Evolving Multilayer Perceptrons

  title={Evolving Multilayer Perceptrons},
  author={Pedro {\'A}ngel Castillo Valdivieso and J. Carpio Ca{\~n}ada and Juan Juli{\'a}n Merelo Guerv{\'o}s and Alberto Prieto and V{\'i}ctor Manuel Rivas Santos and Gabriel A. Romero},
  journal={Neural Processing Letters},
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… CONTINUE READING


Publications citing this paper.
Showing 1-10 of 31 extracted citations


Publications referenced by this paper.
Showing 1-10 of 47 references

Description and implementation details

  • M. Riedmiller
  • Technical report, University of Karlsruhe,
  • 1994
Highly Influential
4 Excerpts

G-Prop-II: Global optimization of multilayer perceptrons using GAs

  • P. A. Castillo, J. Gonzälez, J. J. Merelo, V. Rivas, G. Romero, A. Prieto
  • Congress on Evolutionary Computation
  • 1999
1 Excerpt

Similar Papers

Loading similar papers…