Connectionist representation of multi-valued logic programs

Ekaterina Komendantskaya, Maire Lane, Anthony Karel Seda

    Research output: Chapter in Book/Report/Conference proceedingOther chapter contribution

    6 Citations (Scopus)

    Abstract

    Hölldobler and Kalinke showed how, given a propositional logic program P, a 3-layer feedforward artificial neural network may be constructed, using only binary threshold units, which can compute the familiar immediate-consequence operator TP associated with P. In this chapter, essentially these results are established for a class of logic programs which can handle many-valued logics, constraints and uncertainty; these programs therefore represent a considerable extension of conventional propositional programs. The work of the chapter basically falls into two parts.
    Original languageEnglish
    Title of host publicationPerspectives of neural-symbolic integration
    EditorsBarbara Hammer, Pascal Hitzler
    Place of PublicationBerlin
    PublisherSpringer
    Pages283-313
    Number of pages31
    ISBN (Print)9783540739531
    DOIs
    Publication statusPublished - 2007

    Publication series

    NameStudies in computational intelligence
    PublisherSpringer
    Volume77
    ISSN (Print)1860-949X
    ISSN (Electronic)1860-9503

    Fingerprint Dive into the research topics of 'Connectionist representation of multi-valued logic programs'. Together they form a unique fingerprint.

    Cite this