Introducing Multi-objective Optimization in Cooperative Coevolution of Neural Networks

  • N. García-Pedrajas
  • E. Sanz-Tapia
  • D. Ortiz-Boyer
  • C. Hervás-Martínez
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2084)


This paper presents MONet (Multi-Objective coevolutive NETwork), a cooperative coevolutionary model for evolving artificial neural networks that introduces concepts taken from multi-objective optimization. This model is based on the idea of coevolving subnetworks that must cooperate to form a solution for a specific problem, instead of evolving complete networks. The fitness of each member of the subpopulations of subnetworks is evaluated using an evolutionary multi-objective optimization algorithm. This idea has not been used before in the area of evolutionary artificial neural networks. The use of a multiobjective evolutionary algorithm allows the definition of as many objectives as could be interesting for our problem and the optimization of these objectives in a natural way.


Genetic Algorithm Multiobjective Optimization Multiobjective Evolutionary Algorithm Strength Pareto Evolutionary Algorithm Cooperative Coevolution 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    C. M. Fonseca and P. J. Flemming. Genetic algorithms for multiobjective optimization: Formulation, discussion, and generalization. In Proceedings of the Fifth International Conference on Genetic Algorithms, pages 416–423, 1993.Google Scholar
  2. 2.
    N. García-Pedrajas, C. Hervás-Martínez, and J. Muñoz-Pérez. Symbiont: A cooperative evolutionary model for evolving artificial neural networks for classification. In 8th Interbational Conference on Information Processing and Management of Uncertainty in Knowledge Based Systems, pages 298–305, Madrid, July 2000.Google Scholar
  3. 3.
    N. García-Pedrajas, C. Hervás-Martánez, and J. Muñoz-Pérez. Symbiont: A cooperarive evolutionary model for evolving artificial neural networks for classification. In B. Bouchon-Meunier, J. Gutiérrez-Ríos, L. Magdalena, and R. R. Yager, editors, Technologies for Constructing Intelligent Systems. Springer-Verlag, 2001. (in press).Google Scholar
  4. 4.
    J. Horn, D. E. Goldberg, and K. Deb. Implicit niching in a learning classifier system: Natures’s way. Evolutionary Computation, 2(1):37–66, 1994.CrossRefGoogle Scholar
  5. 5.
    M. A. Potter and K. A. de Jong. Cooperative coevolution: An architecture for evolving coadapted subcomponents. Evolutionary Computation, 8(1):1–29, 2000.CrossRefGoogle Scholar
  6. 6.
    L. Prechelt. Proben1-a set of neural network benchmark problems and benchmarking rules. Technical Report 21/94, Fakultät für Informatik, Universität Karlsruhe, Karlsruhe, Germany, September 1994.Google Scholar
  7. 7.
    N. Srinivas and K. Deb. Multi-objective function optimization using nondominated sorting genetic algorithms. Evolutionary Computation, 2(3):221–248, 1994.CrossRefGoogle Scholar
  8. 8.
    D. Whitley and J. Kauth. Genitor: a different genetic algorithm. In Proceedings of the Rocky Mountain Conference on Artificial Intelligence, pages 118–130, Denver, CO, 1988.Google Scholar
  9. 9.
    X. Yao. Evolving artificial neural networks. Proceedings of the IEEE, 9(87):1423–1447, 1999.Google Scholar
  10. 10.
    E. Zitzler and L. Thiele. Multiobjective optimization using evolutionary algorithms-a comprative case study. Parallel Problem Solving from Nature, V:292–301, 1998.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • N. García-Pedrajas
    • 1
  • E. Sanz-Tapia
    • 1
  • D. Ortiz-Boyer
    • 1
  • C. Hervás-Martínez
    • 1
  1. 1.Dept. of Computing and Numerical AnalysisUniversity of CórdobaCórdobaSpain

Personalised recommendations