruning schedules”, Neurocomputing, vol. 16, no. 1, pp. 49-61, 1997.
View in Google Scholar

[10] A. Krok and Z. Waszczyszyn, „Neural prediction of response spectra from mining tremors using recurrent layered networks and Kalman filtering”, in Proc. 3rd MIT Conf. Comput. Fluid and Solid Mechanics, Cambridge, USA, 2005, K. J. Bathe, Ed., Elsevier, 2005, pp. 302-305.
View in Google Scholar

[11] A. Krok and Z. Waszczyszyn, „Kalman filtering for neural prediction of response spectra from mining tremors”, Computers and Structures, vol. 85, iss. 15-16, pp. 1257-1263, 2007.
View in Google Scholar

[12] A. Krok, „An improved Neural Kalman Filtering Algorithm in the analysis of cyclic behavior of concrete specimens”, Comput. Assist. Mech. Eng. Sci., vol. 18, pp. 275-282, 2011.
View in Google Scholar

[13] A. Krok, „Enhancing NDEKF Algorithm of Artificial Neural Network learning for simulation of hysteresis loops for superconductor”, in Computational Intelligence: Methods and Applications, L. Rutkowski, L. Zadeh, R. Tadeusiewicz, and J. Żurada, Eds. Warszawa: Akademicka Oficyna Wydawnicza EXIT, 2008.
View in Google Scholar

Downloads

Published

2013-12-30

Issue

Section

RESEARCH ARTICLES

How to Cite

[1]
A. Krok, “The Development of Kalman Filter Learning Technique for Artificial Neural Networks”, JTIT, vol. 54, no. 4, pp. 16–21, Dec. 2013, doi: 10.26636/jtit.2013.4.1235.

Most read articles by the same author(s)