Issue No. 10 - October (1990 vol. 12)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/34.58871
<p>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.</p>
pattern recognition; crossvalidation; performance; training; neural networks; classification; residual generalization error; learning systems; neural nets; pattern recognition
P. Salamon and L. Hansen, "Neural Network Ensembles," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 12, no. , pp. 993-1001, 1990.