Abstract
This work presents a technique that integrates the backpropagation learning method with a method to calculate the initial weights in order to train the Multilayer Perceptron Model. The method to calculate the initial weights of the MLP is based on the quality of similarity measure proposed on the framework of the extended Rough Set Theory. Experimental results show that the proposed initialization method performs better than other methods used to calculate the weight of the features, so it is an interesting alternative to the conventional random initialization.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Hocenski, Z., Antunovic, M., Filko, D.: Accelerated Gradient Learning Algorithm for Neural Network Weights Update. In: Lovrek, I., Howlett, R.J., Jain, L.C. (eds.) KES 2008, Part I. LNCS (LNAI), vol. 5177, pp. 49–56. Springer, Heidelberg (2008)
Kim, M., Choi, C.: A New Weight Initialization Method for the MLP with the BP in Multiclass Classification Problems. Neural Processing Letters 6, 11–23 (1997)
Fu, X., Zhang, S., Pang, Z.: A Resource Limited Immune Approach for Evolving Architecture and Weights of Multilayer Neural Network. In: Tan, Y., Shi, Y., Tan, K.C. (eds.) ICSI 2010. LNCS, vol. 6145, pp. 328–337. Springer, Heidelberg (2010)
Almeida, L.M., Ludermir, T.B.: An Evolutionary Approach for Tuning Artificial Neural Network Parameters. In: Corchado, E., Abraham, A., Pedrycz, W. (eds.) HAIS 2008. LNCS (LNAI), vol. 5271, pp. 156–163. Springer, Heidelberg (2008)
Hornik, K., et al.: Multilayer feedforward neural network are universal approximators. Neural Networks 2, 359–366 (1989)
Faúndez-Zanuy, M.: Nonlinear Speech Processing: Overview and Possibilities in Speech Coding. In: Chollet, G., Esposito, A., Faúndez-Zanuy, M., Marinaro, M. (eds.) Nonlinear Speech Modeling and Applications. LNCS (LNAI), vol. 3445, pp. 15–42. Springer, Heidelberg (2005)
Kim, Y.K., Ra, J.B.: Weight value initialization for improving training speed in the backpropagation networks. In: Kim, Y. (ed.) IEEE International Joint Conference on NN, pp. 2396–2401 (1991)
Drago, G., Ridella, S.: Statistically controlled activation weight initialization. IEEE Transaction on Neural Networks 3(4), 627–631 (1992)
Wessels, L., Barnard, E.: Avoiding false local minima by proper initialization. IEEE Transaction on Neural Networks 3(6), 899–905 (1992)
Denoeux, T., Lengelle, R.: Initializing back propagation networks with prototypes. Neural Networks 6, 351–363 (1993)
Thimm, G., Fiesler, E.: High-order and multilayer perceptron initialization. IEEE Trans. on Neural Networks 2, 349–359 (1997)
Almeida, L.M., Ludermir, T.B.: An Evolutionary Approach for Tuning Artificial Neural Network Parameters. In: Corchado, E., Abraham, A., Pedrycz, W. (eds.) HAIS 2008. LNCS (LNAI), vol. 5271, pp. 156–163. Springer, Heidelberg (2008)
Adam, S., Karras, D.A., Vrahatis, M.N.: Revisiting the Problem of Weight Initialization for Multi-Layer Perceptrons Trained with Back Propagation. In: Köppen, M., Kasabov, N., Coghill, G. (eds.) ICONIP 2008. LNCS, vol. 5507, pp. 308–315. Springer, Heidelberg (2009)
Nieminen, P., Kärkkäinen, T.: Ideas about a Regularized MLP Classifier by Means of Weight Decay Stepping. In: Kolehmainen, M., Toivanen, P., Beliczynski, B. (eds.) ICANNGA 2009. LNCS, vol. 5495, pp. 32–41. Springer, Heidelberg (2009)
Rumelhart, D.E., Hilton, G.E., Williams, R.J.: Learning Representations by Backpropagation Errors. Nature 323, 533–536 (1986)
Rocha, M., Cortez, P.C., Neves, J.: Simultaneous Evolution of Neural Network Topologies and Weights for Classification and Regression. In: Cabestany, J., Prieto, A.G., Sandoval, F. (eds.) IWANN 2005. LNCS, vol. 3512, pp. 59–66. Springer, Heidelberg (2005)
Filiberto, Y., Bello, R., Caballero, Y., Larrua, R.: Using PSO and RST to Predict the Resistant Capacity of Connections in Composite Structures. In: González, J.R., Pelta, D.A., Cruz, C., Terrazas, G., Krasnogor, N. (eds.) NICSO 2010. SCI, vol. 284, pp. 359–370. Springer, Heidelberg (2010)
Pawlak, Z.: Rough Sets. International Journal of Computer and Information Sciences 11, 341–356 (1982)
Skowron, A.: Logic, algebra and computer science, Helena Rasiowa and Cecylia Rauszer in Memoriam. In: Bulletin of the Section of Logic, pp. 1–215 (1996)
Slowinski, R., Vanderpooten, D.: A generalized definition of rough approximations based on similarity. IEEE Transactions on Data and Knowledge Engineering 12(2), 331–336 (2000)
Pawlak, Z., Skowron, A.: Rough sets: Some extensions. Information Sciences 177, 28–40 (2007)
Kennedy, J., Eberhart, R.C.: Particle swarm optimization. In: Proceedings of the 1995 IEEE International Conference on Neural Networks. IEEE Service Center, Piscataway (1995)
Asuncion, A., Newman, D.: UCI machine learning repository. A study of the behaviour of several methods for balancing machine learning training data. SIGKDD Explorations 6(1), 20–29 (2007)
Mitchell, T.: Machine Learning. In: Science/Engineering/Math., McGraw Hill, Portland (1997)
Demsar, J.: Statistical comparisons of classifiers over multiple data sets. Journal of Machine Learning Research (7), 1–30 (2006)
Myles, A., et al.: Estimating MLP generalisation ability without a test set using fast, approximate Leave-one-out cross-validation. Neural Computing and Applications 5, 134–151 (1997)
Wettschereckd, D.: A description of the mutual information approach and the variable similarity metric. Technical report, Artificial Intelligence Research Division. German National Research Center for Computer Science, Sankt Augustin (1995)
Kononenko, I.: Estimating attributes: Analysis and extensions of RELIEF. In: Proc. European Conf. on Machine Learning (1994)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Filiberto Cabrera, Y., Bello Pérez, R., Mota, Y.C., Jimenez, G.R. (2011). Improving the MLP Learning by Using a Method to Calculate the Initial Weights of the Network Based on the Quality of Similarity Measure. In: Batyrshin, I., Sidorov, G. (eds) Advances in Soft Computing. MICAI 2011. Lecture Notes in Computer Science(), vol 7095. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-25330-0_31
Download citation
DOI: https://doi.org/10.1007/978-3-642-25330-0_31
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-25329-4
Online ISBN: 978-3-642-25330-0
eBook Packages: Computer ScienceComputer Science (R0)