Research work · 1990

Neural network ensembles

Lars Kai Hansen, Peter B. Salamon

IEEE Transactions on Pattern Analysis and Machine Intelligence

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.>

Read free full text

DOI: 10.1109/34.58871