The development of Kalman Filter learning technique for Artificial Neural Networks

• Autorzy: Krok A.
• Języki publikacji: EN

Abstrakty

EN

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.

Słowa kluczowe

EN

Artificial Neural Networks; Kalman filter

• Wydawca: Instytut Łączności - Państwowy Instytut Badawczy
• Czasopismo: Journal of Telecommunications and Information Technology
• Rocznik: 2013
• Tom: nr 4
• Strony: 16--21
• Opis fizyczny: Bibliogr. 13 poz., rys., tab.

Twórcy

autor

Krok A.

• Faculty of Physics, Mathematics and Computer Science, Tadeusz Kościuszko Cracow University of Technology, Warszawska st 24, 31-155 Cracow, Poland

Bibliografia

• [1] S. Haykin, Neural Networks: A Comprehensive Foundation. 2nd ed. New Jersey: Prentice-Hall, 1999.
• [2] S. Haykin (Ed.), Kalman Filtering and Neural Networks. New York: Wiley, 2001.
• [3] R. M. Garc´ıa-Gimeno, C. Herv´as-Mart´ınez, M. I. de Siloniz, “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.
• [4] P. Trebatick´y, 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.
• [5] M. Aparecido de Oliveira, “An application of Neural Networks trained with Kalman Filter variants (EKF and UKF) to heteroscedastic time series forecasting”, Appl. Mathem. Sci., vol. 6, no. 74, pp. 3675–3686, 2012.
• [6] R. E. Kalman, “A new approach to linear filtering and prediction problems”, Trans. ASME J. Basic Engin., vol. 82, no. 1, pp. 35–45, 1960.
• [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).
• [8] C. M. Bishop, Neural Networks for Pattern Recognition., New York: Oxford University Press, 1995.
• [9] L. Prechelt, “Connection pruning with static and adaptive pruning schedules”, Neurocomputing, vol. 16, no. 1, pp. 49–61, 1997.
• [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 Me- chanics, Cambridge, USA, 2005, J.-K. Bathe, Ed., Elsevier, 2005, pp. 302–305.
• [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.
• [12] A. Krok, “An improved Neural Kalman Filtering Algorithm in the analysis of cyclic behavior of concrete specimens”, Comp. Assist. Mechan. Engin. Sciences, vol. 18, pp. 275–282, 2011.
• [13] A. Krok, “Enhancing NDEKF Algorithm of Artificial Neural Network learning for simulation o 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.