Challenges of Explaining the Behavior of Black-Box AI Systems

Aleksandre Asatiani, Pekka Malo, Per Rådberg Nagbøl, Esko Penttinen, Tapani Rinta-Kahila, Antti Salovaara

    Research output: Journal Article or Conference Article in JournalJournal articleResearchpeer-review

    Abstract

    There are many examples of problems resulting from inscrutable AI systems, so there is a growing need to be able to explain how such systems produce their outputs. Draw- ing on a case study at the Danish Business Authority, we provide a framework and recommendations for addressing the many challenges of explaining the behavior of black-box AI systems. Our findings will enable organizations to successfully develop and deploy AI systems without causing legal or ethical problems.
    Original languageEnglish
    Article number7
    JournalM I S Quarterly Executive
    Volume19
    Issue number4
    Pages (from-to)259-278
    ISSN1540-1960
    DOIs
    Publication statusPublished - 1 Dec 2020

    Keywords

    • Artificial intelligence
    • Explainability
    • Envelopment

    Fingerprint

    Dive into the research topics of 'Challenges of Explaining the Behavior of Black-Box AI Systems'. Together they form a unique fingerprint.

    Cite this