Neural Network Ensembles

Lars Kai Hansen, Peter Salamon

    Research output: Contribution to journalJournal articleResearchpeer-review

    2434 Downloads (Pure)

    Abstract

    We 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.
    Original languageEnglish
    JournalI E E E Transactions on Pattern Analysis and Machine Intelligence
    Volume12
    Pages (from-to)993-1001
    ISSN0162-8828
    Publication statusPublished - 1990

    Keywords

    • fault tolerant computing
    • neural networks
    • crossvalidation

    Fingerprint

    Dive into the research topics of 'Neural Network Ensembles'. Together they form a unique fingerprint.

    Cite this