TSViz: Demystification of Deep Learning Models for Time-Series Analysis
This addresses the need for explainable AI in critical domains like finance and healthcare, where understanding predictions is as important as accuracy, though it is incremental as it adapts visualization methods from images to time-series.
The paper tackles the problem of interpreting convolutional deep learning models for time-series analysis, which lacks intuitive visualization tools compared to image models, by introducing TSViz, a framework that enables exploration of network features, filter importance, and robustness, with results validated through network pruning.
This paper presents a novel framework for demystification of convolutional deep learning models for time-series analysis. This is a step towards making informed/explainable decisions in the domain of time-series, powered by deep learning. There have been numerous efforts to increase the interpretability of image-centric deep neural network models, where the learned features are more intuitive to visualize. Visualization in time-series domain is much more complicated as there is no direct interpretation of the filters and inputs as compared to the image modality. In addition, little or no concentration has been devoted for the development of such tools in the domain of time-series in the past. TSViz provides possibilities to explore and analyze a network from different dimensions at different levels of abstraction which includes identification of parts of the input that were responsible for a prediction (including per filter saliency), importance of different filters present in the network for a particular prediction, notion of diversity present in the network through filter clustering, understanding of the main sources of variation learnt by the network through inverse optimization, and analysis of the network's robustness against adversarial noise. As a sanity check for the computed influence values, we demonstrate results regarding pruning of neural networks based on the computed influence information. These representations allow to understand the network features so that the acceptability of deep networks for time-series data can be enhanced. This is extremely important in domains like finance, industry 4.0, self-driving cars, health-care, counter-terrorism etc., where reasons for reaching a particular prediction are equally important as the prediction itself. We assess the proposed framework for interpretability with a set of desirable properties essential for any method.