PlantedML

Planted Machine Learning (PlantedML) is a new class of interpretable machine learning algorithms with the goal to combine accuracy and intelligibility. PlantedML algorithms discover and learn low dimensional structures along a planted path.

Team

  • image1
    Joseph Meyer
    PhD Student
    Heidelberg University
  • image3
    Enno Mammen
    Professor
    Heidelberg University
  • image2
    Munir Hiabu
    Assistant Professor
    University of Copenhagen
  • image2
    Marvin Wright
    Professor
    The Leibniz Institute for Prevention
    Research and Epidemiology - BIPS
  • image2
    Lukas Burk
    PhD Student
    The Leibniz Institute for Prevention
    Research and Epidemiology - BIPS
  • image3
    Maike Spankus
    Research Assistant
    Heidelberg University

Publications and Preprints


  • Hiabu, Meyer, Wright: Unifying local and global model explanations by functional decomposition of low dimensional structures [arxiv link] [github]

  • Hiabu, Mammen, Meyer: Random Planted Forest: a directly interpretable tree ensemble [arxiv link] [github] [webpage]