O2-M Ontology-based Deep Learning with Explanation for Human Behavior Prediction

PI: Dejing Dou

The goal of this project is to evaluate contemporary techniques for deep learning model explanations and utilize DL Explanation approach for improving model interpretability.


  • Utilizing feature importance methods
    for dimensionality reduction and
    explanation generation
  • Generating representations of the
    latent feature space of a model via
    feature importance
  • User survey to evaluate
    interpretability of class specific label