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.
Publisher
National Institute of Telecommunications
Reference13 articles.
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.