Silicon based Bi0.9La0.1FeO3 ferroelectric tunnel junction memristor for convolutional neural network application

Gongjie Liu; Wei Wang; Zhenqiang Guo; Xiaotong Jia; Zhen Zhao; Zhenyu Zhou; Jiangzhen Niu; Guojun Duan; Xiaobing Yan

doi:10.1039/d3nr00510k

Silicon based Bi_0.9La_0.1FeO₃ ferroelectric tunnel junction memristor for convolutional neural network application

Nanoscale. 2023 Aug 10;15(31):13009-13017. doi: 10.1039/d3nr00510k.

Authors

Gongjie Liu¹, Wei Wang¹, Zhenqiang Guo¹, Xiaotong Jia¹, Zhen Zhao¹, Zhenyu Zhou¹, Jiangzhen Niu¹, Guojun Duan¹, Xiaobing Yan¹

Affiliation

¹ Key Laboratory of brain-like neuromorphic devices and Systems of Hebei Province, College of Electron and Information Engineering, Hebei University, Baoding 071002, P. R. China. yanxiaobing@ime.ac.cn.

PMID: 37485606
DOI: 10.1039/d3nr00510k

Abstract

Computing in memory (CIM) based on memristors is expected to completely solve the dilemma caused by von Neumann architecture. However, the performance of memristors based on traditional conductive filament mechanism is unstable. In this study, we report a nonvolatile high-performance memristor based on ferroelectric tunnel junction (FTJ) Pd/Bi_0.9La_0.1FeO₃ (6.9 nm) (BLFO)/La_0.67Sr_0.33MnO₃ (LSMO) on a silicon substrate. The conductance of this device was adjusted by different pulse stimulation parameter to achieve various synaptic functions because of ferroelectric polarization reversal. Based on the multiple conductance characteristics of the devices and the high linearity and symmetry of weight updating, image processing and VGG8 convolutional neural network (CNN) simulation based on the devices were realized. Excellent results of the image processing are demonstrated. The recognition accuracy of CNN offline learning reached an astonishing 92.07% based on Cifar-10 dataset. This provides a more feasible solution to break through the bottleneck of von Neumann architecture.