Techniques for visualizing LSTMs applied to electrocardiograms
Abstract
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.
- Publication:
-
arXiv e-prints
- Pub Date:
- May 2017
- DOI:
- 10.48550/arXiv.1705.08153
- arXiv:
- arXiv:1705.08153
- Bibcode:
- 2017arXiv170508153V
- Keywords:
-
- Statistics - Machine Learning;
- Computer Science - Machine Learning
- E-Print:
- presented at 2018 ICML Workshop on Human Interpretability in Machine Learning (WHI 2018), Stockholm, Sweden