Running summarizing tools on a new article
Check the paper below, then start its synthesis.
Neural network ensembles
Lars Kai Hansen (San Diego State University), Peter Salamon (San Diego State University)
IEEE Transactions on Pattern Analysis and Machine Intelligence
DOI: 10.1109/34.58871 (Computer Science)
License: not stated (all rights reserved)
Abstract: 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.>
Published on 01 Jan. 1990