What does an LSTM look for in classifying heartbeats?

05/23/2017
by   Jos van der Westhuizen, et al.
0

Long short-term memory (LSTM) recurrent neural networks are renowned for being uninterpretable "black boxes". In the medical domain where LSTMs have shown promise, this is specifically concerning because it is imperative to understand the decisions made by machine learning models in such acute situations. This study employs techniques used in the convolutional neural network domain to elucidate the inputs that are important when LSTMs classify electrocardiogram signals. Of the various techniques available to determine input feature saliency, it was found that learning an occlusion mask is the most effective.

READ FULL TEXT

page 6

page 7

page 8

research
01/02/2019

Performance of Three Slim Variants of The Long Short-Term Memory (LSTM) Layer

The Long Short-Term Memory (LSTM) layer is an important advancement in t...
research
12/29/2018

SLIM LSTMs

Long Short-Term Memory (LSTM) Recurrent Neural networks (RNNs) rely on g...
research
05/05/2020

Long short-term memory networks and laglasso for bond yield forecasting: Peeping inside the black box

Modern decision-making in fixed income asset management benefits from in...
research
12/02/2019

CNNs, LSTMs, and Attention Networks for Pathology Detection in Medical Data

For the weakly supervised task of electrocardiogram (ECG) rhythm classif...
research
08/02/2019

Dialogue Act Classification in Group Chats with DAG-LSTMs

Dialogue act (DA) classification has been studied for the past two decad...
research
07/16/2023

Exploiting FPGA Capabilities for Accelerated Biomedical Computing

This study presents advanced neural network architectures including Conv...
research
09/16/2018

Classifying Process Instances Using Recurrent Neural Networks

Process Mining consists of techniques where logs created by operative sy...

Please sign up or login with your details

Forgot password? Click here to reset