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...

Celý popis

Podrobná bibliografia

Vydané v:	AIMS mathematics Ročník 9; číslo 1; s. 792 - 817
Hlavní autori:	Omae, Yuto, Sakai, Yusuke, Takahashi, Hirotaka
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	AIMS Press 01.01.2024
Predmet:	convolutional neural network signal importance signal selection algorithm time-directional grad-cam
ISSN:	2473-6988, 2473-6988
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!