In‐Memory Computing using Memristor Arrays with Ultrathin 2D PdSeOx/PdSe2 Heterostructure

Yesheng Li; Shuai Chen; Zhigen Yu; Sifan Li; Yao Xiong; Mer‐Er Pam; Yong‐Wei Zhang; Kah-Wee Ang

doi:10.1002/adma.202201488

journal article Open Access May 06, 2022

In‐Memory Computing using Memristor Arrays with Ultrathin 2D PdSeOx/PdSe2 Heterostructure

Yesheng Li

Shuai Chen

Zhigen Yu Sifan Li

Yao Xiong

Mer‐Er Pam Yong‐Wei Zhang Kah-Wee Ang

Advanced Materials Vol. 34 No. 26 · Wiley

View at Publisher Save 10.1002/adma.202201488

Abstract

AbstractIn‐memory computing based on memristor arrays holds promise to address the speed and energy issues of the classical von Neumann computing system. However, the stochasticity of ions’ transport in conventional oxide‐based memristors imposes severe intrinsic variability, which compromises learning accuracy and hinders the implementation of neural network hardware accelerators. Here, these challenges are addressed using a low‐voltage memristor array based on an ultrathin PdSeOx/PdSe2 heterostructure switching medium realized by a controllable ultraviolet (UV)–ozone treatment. A distinctively different ions’ transport mechanism is revealed in the heterostructure that can confine the formation of conductive filaments, leading to a remarkable uniform switching with low set and reset voltage variability values of 4.8% and −3.6%, respectively. Moreover, convolutional image processing is further implemented using various crossbar kernels that achieve a high recognition accuracy of ≈93.4% due to the highly linear and symmetric analog weight update as well as multiple conductance states, manifesting its potential beyond von Neumann computing.

Topics

No keywords indexed for this article. Browse by subject →

References

53

[1]

Memristive crossbar arrays for brain-inspired computing

Qiangfei Xia, J. Joshua Yang

Nature Materials 10.1038/s41563-019-0291-x

[2]

10.1038/s41565-020-0655-z

[3]

In-memory computing with resistive switching devices

Daniele Ielmini, H.-S. Philip Wong

Nature Electronics 10.1038/s41928-018-0092-2

[4]

The future of electronics based on memristive systems

Mohammed A. Zidan, John Paul Strachan, Wei D. Lu

Nature Electronics 10.1038/s41928-017-0006-8

[5]

10.1038/s41586-020-1942-4

[6]

10.1038/s41928-020-0397-9

[7]

10.1063/1.5124915

[8]

Reliable Memristive Switching Memory Devices Enabled by Densely Packed Silver Nanocone Arrays as Electric-Field Concentrators

Byoung Kuk You, Jong Min Kim, Daniel J. Joe et al.

ACS Nano 10.1021/acsnano.6b04578

[9]

10.1002/aelm.201800835

[10]

10.1002/adfm.201808430

[11]

10.1002/pssr.201800429

[12]

Efficient and self-adaptive in-situ learning in multilayer memristor neural networks

Daniel Belkin, Yunning Li, Peng Yan et al.

Nature Communications 10.1038/s41467-018-04484-2

[13]

10.1038/s41563-017-0001-5

[14]

10.1038/ncomms5232

[15]

10.1038/ncomms1737

[16]

10.1002/adfm.202004609

[17]

10.1039/c9nr09845c

[18]

10.1063/1.4983465

[19]

10.1002/aelm.201900439

[20]

10.1002/aelm.201800833

[21]

10.1038/srep43664

[22]

10.1038/nature14441

[23]

10.1002/adma.201703232

[24]

Memristors Based on 2D Materials as an Artificial Synapse for Neuromorphic Electronics

Woong Huh, Donghun Lee, Chul‐Ho Lee

Advanced Materials 10.1002/adma.202002092

[25]

10.1038/s41565-020-0647-z

[26]

10.1002/adma.201806790

[27]

Anomalous resistive switching in memristors based on two-dimensional palladium diselenide using heterophase grain boundaries

Yesheng Li, Leyi Loh, Sifan Li et al.

Nature Electronics 10.1038/s41928-021-00573-1

[28]

10.1126/sciadv.1700481

[29]

10.1021/acs.nanolett.0c02951

[30]

10.1038/nmat4135

[31]

10.1002/adma.201606927

[32]

10.1021/acsami.9b17160

[33]

10.1002/aelm.201900467

[34]

10.1002/aelm.201800944

[35]

10.1021/jacs.7b04865

[36]

10.1002/adfm.201806878

[37]

10.1103/physrevlett.121.086101

[38]

10.1021/acs.jpclett.9b03312

[39]

10.1002/adfm.202007587

[40]

10.1038/s41699-021-00268-3

[41]

10.1103/physrevb.99.245114

[42]

10.1021/acsami.9b21287

[43]

10.1002/adma.202103656

[44]

10.1021/acsnano.0c00180

[45]

10.1088/1361-6463/ab42b0

[46]

10.1063/1.4939436

[47]

10.1038/s41467-021-23180-2

[48]

10.1002/aelm.201900287

[49]

Chen P. (2017)

[50]

10.1002/aelm.201600090

Showing 50 of 53 references

Metrics

117

Citations

53

References

Details

Published: May 06, 2022
Vol/Issue: 34(26)
License: View

Authors

Y

Yesheng Li

Department of Electrical and Computer Engineering National University of Singapore 4 Engineering Drive 3 Singapore 117583 Singapore; Department of Microstructure School of Physics and Technology Wuhan University Wuhan 430072 China

S

Shuai Chen

Institute for High Performance Computing A*STAR 1 Fusionopolis Way Singapore 138632 Singapore

Z

Zhigen Yu

Institute for High Performance Computing A*STAR 1 Fusionopolis Way Singapore 138632 Singapore

S

Sifan Li

Department of Electrical and Computer Engineering National University of Singapore 4 Engineering Drive 3 Singapore 117583 Singapore

Y

Yao Xiong

Department of Physics School of Science Wuhan University of Technology Wuhan 430070 China

M

Mer‐Er Pam

Department of Electrical and Computer Engineering National University of Singapore 4 Engineering Drive 3 Singapore 117583 Singapore

Y

Yong‐Wei Zhang

Institute for High Performance Computing A*STAR 1 Fusionopolis Way Singapore 138632 Singapore

K

Kah-Wee Ang

Department of Electrical and Computer Engineering National University of Singapore 4 Engineering Drive 3 Singapore 117583 Singapore; Institute of Materials Research and Engineering A*STAR 2 Fusionopolis Way Singapore 138634 Singapore

Funding

Science and Engineering Research Council Award: A2083c0061

Cite This Article

Yesheng Li, Shuai Chen, Zhigen Yu, et al. (2022). In‐Memory Computing using Memristor Arrays with Ultrathin 2D PdSeOx/PdSe2 Heterostructure. Advanced Materials, 34(26). https://doi.org/10.1002/adma.202201488

In‐Memory Computing using Memristor Arrays with Ultrathin 2D PdSeOx/PdSe2 Heterostructure

You May Also Like