Features gradient-based signals selection algorithm of linear complexity for convolutional neural networks

Recently, convolutional neural networks (CNNs) for classification by time domain data of multi-signals have been developed. Although some signals are important for correct classification, others are not. The calculation, memory, and data collection costs increase when data that include unimportant s...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	AIMS mathematics Jg. 9; H. 1; S. 792 - 817
Hauptverfasser:	Omae, Yuto, Sakai, Yusuke, Takahashi, Hirotaka
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	AIMS Press 01.01.2024
Schlagworte:	convolutional neural network signal importance signal selection algorithm time-directional grad-cam
ISSN:	2473-6988, 2473-6988
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!