Skip to main content
SpringerLink
Log in

Saturated Perceptrons for Maximum Margin and Minimum Misclassification Error

  • Published:
Neural Processing Letters Aims and scope Submit manuscript

Abstract

This Letter discusses the application of gradient-based methods to train a single layer perceptron subject to the constraint that the saturation degree of the sigmoid activation function (measured as its maximum slope in the sample space) is fixed to a given value. From a theoretical standpoint, we show that, if the training set is not linearly separable, the minimization of an L p error norm provides an approximation to the minimum error classifier, provided that the perceptron is highly saturated. Moreover, if data are linearly separable, the perceptron approximates the maximum margin classifier

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

Similar content being viewed by others

References

  1. Auer, P., Cesa-Bianchi, N. and Gentile, C.: Adaptive and Self-Concdent On-Line Learning Algorithms, NeuroCOLT Technical Report NC-TR-00-083. Submitted for journal publication, 2001.

  2. Bobrowsky, L. and Sklansky, J.: Linear Classicers by Window Training, IEEE Transactions on System Science and Cybernetics 25 (1995), 1–9.

    Google Scholar 

  3. Do-Tu, H. and Installe, M.: Learning Algorithms for Non-Parametric Solution to the Minimum Error Classification Problem, IEEE Transactions on Computers 27(7) (1978), 648–659.

    Google Scholar 

  4. Duda, R. O. and Hart, P. E.: Pattern Classification and Scene Analysis, Wiley-Interscience, 1973.

  5. Navia-Vázquez, A., Pérez-Cruz, F., Artés-Rodríguez, A. and Figueiras-Vidal, A. R.: Weighted Least Squares Training of Support Vector Classicers Leading to Compact and Adaptive Schemes, IEEE Transactions on Neural Networks. Accepted for publication. To appear, 2001.

  6. Raudys, S.: Evolution and Generalization of a Single Neurone. I. Single Layer Perceptron as Seven Statistical Classicers, Neural Networks 11 (1998a), 283–296.

    Google Scholar 

  7. Raudys, S.: Evolution and Generalization of a Single Neurone. II. Complexity of Statistical Classicers and Sample Size Considerations, Neural Networks 11 (1998b), 297–313.

    Google Scholar 

  8. Ruck, D. W., Rogers, S. K., Kabrinsky, M., Oxley, M. E. and Suter, B. W.: The Multilayer Perceptron as an Approximation to a Bayes Optimal Discriminant Function, IEEE Transactions on Neural Networks 1(4) (1990), 296–298.

    Google Scholar 

  9. Telfer, B. A. and Szu, H. H.: Energy Functions for Minimizing Misclassiccation Error with Minimum-Complexity Networks, Neural Networks 7 (1994), 809–818.

    Google Scholar 

  10. Vapnik, V.: Statistical Learning Theory. New York: Wiley, 1998.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Dpto. de Tecnologías de las Comunicaciones, Universidad Carlos III de Madrid, Avda. de la Universidad 30, 28911, Leganés-Madrid, Spain

    Jesús Cid-Sueiro & José L. Sancho-Gómez

Authors
  1. Jesús Cid-Sueiro
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. José L. Sancho-Gómez
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jesús Cid-Sueiro.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Cid-Sueiro, J., Sancho-Gómez, J.L. Saturated Perceptrons for Maximum Margin and Minimum Misclassification Error. Neural Processing Letters 14, 217–226 (2001). https://doi.org/10.1023/A:1012755431700

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1023/A:1012755431700

Search

Navigation