Avaliação estatística de métodos de poda aplicados em neurônios intermediários da rede neural MLP
IEEE Latin America Transactions, v. 4, n. 4, p. 249-256, 2006.
Silvestre, Miriam Rodrigues
Ling, Lee Luan
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.
Showing items related by title, author, creator and subject.
A suplementação dietética de taurina atenua a elevação da pressão arterial em prole de ratas submetidas à ingestão hipoproteica durante a gestação = repercussão sobre a função renal e a citometria neural do tronco encefálico = Taurine supplementation attenuates the blood pressure rise in offspring of rats submitted to hypoproteic intake during pregnancy : impact on renal function and neural cytometry of brain stem Scabora, José Eduardo, 1971-
Estudo da produção de biossurfactante, usando resíduos agroindustriais com desenvolvimento de modelos estatísticos e sensor virtual por modelagem neural = Study of biosurfactant production, using agro-industrial waste with development of statistical models and soft sensor by artificial neural network Santos, Brunno Ferreira dos, 1986-