Learning Saliency Maps to Explain Deep Time Series Classifiers
Prathyush Parvatharaju, Ramesh Doddaiah, Thomas Hartvigsen, Elke A. Rundensteiner
Abstract
Explainable classification is essential to high-impact settings where practitioners requireevidence to support their decisions. However, state-of-the-art deep learning models lack transparency in how they make their predictions. One increasingly popular solution is attribution-based explainability, which finds the impact of input features on the model's predictions. While this is popular for computer vision, little has been done to explain deep time series classifiers.In this work, we study this problem and propose PERT, a novel perturbation-based explainability method designed to explain deep classifiers' decisions on time series. PERT extends beyond recent perturbation methods to generate a saliency map that assigns importance values to the timesteps of the instance-of-interest.