This paper was presented at the Human in the Loop Learning Workshop at the 2019 International Conference on Machine Learning.

Abstract

In an attempt to gather a deeper understanding of how convolutional neural networks (CNNs) reason about human-understandable concepts, we present a method to infer labeled concept data from hidden layer activations and interpret the concepts through a shallow decision tree. The decision tree can provide information about which concepts a model deems important, as well as provide an understanding of how the concepts interact with each other. Experiments demonstrate that the extracted decision tree is capable of accurately representing the original CNN's classifications at low tree depths, thus encouraging human-in-the-loop understanding of discriminative concepts.