Indexed by: Journal paper

First Author: 李鑫

Correspondence Author: He Qiang,TONG HAO

Co-author: He Qiang,TONG HAO

Journal: IEEE Electron Device Letters

Affiliation of Author(s): 华中科技大学

Discipline: Engineering

First-Level Discipline: Electronic Science And Technology

Document Type: J

Volume: 43

Issue: 4

Page Number: 565-568

Key Words: 相变存储器、双极性操作、阻值漂移、电导水平、、神经网络、卷积神经网络

DOI number: 10.1109/LED.2022.3154440

Date of Publication: 4461-06-01

Abstract: Phase change materials, which has been focused on the non-volatile memory field, show the possibility to carry out data storage and computing in the same physical location. However, the resistance drift behavior of phase change memory has been a huge barrier not only to traditional binary memory application for a long time, but to multi-level storage and therefore the neural network computing. Here, a bipolar programming scheme is exploited to achieve drift-reduced intermediate states and convolutional neural network (CNN) computations in Ge 2 Sb 2 Te 5 (GST) based memory cells. Experiments show that the resistance drift phenomena under bipolar programming have been reduced. Furthermore, the impact of bipolar operation on CNN for inference is investigated. This work provides effective means for implementing phase change neuromorphic processor with enhanced stability.

Links to published journals: https://ieeexplore.ieee.org/abstract/document/9721231