Multi-Objective Algorithms for Neural Networks Learning

  • Antônio Pádua Braga
  • Ricardo H. C. Takahashi
  • Marcelo Azevedo Costa
  • Roselito de Albuquerque Teixeira
Part of the Studies in Computational Intelligence book series (SCI, volume 16)


Most supervised learning algorithms for Artificial Neural Networks (ANN)aim at minimizing the sum of the squared error of the training data [12, 11, 5, 10]. It is well known that learning algorithms that are based only on error minimization do not guarantee good generalization performance models. In addition to the training set error, some other network-related parameters should be adapted in the learning phase in order to control generalization performance. The need for more than a single objective function paves the way for treating the supervised learning problem with multi-objective optimization techniques. Although the learning problem is multi-objective by nature, only recently it has been given a formal multi-objective optimization treatment [16]. The problem has been treated from different points of view along the last two decades.


Hide Node Validation Error Pruning Method Neural Network Learn Weight Decay 
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]
    B. Boser, I. Guyon, and V. Vapnik. A training algorithm for optimal margin classifiers. Fifth Annual Workshop on Computational Learning Theory, pages 144–152, 1992.Google Scholar
  2. [2]
    V. Chankong and Y. Y. Haimes. Multiobjective Decision Making: Theory and Methodology, volume 8. North-Holland (Elsevier), New York, 1983.Google Scholar
  3. [3]
    C. Cortes and V. Vapnik. Support vector networks. Machine Learning, 20:273–279, 1995.MATHGoogle Scholar
  4. [4]
    Yann Le Cun, John S. Denker, and Sara A. Solla. Optimal brain damage. In Advances in Neural Information Processing Systems 2, pages 598–605, 1990.Google Scholar
  5. [5]
    S. E. Fahlman. Faster-learning variations on back-propagation: an empirical study. In D. Touretzky, G. Hinton, and T. Sejnowski, editors, Proceedings of the 1988 Connectionist Models Summer School, Pittsburg, pages 38–51, San Mateo, CA, 1988. Morgan Kaufmann.Google Scholar
  6. [6]
    S. R. Gunn. Support vector machines for classification and regression. Technical report, Image Speech and Intelligent Systems Research Group, University of Southampton, 1997.Google Scholar
  7. [7]
    S. Haykin. Neural Networks: A Comprehensive Foundation. Prentice Hall, 1999.Google Scholar
  8. [8]
    Ehud D. Karnin. A simple procedure for pruning back-propagation trained neural networks. IEEE Transactions on Neural Networks, 1(2):239–242, 1990.CrossRefGoogle Scholar
  9. [9]
    M. C. Mozer and P. Smolensky. Skeletonization: A technique for trimming the fat from a network via relevance assessment. Advances in Neural Information Processing, vol. 1, pages 107–115, 1989.Google Scholar
  10. [10]
    Gustavo G. Parma, Antonio P. Braga, and Benjamim R. Menezes. Sliding mode algorithm for training multi-layer neural networks. IEE Electronics Letters, 38(1):97–98, January 1998.CrossRefGoogle Scholar
  11. [11]
    Martin Riedmiller and Heinrich Braun. A direct adaptive method for faster back propagation learning: The RPROP algorithm. In Proc. of the IEEE Intl. Conf. on Neural Networks, pages 586–591, San Francisco, CA, April 1993.Google Scholar
  12. [12]
    D. E. Rumelhart, G. E. Hinton, and R. J. Williams. Learning representations by back-propagating errors. Nature, 323:533–536, 1986.CrossRefGoogle Scholar
  13. [13]
    N. Z. Shor. Cut-off method with space extension in convex programming problems. Cybernetics, 12:94–96, 1977.Google Scholar
  14. [14]
    R. H. C. Takahashi, P. L. D. Peres, and P. A. V. Ferreira. H2/h-infinity multiobjective pid design. IEEE Control Systems Magazine, 17(5):37–47, June 1997.CrossRefGoogle Scholar
  15. [15]
    V. Vapnik. The Nature of Statistical Learning Theory. Springer-Verlag, 1995.Google Scholar
  16. [16]
    R. A. Teixeira, A. P. Braga, R. H. C. Takahashi, and R. R. Saldanha. Improving generalization of mlps with multi-objective optimization. Neurocomputing, 35(1–4):189–194, 2000.MATHCrossRefGoogle Scholar
  17. [17]
    G. A. Hinton. Connectionist learning procedures. Artificial Intelligence, 40:185–234, 1989.CrossRefGoogle Scholar
  18. [18]
    V. Pareto. Cours D'Economie Politique. Rouse, Lausanne, 1896. vols. I and II.Google Scholar
  19. [19]
    R. A. Teixeira, A. P. Braga, R. H. C. Takahashi, and R. R. Saldanha. Utilização de seção áurea no cálculo de soluçõ efficientes para treinamento de redes neurais artificiais através de otimização multi-objetivo. 8th Brazilian Symposium on Neural Networks, November 2004.Google Scholar
  20. [20]
    U. Itkis. Control Systems of Variable Structure. Keter Publishing House Jerusalem LTD, 1976.Google Scholar
  21. [21]
    M. A. Costa, A. P. Braga, B. R. de Menezes, G. G. Parma, and R. A. Teixeira. Training neural networks with a multi-objective sliding mode control algorithm. Neurocomputing, 51:467–473, 2003.CrossRefGoogle Scholar
  22. [22]
    M. A. Costa, A. P. Braga and B. R. de Menezes. Improving neural networks generalization with new constructive and pruning methods. Journal of Intelligent & Fuzzy Systems, 10:1–9, 2003.Google Scholar
  23. [23]
    C.L. Blake and C.J. Merz. {UCI} Repository of machine learning databases. University of California, Irvine, Dept. of Information and Computer Sciences, html, 1998.Google Scholar
  24. [24]
    S. E. Fahlman and C. Lebiere, The cascade-correlation learning architecture, Morgan Kaufmann, In Advances in Neural Information Processing Systems 2 (D. S. Touretzky, Editor), 1990Google Scholar
  25. [25]
    Jean-Pierre Nadal, Study of a growth algorithm for a feedforward network, International Journal of Neural Systems, 1(1):55–59, 1989.CrossRefMathSciNetGoogle Scholar
  26. [26]
    Ron Kohavi, A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection,, 1995.Google Scholar
  27. [27]
    S. Geman and E. Bienenstock and R. Doursat. Neural Networks and the Bias/Variance Dilemma, Neural Computation, 4(1):1–58, 1992.Google Scholar

Copyright information

© Springer 2006

Authors and Affiliations

  • Antônio Pádua Braga
    • 1
  • Ricardo H. C. Takahashi
    • 1
  • Marcelo Azevedo Costa
    • 1
  • Roselito de Albuquerque Teixeira
    • 2
  1. 1.Federal University of Minas GeraisBrazil
  2. 2.Eastern University Centre of Minas GeraisBrazil

Personalised recommendations