Title :
Neural network training using the constructivism paradigms
Author :
Teixeira, Minhoto ; Lamas, Dkio
Author_Institution :
Dept. of Electr. Eng., UNESP, Sao Paulo, Brazil
Abstract :
The Backpropagation Algorithm (BA) is the standard method for training multilayer Artificial Neural Networks (ANN), although it converges very slowly and can stop in a local minimum. We present a new method for neural network training using the BA inspired on constuctivism, an alphabetization method proposed by Emilia Ferreiro (1985) based on Piaget philosophy. Simulation results show that the proposed configuration usually obtained a lower final mean square error, when compared with the standard BA and with the BA with momentum factor
Keywords :
backpropagation; multilayer perceptrons; Piaget philosophy; alphabetization method; backpropagation algorithm; constructivism paradigms; final mean square error; multilayer artificial neural networks; neural network training; Artificial neural networks; Backpropagation algorithms; Educational institutions; Explosives; Filtering; Filters; Mean square error methods; Multi-layer neural network; Neural networks; Roentgenium;
Conference_Titel :
Circuits and Systems, 1995., Proceedings., Proceedings of the 38th Midwest Symposium on
Conference_Location :
Rio de Janeiro
Print_ISBN :
0-7803-2972-4
DOI :
10.1109/MWSCAS.1995.504497
