Artículos de revistas
Statistical Evaluation Of Pruning Methods Applied In Hidden Neurons Of The Mlp Neural Network [avaliação Estatística De Métodos De Poda Aplicados Em Neurônios Intermediários Da Rede Neural Mlp]
Registro en:
Ieee Latin America Transactions. , v. 4, n. 4, p. 249 - 256, 2006.
15480992
10.1109/TLA.2006.4472121
2-s2.0-77958181102
Autor
Silvestre M.R.
Ling L.L.
Institución
Resumen
There are several papers on pruning methods in the artificial neural networks area. However, with rare exceptions, none of them presents an appropriate statistical evaluation of such methods. In this article, we proved statistically the ability of some methods to reduce the number of neurons of the hidden layer of a multilayer perceptron neural network (MLP), and to maintain the same landing of classification error of the initial net. They are evaluated seven pruning methods. The experimental investigation was accomplished on five groups of generated data and in two groups of real data. Three variables were accompanied in the study: apparent classification error rate in the test group (REA); number of hidden neurons, obtained after the application of the pruning method; and number of training/retraining epochs, to evaluate the computational effort. The non-parametric Friedman's test was used to do the statistical analysis. 4 4 249 256 Reed, R., Pruning algorithms - A survey (1993) IEEE Trans. Neural Networks, 4 (5), pp. 740-747 Karnin, E.D., A simple procedure for pruning back-propagation trained neural networks (1990) IEEE Trans. Neural Networks, 1 (2), pp. 239-242 Lecun, Y., Denker, J.S., Solla, S.A., Optimal brain damage (1990) Advances in Neural Information Processing, 2, pp. 598-605. , D.S. Touretzky, Ed. Denver Mao, J., Mohiuddin, K., Jain, A.K., Parsimonious network design and feature selection through node pruning (1994) Proc. International Conf. Pattern Recognition, pp. 622-624 Park, Y.R., Murray, T.J., Chen, C., Predicting sun spots using a layered perceptron neural network (1996) IEEE Trans. Neural Networks, 7 (2), pp. 501-505 Murase, K., Matsunaga, Y., Nakade, Y., A backpropagation algorithm which automatically determines the number of association units Proc. International Conf. Neural Networks, pp. 783-788. , 199 Castellano, G., Fanelli, A.M., Pelillo, M., An iterative pruning algorithm for feedforward neural networks (1997) IEEE Trans. Neural Networks, 8 (3), pp. 519-531 Silvestre, M.R., Ling, L.L., Reduzindo a arquitetura de uma rede via gap das saliências dos neurônios (1998) Anais V Simpósio Brasileiro de Redes Neurais, pp. 91-96 Silvestre, M.R., Ling, L.L., Optimization of neural classifiers based on Bayesian decision boundaries and idle neurons pruning (2002) Proc. International Conf. Pattern Recognition, pp. 387-390 Murphy, P.M., Aha, D.W., (1994) UCI Repository of Machine Learning Databases, , http://www.ics.uci.edu/~mlearn/MLRepository.html, 1994. Irvine, CA: University of California, Department of Information and Computer Science [Online]. Available Haykin, S., (1994) Neural Networks: A Comprehensive Foundation, p. 696. , New Jersey: Wiley Pontes, A.C.F., (2002) Obtenção Dos Níveis de Significância para Os Testes de Kruskal-Wallis, Friedman e Comparações Múltiplas Não-paramétricas, , Dissertação (Mestrado) - Dep. de Ciências Exatas, Escola Superior de Agricultura Luiz de Queiroz, Universidade de São Paulo, Piracicaba Björck, A., Elfving, T., Accelerated projection methods for computing in artificial neural networks (1979) BIT, 19, pp. 145-163