High On/Off Ratio Spintronic Multi‐Level Memory Unit for Deep Neural Network (Adv. Sci. 13/2022)
Kun Zhang, Xiaotao Jia, Kaihua Cao, Jinkai Wang, Yue Zhang, Kelian Lin, Lei Chen, Xueqiang Feng, Zhenyi Zheng, Zhizhong Zhang, Youguang Zhang, Weisheng Zhao · Advanced Science · 2022
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.