InterpretTime: a new approach for the systematic evaluation of neural-network interpretability in time series classification

no code implementations • 11 Feb 2022 • Hugues Turbé, Mina Bjelogrlic, Christian Lovis, Gianmarco Mengaldo

We present a novel approach to evaluate the performance of interpretability methods for time series classification, and propose a new strategy to assess the similarity between domain experts and machine data interpretation.

Classification Time Series +2