Variance Tolerance Factors For Interpreting Neural Networks

09/28/2022

∙

by   Sichao Li, et al.

∙

58

∙

share

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.