Variance Tolerance Factors For Interpreting Neural Networks

Black box models only provide results for deep learning tasks and lack informative details about how these results were obtained. In this paper, we propose a general theory that defines a variance tolerance factor (VTF) to interpret the neural networks by ranking the importance of features and constructing a novel architecture consisting of a base model and feature model to demonstrate its utility. Two feature importance ranking methods and a feature selection method based on the VTF are created. A thorough evaluation on synthetic, benchmark, and real datasets is provided.