Comparing evolutionary hybrid systems for design and optimization of multilayer perceptron structure along training parameters

  • Authors:
  • P. A. Castillo;J. J. Merelo;M. G. Arenas;G. Romero

  • Affiliations:
  • Departamento de Arquitectura y Tecnología de Computadoras, ETSI Informática, Universidad de Granada, Spain;Departamento de Arquitectura y Tecnología de Computadoras, ETSI Informática, Universidad de Granada, Spain;Departamento de Informática de la Universidad de Jaén, Escuela Politécnica Superior, Universidad de Jaén, Avda. Madrid, 35, E. 23071 Jaén, Spain;Departamento de Arquitectura y Tecnología de Computadoras, ETSI Informática, Universidad de Granada, Spain

  • Venue:
  • Information Sciences: an International Journal
  • Year:
  • 2007

Quantified Score

Hi-index 0.07

Visualization

Abstract

In this paper we present a comparative study of several methods that combine evolutionary algorithms and local search to optimize multilayer perceptrons: A method that optimizes the architecture and initial weights of multilayer perceptrons; another that searches for training algorithm parameters, and finally, a co-evolutionary algorithm, introduced here, that handles the architecture, the network's initial weights and the training algorithm parameters. Our aim is to determine how the co-evolutive method can obtain better results from the point of view of running time and classification ability. Experimental results show that the co-evolutionary method obtains similar or better results than the other approaches, requiring far less training epochs and thus, reducing running time.