Towards Fully Interpretable Deep Neural Networks: Are We There Yet?
It identifies gaps and suggests directions for making DNNs fully interpretable, which is an incremental contribution as it synthesizes existing work without introducing novel methods.
This paper reviews methods for developing inherently interpretable deep neural networks, particularly CNNs, to address the black-box nature of DNNs that hinders trust in AI systems, but it does not present new experimental results or concrete numbers.
Despite the remarkable performance, Deep Neural Networks (DNNs) behave as black-boxes hindering user trust in Artificial Intelligence (AI) systems. Research on opening black-box DNN can be broadly categorized into post-hoc methods and inherently interpretable DNNs. While many surveys have been conducted on post-hoc interpretation methods, little effort is devoted to inherently interpretable DNNs. This paper provides a review of existing methods to develop DNNs with intrinsic interpretability, with a focus on Convolutional Neural Networks (CNNs). The aim is to understand the current progress towards fully interpretable DNNs that can cater to different interpretation requirements. Finally, we identify gaps in current work and suggest potential research directions.