Interpretation of Recurrent Neural Networks

Morten With Pedersen, Jan Larsen

    Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

    543 Downloads (Pure)

    Abstract

    This paper addresses techniques for interpretation and characterization of trained recurrent nets for time series problems. In particular, we focus on assessment of effective memory and suggest an operational definition of memory. Further we discuss the evaluation of learning curves. Various numerical experiments on time series prediction problems are used to illustrate the potential of the suggested methods
    Original languageEnglish
    Title of host publicationProceedings of the IEEE Workshop on Neural Networks for Signal Processing VII
    Place of PublicationPiscataway, New Jersey
    PublisherIEEE
    Publication date1997
    Pages82-91
    ISBN (Print)0-7803-4256-9
    DOIs
    Publication statusPublished - 1997
    Event1997 IEEE Workshop on Neural Networks for Signal Processing VII - Piscataway, NJ, United States
    Duration: 24 Sep 199726 Sep 1997
    http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=4900

    Workshop

    Workshop1997 IEEE Workshop on Neural Networks for Signal Processing VII
    CountryUnited States
    CityPiscataway, NJ
    Period24/09/199726/09/1997
    Internet address

    Bibliographical note

    Copyright: 1997 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE

    Fingerprint Dive into the research topics of 'Interpretation of Recurrent Neural Networks'. Together they form a unique fingerprint.

    Cite this