TreeView: Peeking into Deep Neural Networks Via Feature-Space Partitioning

Understand

With the advent of highly predictive but opaque deep learning models, it has become more important than ever to understand and explain the predictions of such models.

• Existing approaches define interpretability as the inverse of complexity and achieve interpretability at the cost of accuracy.
• This introduces a risk of producing interpretable but misleading explanations.
• As humans, we are prone to engage in this kind of behavior \cite{mythos}.