crossvalidationnetwork parameters and architecture optimizationneural network ensemblesresidual generalization error
Figures from the paper
Abstract (AI)
Several means for improving the performance and training of neural networks for classification are proposed. Crossvalidation is used as a tool for optimizing network parameters and architecture. It is shown that the remaining residual generalization error can be reduced by invoking ensembles of similar networks.>
Key Findings
1
Cross-validation can be used to optimize neural network parameters and architecture for classification tasks.
2
Ensembles of similar neural networks reduce the remaining residual generalization error.
3
Using multiple means (including cross-validation and ensembles) improves performance and training of classification neural networks.
Research Object
Neural network classifiers (ensembles of similar neural networks)
Research Subject
Methods to improve performance and training, including cross-validation for parameter/architecture selection and reduction of residual generalization error via ensembles
Publication Details
Publication Date
1990-01-01
Journal
Publisher
ISSN
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest