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.
Similar content being viewed by others
References
S. I. Nikolenko and A. L. Tulupiev, Learning Systems (Moscow, MCCME, 2009) [in Russian].
E. V. Koonin, The Logic of Chance: The Nature and Origin of Biological Evolution (FT Press, 2011).
M. Mézard, G. Parisi and M. A. Virasoro, Spin Glass Theory and Beyond (World Scientific, Singapore, 1987).
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.
Author information
Authors and Affiliations
Corresponding author
Additional information
Dedicated to Igor Vasilievich Volovich on the occasion of his 65th birthday
The text was submitted by the author in English.
Rights and permissions
About this article
Cite this article
Kozyrev, S.V. Classification by ensembles of neural networks. P-Adic Num Ultrametr Anal Appl 4, 27–33 (2012). https://doi.org/10.1134/S2070046612010049
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S2070046612010049