SciELO - Scientific Electronic Library Online

 
vol.15 número5Influencia del Envejecimiento Higrotérmico en el Comportamiento Mecánico de Materiales Compuestos PEI - Fibra de Vidrio Sometidos a Solicitaciones TérmicasOptimización de la Producción de Gas Utilizando un Algoritmo Basado en el Concepto de Regiones de Confianza índice de autoresíndice de materiabúsqueda de artículos
Home Pagelista alfabética de revistas  

Información tecnológica

versión On-line ISSN 0718-0764

Resumen

SANCHEZ, G.; PEREZ, H.  y  NAKANO, M.. Growing Cell Neural Network using Simultaneous Perturbation. Inf. tecnol. [online]. 2004, vol.15, n.5, pp. 45-52. ISSN 0718-0764.  http://dx.doi.org/10.4067/S0718-07642004000500008.

This paper proposes a multilayer perceptron neural network (MLP) which optimizes both the matrix weights and the numbers of hidden neurons. Initially, the proposed system uses a reduced number of hidden neurons, optimizing the matrix weights by using a simultaneous perturbation algorithm. Once the network converges, its function is analyzed and if this is not as expected, a hidden neuron is added. This process is repeated until achieving the desired functioning. The results obtained show that the proposed system functions similarly to that of a conventional MLP when this has an optimal number of nodes in the hidden layer, decreasing the computational complexity during the training step.

Palabras clave : simultaneous perturbation; multilayer perceptron; growing cell network; pattern recognition.

        · resumen en Español     · texto en Español