Sequential Interpretability: Methods, Applications, and Future Direction for Understanding Deep Learning Models in the Context of Sequential Data
It addresses the need for interpretability in sequential domains like healthcare, but is incremental as it primarily surveys existing methods.
The paper reviews techniques for interpreting deep learning models applied to sequential data, such as in natural language processing and healthcare, to address the lack of transparency in these 'black box' models, but does not present new experimental results or concrete numbers.
Deep learning continues to revolutionize an ever-growing number of critical application areas including healthcare, transportation, finance, and basic sciences. Despite their increased predictive power, model transparency and human explainability remain a significant challenge due to the "black box" nature of modern deep learning models. In many cases the desired balance between interpretability and performance is predominately task specific. Human-centric domains such as healthcare necessitate a renewed focus on understanding how and why these frameworks are arriving at critical and potentially life-or-death decisions. Given the quantity of research and empirical successes of deep learning for computer vision, most of the existing interpretability research has focused on image processing techniques. Comparatively, less attention has been paid to interpreting deep learning frameworks using sequential data. Given recent deep learning advancements in highly sequential domains such as natural language processing and physiological signal processing, the need for deep sequential explanations is at an all-time high. In this paper, we review current techniques for interpreting deep learning techniques involving sequential data, identify similarities to non-sequential methods, and discuss current limitations and future avenues of sequential interpretability research.