Classification by ensembles of neural networks

Research Articles

Abstract

We introduce a new procedure for training of artificial neural networks by using the approximation of an objective function by arithmetic mean of an ensemble of selected randomly generated neural networks, and apply this procedure to the classification (or pattern recognition) problem. This approach differs from the standard one based on the optimization theory. In particular, any neural network from the mentioned ensemble may not be an approximation of the objective function.

Key words

neural networks classification pattern recognition 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    S. I. Nikolenko and A. L. Tulupiev, Learning Systems (Moscow, MCCME, 2009) [in Russian].Google Scholar
  2. 2.
    E. V. Koonin, The Logic of Chance: The Nature and Origin of Biological Evolution (FT Press, 2011).Google Scholar
  3. 3.
    M. Mézard, G. Parisi and M. A. Virasoro, Spin Glass Theory and Beyond (World Scientific, Singapore, 1987).MATHGoogle Scholar
  4. 4.
    S. V. Kozyrev and A. Yu. Khrennikov, “Replica procedure for probabilistic algorithms as a model of gene duplication”, DokladyMath. 84(2), 657–660 (2011); arXiv:1105.2893.Google Scholar

Copyright information

© Pleiades Publishing, Ltd. 2012

Authors and Affiliations

  1. 1.Steklov Mathematical InstituteRussian Academy of SciencesMoscowRussia

Personalised recommendations