Geodesic
Neural networks using Bayesian training
Kybernetika, Tome 39 (2003) no. 5, pp. 511-520 Cet article a éte moissonné depuis la source Czech Digital Mathematics Library

Voir la notice de l'article

Bayesian probability theory provides a framework for data modeling. In this framework it is possible to find models that are well-matched to the data, and to use these models to make nearly optimal predictions. In connection to neural networks and especially to neural network learning, the theory is interpreted as an inference of the most probable parameters for the model and the given training data. This article describes an application of Neural Networks using the Bayesian training to the problem of Predictions of Geomagnetic Storms.
Bayesian probability theory provides a framework for data modeling. In this framework it is possible to find models that are well-matched to the data, and to use these models to make nearly optimal predictions. In connection to neural networks and especially to neural network learning, the theory is interpreted as an inference of the most probable parameters for the model and the given training data. This article describes an application of Neural Networks using the Bayesian training to the problem of Predictions of Geomagnetic Storms.
Classification : 62F15, 62M45, 86A25, 86A32
Keywords: neural network; Bayesian probability theory; geomagnetic storm; prediction 
@article{KYB_2003_39_5_a1,
     author = {Andrejkov\'a, Gabriela and Levick\'y, Miroslav},
     title = {Neural networks using {Bayesian} training},
     journal = {Kybernetika},
     pages = {511--520},
     year = {2003},
     volume = {39},
     number = {5},
     mrnumber = {2042338},
     zbl = {1248.62174},
     language = {en},
     url = {http://geodesic.mathdoc.fr/item/KYB_2003_39_5_a1/}
}
TY  - JOUR
AU  - Andrejková, Gabriela
AU  - Levický, Miroslav
TI  - Neural networks using Bayesian training
JO  - Kybernetika
PY  - 2003
SP  - 511
EP  - 520
VL  - 39
IS  - 5
UR  - http://geodesic.mathdoc.fr/item/KYB_2003_39_5_a1/
LA  - en
ID  - KYB_2003_39_5_a1
ER  - 
%0 Journal Article
%A Andrejková, Gabriela
%A Levický, Miroslav
%T Neural networks using Bayesian training
%J Kybernetika
%D 2003
%P 511-520
%V 39
%N 5
%U http://geodesic.mathdoc.fr/item/KYB_2003_39_5_a1/
%G en
%F KYB_2003_39_5_a1
Andrejková, Gabriela; Levický, Miroslav. Neural networks using Bayesian training. Kybernetika, Tome 39 (2003) no. 5, pp. 511-520. http://geodesic.mathdoc.fr/item/KYB_2003_39_5_a1/

[1] Anděl J.: Mathematical Random Events (in Czech). Matfyzpress, Praha 2002

[2] Andrejková G., Azorová, J., Kudela K.: Artificial neural networks in prediction $D_{st}$ index. Proc. 1st Slovak Neural Network Symposium, ELFA, Košice, 1996, pp. 51–59

[3] Andrejková G., Tóth, H., Kudela K.: Fuzzy neural networks in the prediction of geomagnetic storms. Proc. “Artificial Intelligence in Solar-Terrestrial Physics”, Publisher European Space Agency, Lund 1997, pp. 173–179

[4] Bernardo J. M., Smith A. F. M.: Bayesian Theory. Wiley, New York 2002 | MR | Zbl

[5] Darwiche A.: A differential approach to inference in Bayesian networks. J. Assoc. Comput. Mach. 50 (2003), 2, 280–305 | DOI | MR

[6] Dechter R., Rish I.: Mini-buckets: A general scheme for bounded inference. J. Assoc. Comput. Mach. 50 (2003), 3, 107–153 | DOI | MR

[7] Hassoun M. H.: Fundamentals of Artificial Neural Networks. MIT Press, Cambridge, MA 1995 | Zbl

[8] Hertz J., Krogh, A., Palmer R. G.: Introduction to the Theory of Neural Computation (Santa Fe Institute Studies in the Science of Complexity, Vol. 1). Addison-Wesley, Reading 1991 | MR

[9] Levický M.: Neural Networks in the Analysis and the Document Classification. Diploma Thesis, P. J. Šafárik University, Košice, 2002

[10] Lundstedt H., Wintoft P.: Prediction of geomagnetic storms from solar wind data with the use of a neural network. Ann. Geophysicae 12, EGS-Springer-Verlag, 1994, pp. 19–24 | DOI

[11] MacKay D. J. C.: Bayesian Methods for Neural Networks: Theory and Applications. Neural Network Summer School, 1995

[12] MacKay D. J. C.: A practical Bayesian framework for backprop networks. Neural Computation 4, pp. 448–472 | DOI

[13] Müller P., Insua D. R.: Issues in Bayesian analysis of neural network model. Neural Computation 10, pp. 749–770 | DOI

[14] Neal R. M.: Probabilistic Inference Using Markov Chain Monte Carlo Methods. Technical Report CRG-TR-93-1, University of Toronto, 1993

[15] Neal R. M.: Bayesian Training of Backpropagation Networks by the Hybrid Monte Carlo Method. Technical Report CRG-TR-92-1, University of Toronto, 1992

[16] Schlesinger M. I., Hlaváč V.: Deset přednášek z teorie statistického a strukturního rozpoznávaní. ČVUT, Praha 1999