Optical Memory and Neural Networks

, Volume 17, Issue 3, pp 208–219

Performance criterion of neural networks learning


DOI: 10.3103/S1060992X08030041

Cite this article as:
Larko, A.A. Opt. Mem. Neural Networks (2008) 17: 208. doi:10.3103/S1060992X08030041


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 learninggeneralization errorquality criterionBayes theoremcyberneticssynergy

Copyright information

© Allerton Press, Inc. 2008

Authors and Affiliations

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