Evolving Multilayer Perceptrons

  • Authors:

  • P. A. Castillo;J. Carpio;J. J. Merelo;A. Prieto;V. Rivas;G. Romero

  • Affiliations:

  • Department of Architecture and Computer Technology, University of Granada, Campus de Fuentenueva, E. 18071 Granada, Spain.;Department of Architecture and Computer Technology, University of Granada, Campus de Fuentenueva, E. 18071 Granada, Spain.;Department of Architecture and Computer Technology, University of Granada, Campus de Fuentenueva, E. 18071 Granada, Spain.;Department of Architecture and Computer Technology, University of Granada, Campus de Fuentenueva, E. 18071 Granada, Spain.;Department of Computer Science, University of Jaén, Avda. Madrid, 35, E. 23071 Jaén, Spain.;Department of Architecture and Computer Technology, University of Granada, Campus de Fuentenueva, E. 18071 Granada, Spain.

  • Venue:
  • Neural Processing Letters
  • Year:
  • 2000

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper proposes a new version of a method (G-Prop, genetic backpropagation) that attempts to solve the problem of finding appropriate initial weights and learning parameters for a single hidden layer Multilayer Perceptron (MLP) by combining an evolutionary algorithm (EA) and backpropagation (BP). The EA selects the MLP initial weights, the learning rate and changes the number of neurons in the hidden layer through the application of specific genetic operators, one of which is BP training. The EA works on the initial weights and structure of the MLP, which is then trained using QuickProp; thus G-Prop combines the advantages of the global search performed by the EA over the MLP parameter space and the local search of the BP algorithm. The application of the G-Prop algorithm to several real-world and benchmark problems shows that MLPs evolved using G-Prop are smaller and achieve a higher level of generalization than other perceptron training algorithms, such as QuickPropagation or RPROP, and other evolutive algorithms. It also shows some improvement over previous versions of the algorithm.