Neuro-symbolic representation of logic programs defining infinite sets

Ekaterina Komendantskaya, Krysia Broda, Artur d'Avila Garcez

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    1 Citation (Scopus)

    Abstract

    It has been one of the great challenges of neuro-symbolic integration to represent recursive logic programs using neural networks of finite size. In this paper, we propose to implement neural networks that can process recursive programs viewed as inductive definitions.

    Original languageEnglish
    Title of host publicationArtificial Neural Networks-Icann 2010, Pt I
    EditorsK Diamantaras, W Duch, LS Iliadis
    Place of PublicationBerlin
    PublisherSpringer
    Pages301-304
    Number of pages4
    ISBN (Print)9783642158186
    DOIs
    Publication statusPublished - 2010
    Event20th International Conference on Artificial Neural Networks - Thessaloniki, Greece
    Duration: 15 Sep 201018 Sep 2010
    http://delab.csd.auth.gr/icann2010/index.html

    Conference

    Conference20th International Conference on Artificial Neural Networks
    Abbreviated title20th ICANN 2010
    CountryGreece
    CityThessaloniki
    Period15/09/1018/09/10
    Internet address

    Keywords

    • Neurosymbolic integration
    • Structured learning
    • Mathematical theory of neurocomputing
    • Logic programming

    Cite this