Avaliação Estatística de Métodos de Poda Aplicados em Neurônios intermediários da rede neural MLP (Statistical Evaluation of Pruning Methods Applied in Hidden Neurons of the MLP Neural Network)

Miriam Rodrigues Silvestre (miriam@fct.unesp.br)1, Lee Luan Ling (lee@decom.fee.unicamp.br)2

1Depto. de Matemática, Estatística e Computação, Universidade Estadual Paulista, Presidente Prudente-SP, Brazil
2Depto. de Comunicações, Universidade Estadual de Campinas, Campinas-SP, Brazil

This paper appears in: Revista IEEE América Latina

Publication Date: June 2006
Volume: 4,   Issue: 4 
ISSN: 1548-0992

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.

Index Terms:
iterative pruning method, multilayer perceptron neural network, MLP neural network, pattern recognition, Friedman’s test   

Documents that cite this document
This function is not implemented yet.

[PDF Full-Text (219)]