Towards Explanation of DNN-based Prediction with Guided Feature Inversion

Understand

While deep neural networks (DNN) have become an effective computational tool, the prediction results are often criticized by the lack of interpretability, which is essential in many real-world applications such as health informatics.

• Existing attempts based on local interpretations aim to identify relevant features contributing the most to the prediction of DNN by monitoring the neighborhood of a given input.
• They usually simply ignore the intermediate layers of the DNN that might contain rich information for interpretation.
• To bridge the gap, in this paper, we propose to investigate a guided feature inversion framework for taking advantage of the deep architectures towards effective interpretation.