Neural Networks’ Training Software Environment with Evolutive Adjust of Topology and Activation Functions

Authors

  • Edgar Méndez Ortiz Grupo de Investigación en Ingeniería Biomédica (GIIB), Universidad Industrial de Santander
  • Juan Sebastián Mariño Grupo de Investigación en Ingeniería Biomédica (GIIB), Universidad Industrial de Santander
  • Henry Arguello Fuentes Grupo de Investigación en Ingeniería Biomédica (GIIB), Universidad Industrial de Santander

DOI:

https://doi.org/10.18046/syt.v7i13.1009

Keywords:

Neural networks, genetic algorithms, evolutionary computation, optimization.

Abstract

This research examines two problems in the optimization in the neural networks used for most real applications: first, architectural design that involves determining the number of layers and neurons by layer, and second, the activation functions that will be should use in each of these layers. For it is developed a software tool based on genetic algorithms to find these parameters of a neural network. The developed tool allows the user to choose the algorithm used for training and also apply techniques to achieve better generalization such as the early stopping, the repetition of training and adjusting the training data to the activation functions used. Finally, the developed tool is tested into a specialized group of users who use the tool to find an optimal neural network architecture to solve a problem of identity verification through the facial image using artificial neural networks.

Author Biographies

  • Edgar Méndez Ortiz, Grupo de Investigación en Ingeniería Biomédica (GIIB), Universidad Industrial de Santander
    Bio Statement is available in Spanish
  • Juan Sebastián Mariño, Grupo de Investigación en Ingeniería Biomédica (GIIB), Universidad Industrial de Santander
    Bio Statement is available in Spanish
  • Henry Arguello Fuentes, Grupo de Investigación en Ingeniería Biomédica (GIIB), Universidad Industrial de Santander
    Bio Statement is available in Spanish

Downloads

Published

2009-08-18

Issue

Section

Original Research