Performance criterion of neural networks learning
- First Online:
- 38 Downloads
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 wordsmachine learning generalization error quality criterion Bayes theorem cybernetics synergy
Unable to display preview. Download preview PDF.