Abstract
The article presents of accelerating neural network learning by the Back Propagation algorithm and one of its fastest modifications – the Levenberg–Marqurdt method. The learning is accelerated by introducing the ‘single-direction’ coefficient of the change of x for calculating its new values (the number of iterations is decreased by approximately 30%). Simulation results of learning neural networks by applying both the classic method and the method of accelerating the procedure are presented.
Similar content being viewed by others
References
Bishop, C. M.: Neural Networks for Pattern Recognition, Oxford university press, ISBN 0 19 853864 2, 2000.
Haykin, S. Neural Networks: A Comprehensive Foundation, Prentice Hall, New Jersey, 1999.
J. P. Webros (1974) Beyond regression: New tool for prediction and analysis in behavioral science Harvard University Cambridge, MA
D. B. Parker (1985) Learning-logic: Casting the cortex of the human brain in silicon, Technical report TR-47, Center for computational research in Economics and Management Science MIT Cambridge, MA
M. T. Hagan H. B. Demuth M. Beale (1996) Neural Network Design PWS Publishing Company Boston
D. E. Rumelhart G. E. Hinton R. J. Williams (1986) ArticleTitleLearning representation by back-propagation errors Nature 323 533–536 Occurrence Handle10.1038/323533a0
S. V. Kamarthi S. Pittner (1999) ArticleTitleAccelerating neural network training using weight extrapolations Neural Networks 12 IssueID9 1285–1299 Occurrence Handle10.1016/S0893-6080(99)00072-6 Occurrence Handle12662633
M.R. Meybodi H. Beigy (2002) ArticleTitleNew learning automata based algorithms for adaptation of backpropagation algorithm parameters International Journal of Neural Systems 12 IssueID1 45–67 Occurrence Handle11852444
D. M. Bates D. G. Watts (1988) Nonlinear Regression and Its Applications Wiley New York
P. R. Gill W. Murray M.H. Wright (1981) The Levenberg–Marquardt Method §4. 7.3 in Practical Optimization Academic Press London 136–137
K. Levenberg (1944) ArticleTitleA method for the solution of certain problems in least squares Quarterly Applied Mathematics 2 164–168
D. Marquardt (1963) ArticleTitleAn algorithm for least-squares estimation of nonlinear parameters SIAM Journal of Applied Mathematics 11 431–441 Occurrence Handle10.1137/0111030
Tai-cong, C., Da-jian H., Au, F. T. K. and Tham, L.G.: Acceleration of Levenberg– Marquardt training of neural networks with variable decay rate, Proceedings of the International Joint Conference on Neural Networks, 3 (2003) pp. 1873–1878.
Bogdan, M. W., Serdar, I., Okyay, K., Önder Efe, M.: An Algorithm for Fast Convergence in Training Neural Networks, International Joint Conference on Neural Networks (IJCNN01), Washington D.C, July 15–19, 2001.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Sotirov, S. A Method of Accelerating Neural Network Learning. Neural Process Lett 22, 163–169 (2005). https://doi.org/10.1007/s11063-005-3094-9
Issue Date:
DOI: https://doi.org/10.1007/s11063-005-3094-9