This paper explores four different visualization techniques for long short-term memory (LSTM) networks applied to continuous-valued time series. On the datasets analysed, we find that the best visualization technique is to learn an input deletion mask that optimally reduces the true class score. With a specific focus on single-lead electrocardiograms from the MIT-BIH arrhythmia dataset, we show that salient input features for the LSTM classifier align well with medical theory.
Cite
@article{arxiv.1705.08153,
title = {Techniques for visualizing LSTMs applied to electrocardiograms},
author = {Jos van der Westhuizen and Joan Lasenby},
journal= {arXiv preprint arXiv:1705.08153},
year = {2018}
}
Comments
presented at 2018 ICML Workshop on Human Interpretability in Machine Learning (WHI 2018), Stockholm, Sweden