Neural Network Ensembles

Lars Kai Hansen, Peter Salamon

AbstractWe propose several means for improving the performance an training of neural networks for classification. We use crossvalidation as a tool for optimizing network parameters and architecture. We show further that the remaining generalization error can be reduced by invoking ensembles of similar networks.
Keywordscrossvalidation, fault tolerant computing,neural networks
TypeJournal paper [With referee]
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Year1990    Vol. 12    pp. 993-1001
Electronic version(s)[pdf]
BibTeX data [bibtex]
IMM Group(s)Intelligent Signal Processing


Back  ::  IMM Publications