Focusing on What is Relevant: Time-Series Learning and Understanding using Attention
This work addresses interpretability for users of time-series models, but it is incremental as it builds on existing attention techniques.
The paper tackles the problem of interpretability in deep learning models for time-series by proposing a temporal attention layer that selects relevant information for tasks like data completion, key-frame detection, and classification, achieving comparable results to state-of-the-art methods and providing better interpretability with more significant attention weights.
This paper is a contribution towards interpretability of the deep learning models in different applications of time-series. We propose a temporal attention layer that is capable of selecting the relevant information to perform various tasks, including data completion, key-frame detection and classification. The method uses the whole input sequence to calculate an attention value for each time step. This results in more focused attention values and more plausible visualisation than previous methods. We apply the proposed method to three different tasks. Experimental results show that the proposed network produces comparable results to a state of the art. In addition, the network provides better interpretability of the decision, that is, it generates more significant attention weight to related frames compared to similar techniques attempted in the past.