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

PI: Dejing Dou

The goals of this project are to (1) evaluate contemporary techniques for deep learning model explanations and (2) utilize DL Explanation approach for improving model performance.


  • Identifying noisy features by aggregating local model approximation via fitting explainable submodels (LIME – local approximation)
  • Generating representations of the latent feature space of a model via disentanglement