Optical Memory and Neural Networks

, Volume 17, Issue 3, pp 208–219

Performance criterion of neural networks learning



The article deals with a new criterion (the wave criterion) of estimating the generalizing ability of a neural network. The theoretical grounding of the criterion is based on Bayes theorem, the methods of cybernetics and synergy. The computing experiments carried out with the databases Fmtrain, Matt, Grng, Ada have proved the criterion to be an effective tool.

Key words

machine learning generalization error quality criterion Bayes theorem cybernetics synergy 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Allerton Press, Inc. 2008

Authors and Affiliations

  1. 1.CJSC “Infozentr”AbakanRussia, Republic of Khakassia

Personalised recommendations