eXplainable Deep Neural Networks (xDNN)

xDNN is a prototype-based network that uses data density as its core mechanism.

Prototypes are selected data samples that the users can easily view, understand and analyze their similarity to other data samples.

xDNN for model interpretability in the context of DRL

xDNN is used to approximate the DRL model with a set of IF…THEN rules that provide an alternative interpretable model, which is further enhanced by visualizing the rules.

xDNN for object detection

xDNN is applied for the object detection context. Due to its transparent design, it allows an explainable error analysis which is crucial for high stake applications.

xClass for Novelty detection

xClass extends xDNN and offers:

  • Real-time “novelty detection” through the recursive density and the m-sigma rule.
  • Weakly supervised structure that allows few 1 class and few data samples initially.
  • Automatic creation of new classes.
  • Transparent structure that allows humans to audit it.