Open AccessHigh On/Off Ratio Spintronic Multi‐Level Memory Unit for Deep Neural Network (Adv. Sci. 13/2022)
Author(s) -
Zhang Kun,
Jia Xiaotao,
Cao Kaihua,
Wang Jinkai,
Zhang Yue,
Lin Kelian,
Chen Lei,
Feng Xueqiang,
Zheng Zhenyi,
Zhang Zhizhong,
Zhang Youguang,
Zhao Weisheng
Publication year - 2022
Publication title -
advanced science
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 5.388
H-Index - 100
ISSN - 2198-3844
DOI - 10.1002/advs.202270086
Subject(s) - spintronics , artificial neural network , computer science , unit (ring theory) , deep learning , artificial intelligence , physics , ferromagnetism , psychology , mathematics education , quantum mechanics
Spintronic Multi‐Level Memory Unit In article number 2103357 by Kun Zhang, Yue Zhang, and co‐workers, a spintronic multi‐level memory unit (MLMU) with high on/off ratio is constructed by integrating a magnetic tunnel junction chain and a diode in parallel. This MLMU can enable high‐accuracy artificial intelligence applications, such as a deep neural network accelerator for image classification. Just as described in the cover design, the MLMUs are regarded as building blocks to assemble the artificial‐intelligence brain.