CUED Publications database

Techniques for visualizing LSTMs applied to electrocardiograms

Westhuizen, JVD and Lasenby, J Techniques for visualizing LSTMs applied to electrocardiograms. (Unpublished)

Full text not available from this repository.

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.

Item Type: Article
Uncontrolled Keywords: stat.ML stat.ML cs.LG
Subjects: UNSPECIFIED
Divisions: Div F > Signal Processing and Communications
Depositing User: Cron Job
Date Deposited: 17 Jul 2017 20:00
Last Modified: 18 Feb 2021 14:28
DOI: