Reservoir-Based 1D Convolution: Low-Training-Cost AI
IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences · 01.06.2024 · E107.A (6) · 941-944
DOI: 10.1587/transfun.2023eal2050 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, erschienen am 01.06.2024. Verfasst von Yuichiro TANAKA und 1 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 22 Literaturangaben.
Abstract (Originalsprache)
In this study, we introduce a reservoir-based one-dimensional (1D) convolutional neural network that processes time-series data at a low computational cost, and investigate its performance and training time. Experimental results show that the proposed network consumes lower training computational costs and that it outperforms the conventional reservoir computing in a sound-classification task.
Zitieren
APA
TANAKA, Y., & TAMUKOH, H. (2024). Reservoir-Based 1D Convolution: Low-Training-Cost AI. IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, E107.A(6), 941-944. https://doi.org/10.1587/transfun.2023eal2050
Vancouver
TANAKA Y, TAMUKOH H. Reservoir-Based 1D Convolution: Low-Training-Cost AI. IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences. 2024;E107.A(6):941-944. doi:10.1587/transfun.2023eal2050
BibTeX
@article{TANAKA2024,
author = {TANAKA, Yuichiro and TAMUKOH, Hakaru},
title = {Reservoir-Based 1D Convolution: Low-Training-Cost AI},
journal = {IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences},
year = {2024},
volume = {E107.A},
number = {6},
pages = {941--944},
doi = {10.1587/transfun.2023eal2050}
}
EUVIMED