Learning feed-forward multi-nets

RS Venema*, L Spaanenburg

*Corresponding author for this work

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    Abstract

    Multi-nets promise an improved performance over monolithic neural networks by virtue of their distributed implementation. This potential lacks popularity as, without precautions, the learning rate has to drop considerably to eliminate the occurrence of unlearning. This paper introduces extensions of the Error Back-Propagation algorithm to enable function-preserving merging of neural modules at full learning rate.

    Original languageEnglish
    Title of host publicationARTIFICIAL NEURAL NETS AND GENETIC ALGORITHMS
    Editors Kurkova, NC Steele, R Neruda, M Karny
    Place of PublicationVIENNA
    PublisherSpringer
    Pages102-105
    Number of pages4
    ISBN (Print)3-211-83651-9
    Publication statusPublished - 2001
    EventInternational Conference on Artificial Neural Networks and Genetic Algorithms (ICANNGA) - , Czech Republic
    Duration: 22-Apr-200125-Apr-2001

    Publication series

    NameSPRINGER COMPUTER SCIENCE
    PublisherSPRINGER-VERLAG WIEN

    Other

    OtherInternational Conference on Artificial Neural Networks and Genetic Algorithms (ICANNGA)
    CountryCzech Republic
    Period22/04/200125/04/2001

    Cite this