• DocumentCode
    2485380
  • Title

    ExOpaque: A Framework to Explain Opaque Machine Learning Models Using Inductive Logic Programming

  • Author

    Guo, Yunsong ; Selman, Bart

  • Author_Institution
    Cornell Univ., Ithaca
  • Volume
    2
  • fYear
    2007
  • fDate
    29-31 Oct. 2007
  • Firstpage
    226
  • Abstract
    In this paper we developed an Inductive Logic Programming (ILP) based framework ExOpaque that is able to extract a set of Horn clauses from an arbitrary opaque machine learning model, to describe the behavior of the opaque model with high fidelity while maintaining the simplicity of the Horn clauses for human interpretations.
  • Keywords
    Horn clauses; inductive logic programming; learning (artificial intelligence); set theory; ExOpaque-opaque machine learning model; Horn clauses; inductive logic programming; Artificial intelligence; Biological system modeling; Cancer; Decision trees; Humans; Logic programming; Machine learning; Magnetic heads; Support vector machines; USA Councils;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Tools with Artificial Intelligence, 2007. ICTAI 2007. 19th IEEE International Conference on
  • Conference_Location
    Patras
  • ISSN
    1082-3409
  • Print_ISBN
    978-0-7695-3015-4
  • Type

    conf

  • DOI
    10.1109/ICTAI.2007.140
  • Filename
    4410384
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=2485380