Skip to main content
SpringerLink
Log in

Controlling the parallel layer perceptron complexity using a multiobjective learning algorithm

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

This paper deals with the parallel layer perceptron (PLP) complexity control, bias and variance dilemma, using a multiobjective (MOBJ) training algorithm. To control the bias and variance the training process is rewritten as a bi-objective problem, considering the minimization of both training error and norm of the weight vector, which is a measure of the network complexity. This method is applied to regression and classification problems and compared with several other training procedures and topologies. The results show that the PLP MOBJ training algorithm presents good generalization results, outperforming traditional methods in the tested examples.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19

Similar content being viewed by others

References

  1. Bartlett PL (1998) The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the network. IEEE Trans Inf Theory 44(2):525–536

    Article  MATH  MathSciNet  Google Scholar 

  2. Caminhas WM, Vieira DAG, Vasconcelos JA (2003) Parallel layer perceptron. Neurocomputing 55(3–4):771–778

    Article  Google Scholar 

  3. Chinrungrueng C, Séquin CH (1995) Optimal adaptive k-means algorithm with dynamic adjustment of learning rate. IEEE Trans Neural Netw 6:157–169

    Article  Google Scholar 

  4. Cortes C, Vapnik V (1995) Support vector networks. Mach Learn 20:273–279

    MATH  Google Scholar 

  5. Costa MA, Braga AP, Menezes BR, Teixiera RA, Parma GG (2003) Training neural networks with a multi-objective sliding mode control algorithm. Neurocomputing 51:467–473

    Article  Google Scholar 

  6. Duda RO, Hart PE (1973) Pattern classification and scene analysis. Wiley-Interscience, New York

    MATH  Google Scholar 

  7. Fahlman SE, Lebiere C (1990) The cascade-correlation learning architecture. In: Touretzky D (ed) Advances in neural information processing systems, vol 2. Morgan Kaufmann, San Mateo

  8. Geman S, Bienenstock E, Doursat R (1992) Neural networks and the bias-variance dilemma. Neural Comput 4(1):1–58

    Google Scholar 

  9. Hangan MT, Menjah MB (1994) Training feedforward network with the Marquardt algorithm. IEEE Trans Neural Netw 5(6):989–993

    Article  Google Scholar 

  10. Ismail MA, Kamel MS (1989) Multidimensional data clustering utilizing hybrid strategies. Pattern Recognit 22:75–89

    Article  MATH  MathSciNet  Google Scholar 

  11. Ismail MA, Selim SZ, Aror SK (1984) Efficient clustering of multidimensional data. In: Proceedings of the IEEE international conference on systems man and cybernetics, pp 120–123

  12. Kearns MJ, Schapire RE (1990) Efficient distribution-free learning of probabilistic concepts (Abstract). In: COLT ’90: Proceedings of the 3rd annual workshop on computational learning theory

  13. Lacerda E, Carvalho A, Braga AP, Ludermir TB (2005) Using evolutionary RBF networks for credit assessment. Appl Intell 22(3):167–182

    Article  Google Scholar 

  14. Llyod SP (1982) Least squares quantization in pcm. IEEE Trans Inf Theory 28(2):129–137

    Article  Google Scholar 

  15. MacQueen J (1967) Some methods for classification and analysis of multivariate observations. In: Proceedings of the 5th Berkley symposium mathematical statistics and probability, vol 1, pp 281–297

  16. Parekh R, Yang J, Honavar V (1987) Constructive neural network learning algorithms for multi-category real-valued pattern classification. Technical report, Iowa State University, Department of Computer Science

  17. Sexton R, Dorsey R (2000) Reliable classification using neural networks: a genetic algorithm and backpropagation comparison. IEEE Trans Knowl Data Eng 30:11–22

    Google Scholar 

  18. Shawe-Taylor J, Bartlett PL (1998) Structural risk minimization over data-dependent hierarchies. IEEE Trans Inf Theory 44(5):1926–1940

    Article  MATH  MathSciNet  Google Scholar 

  19. Shor NZ (1977) Cut-off method with space extension in convex programming problems. Cybernetics 12:94–96

    Google Scholar 

  20. Takahashi RH, Peres PLD, Ferreira PAV (1997) H2/h-infinity multiobjective pid design. IEEE Control Syst 15(5):37–34

    Article  Google Scholar 

  21. Teixeira RA (2001) Treinamento de Redes Neurais Artificias Atraves de Otimizatpo Multi-Objetivo: Uma Nova Abordagem para o Equilibro entre a Polarizacao e a Variancia. PhD Thesis, CPDEE- UFMG

  22. Teixiera RA, Braga AP, Takaha R, Saldanha RR (2000) Improving generalization of MLPs with multi-objective optimization. Neurocomputing 35:189–194

    Article  Google Scholar 

  23. Vapnik VN (1998) Statistical learning theory. Wiley, New York

    MATH  Google Scholar 

  24. Vapnik VN (2001) The nature of statistical learning theory, Statistics for Engineering and Information Science, 2nd edn. Springer, Berlin Heidelberg New York

  25. Yao X (1993) a review of evolutionary artificial neural networks. Int J Intell Syst 8:539–567

    Google Scholar 

Download references

Acknowledgments

This work was supported by CNPq (grants no. 350902/1997-6, no. 140009/2004-3), CAPES-COFECUB Project Cooperation no. 318/00-II and CAPES (grant no. 3421/04-0), Brazil.

Author information

Authors and Affiliations

  1. Department of Electrical Engineering, Federal University of Minas Gerias, Campus da UFMG (Pampulha), CEP 30.270-010, Belo Horizonte, MG, Brazil

    D. A. G. Vieira, J. A. Vasconcelos & W. M. Caminhas

Authors
  1. D. A. G. Vieira
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. J. A. Vasconcelos
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. W. M. Caminhas
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to W. M. Caminhas.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Vieira, D.A.G., Vasconcelos, J.A. & Caminhas, W.M. Controlling the parallel layer perceptron complexity using a multiobjective learning algorithm. Neural Comput & Applic 16, 317–325 (2007). https://doi.org/10.1007/s00521-006-0052-z

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-006-0052-z

Keywords

Search

Navigation