Focusing on What is Relevant: Time-Series Learning and Understanding using Attention

06/22/2018
by   Phongtharin Vinayavekhin, et al.
0

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.

READ FULL TEXT
research
12/16/2020

Series Saliency: Temporal Interpretation for Multivariate Time Series Forecasting

Time series forecasting is an important yet challenging task. Though dee...
research
07/11/2023

A Deep Dive into Perturbations as Evaluation Technique for Time Series XAI

Explainable Artificial Intelligence (XAI) has gained significant attenti...
research
04/07/2017

A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction

The Nonlinear autoregressive exogenous (NARX) model, which predicts the ...
research
05/03/2019

Temporal Graph Convolutional Networks for Automatic Seizure Detection

Seizure detection from EEGs is a challenging and time consuming clinical...
research
12/01/2016

Temporal Attention-Gated Model for Robust Sequence Classification

Typical techniques for sequence classification are designed for well-seg...
research
06/09/2021

Towards Explainable Abnormal Infant Movements Identification: A Body-part Based Prediction and Visualisation Framework

Providing early diagnosis of cerebral palsy (CP) is key to enhancing the...
research
08/09/2023

Sparse Binary Transformers for Multivariate Time Series Modeling

Compressed Neural Networks have the potential to enable deep learning ac...

Please sign up or login with your details

Forgot password? Click here to reset