Skip to main content
SpringerLink
Log in

Virtual sample generation using a population of networks

  • Published:
Neural Processing Letters Aims and scope Submit manuscript

Abstract

Multilayer perceptrons have been shown to approximate any continuous functions with a desired precision. With insufficient training samples, however, the network can not learn the function properly and popular model selection methods such as cross validation can not be used. We propose a scheme to generate virtual samples using a population of networks. They are applied to regression problems and are shown to improve generalization and to solve the model selection problem at the same time.

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. G. An, “The effects of adding noise duringbackpropagation training on a generalization performance”, Neural Computation, Vol. 7, pp. 613–674, 1996.

    Google Scholar 

  2. A. Bandura, SocialLearning Theory, General Learning Press: New York, 1971.

    Google Scholar 

  3. P. Bartlett, “Vapnik-Chervonenkis dimension bounds for two-and three-layer networks”, Neural Computation, Vol. 5, pp. 371–373, 1993.

    Google Scholar 

  4. S. Cho and K. Cha, “Evolution of neural network training setthrough addition of virtual samples”, Proceedings 1996 IEEE International Conference on Evolutionary Computation, pp. 685–688, Nagoya, Japan, 1996.

  5. D. Cohn, Z. Ghahramani and M. Jordan, “Active learning withstatistical models”, Neural Information Processing Systems, Vol. 7, pp. 705–712, 1995.

    Google Scholar 

  6. R. Duda and P. Hart, Pattern Classificationand Scene Analysis, Wiley: New York, 1973.

    Google Scholar 

  7. K. Funahashi,“On the approximate realization of continuous mappings by neural networks”, Neural Networks, Vol. 2, pp. 189–195, 1989.

    Google Scholar 

  8. A. Abu-Mostafa, “Hints”, Neural Computation, Vol.7, pp. 639–671, 1995.

    Google Scholar 

  9. M. Perrone, “Generalaveraging results for convex optimization”, in M. Mozer et al. (eds), Proceedings 1993 Connectionist Models Summer School, pp. 364–371, Lawrence Erlbaum: Hillsdale, USA, 1994.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science and Engineering, Information Research Laboratories, Pohang University of Science and Technology, Pohang, Kyungbuk, 790–784, Korea.

    Sungzoon Cho, Min Jang & Sungjune Chang

Authors
  1. Sungzoon Cho
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Min Jang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Sungjune Chang
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

About this article

Cite this article

Cho, S., Jang, M. & Chang, S. Virtual sample generation using a population of networks. Neural Processing Letters 5, 21–27 (1997). https://doi.org/10.1023/A:1009653706403

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1023/A:1009653706403

Search

Navigation