Problems of representation of electrocardiograms in convolutional neural networks

TL;DR

This paper explores the inherent challenges in representing electrocardiograms with convolutional neural networks, highlighting systemic issues caused by the flexible nature of signal patterns and surprising effects on generalization.

Contribution

It identifies fundamental problems in modeling one-dimensional signals with CNNs and discusses their systemic nature and impact on generalization.

Findings

Systemic issues in CNN modeling of ECG signals.

Problems caused by flexible pattern components.

Counterintuitive effects on network generalization.

Abstract

Using electrocardiograms as an example, we demonstrate the characteristic problems that arise when modeling one-dimensional signals containing inaccurate repeating pattern by means of standard convolutional networks. We show that these problems are systemic in nature. They are due to how convolutional networks work with composite objects, parts of which are not fixed rigidly, but have significant mobility. We also demonstrate some counterintuitive effects related to generalization in deep networks.