An artificial synapse by superlattice-like phase-change material for low-power brain-inspired computing

doi:10.1088/1674-1056/ab892a

中国物理B ›› 2020, Vol. 29 ›› Issue (7): 70701-070701.doi: 10.1088/1674-1056/ab892a

所属专题： SPECIAL TOPIC — Physics in neuromorphic devices

An artificial synapse by superlattice-like phase-change material for low-power brain-inspired computing

Qing Hu(胡庆), Boyi Dong(董博义), Lun Wang(王伦), Enming Huang(黄恩铭), Hao Tong(童浩), Yuhui He(何毓辉), Ming Xu(徐明), Xiangshui Miao(缪向水)

Wuhan National Laboratory for Optoelectronics, School of Optical and Electronic Information,Huazhong University of Science and Technology, Wuhan 430074, China

收稿日期:2020-02-27 修回日期:2020-04-11 出版日期:2020-07-05 发布日期:2020-07-05
通讯作者: Hao Tong, Ming Xu E-mail:tonghao@hust.edu.cn;mxu@hust.edu.cn
基金资助:
Project supported by the National Science and Technology Major Project of China (Grant No. 2017ZX02301007-002), the National Key R&D Plan of China (Grant No. 2017YFB0701701), and the National Natural Science Foundation of China (Grant Nos. 61774068 and 51772113). The authors acknowledge the support from Hubei Key Laboratory of Advanced Memories & Hubei Engineering Research Center on Microelectronics.

An artificial synapse by superlattice-like phase-change material for low-power brain-inspired computing

Qing Hu(胡庆), Boyi Dong(董博义), Lun Wang(王伦), Enming Huang(黄恩铭), Hao Tong(童浩), Yuhui He(何毓辉), Ming Xu(徐明), Xiangshui Miao(缪向水)

Wuhan National Laboratory for Optoelectronics, School of Optical and Electronic Information,Huazhong University of Science and Technology, Wuhan 430074, China

Received:2020-02-27 Revised:2020-04-11 Online:2020-07-05 Published:2020-07-05
Contact: Hao Tong, Ming Xu E-mail:tonghao@hust.edu.cn;mxu@hust.edu.cn
Supported by:
Project supported by the National Science and Technology Major Project of China (Grant No. 2017ZX02301007-002), the National Key R&D Plan of China (Grant No. 2017YFB0701701), and the National Natural Science Foundation of China (Grant Nos. 61774068 and 51772113). The authors acknowledge the support from Hubei Key Laboratory of Advanced Memories & Hubei Engineering Research Center on Microelectronics.

摘要/Abstract

摘要： Phase-change material (PCM) is generating widespread interest as a new candidate for artificial synapses in bio-inspired computer systems. However, the amorphization process of PCM devices tends to be abrupt, unlike continuous synaptic depression. The relatively large power consumption and poor analog behavior of PCM devices greatly limit their applications. Here, we fabricate a GeTe/Sb₂Te₃ superlattice-like PCM device which allows a progressive RESET process. Our devices feature low-power consumption operation and potential high-density integration, which can effectively simulate biological synaptic characteristics. The programming energy can be further reduced by properly selecting the resistance range and operating method. The fabricated devices are implemented in both artificial neural networks (ANN) and convolutional neural network (CNN) simulations, demonstrating high accuracy in brain-like pattern recognition.

关键词: superlattice-like, phase-change material, artificial synapse, low-power consumption

Abstract: Phase-change material (PCM) is generating widespread interest as a new candidate for artificial synapses in bio-inspired computer systems. However, the amorphization process of PCM devices tends to be abrupt, unlike continuous synaptic depression. The relatively large power consumption and poor analog behavior of PCM devices greatly limit their applications. Here, we fabricate a GeTe/Sb₂Te₃ superlattice-like PCM device which allows a progressive RESET process. Our devices feature low-power consumption operation and potential high-density integration, which can effectively simulate biological synaptic characteristics. The programming energy can be further reduced by properly selecting the resistance range and operating method. The fabricated devices are implemented in both artificial neural networks (ANN) and convolutional neural network (CNN) simulations, demonstrating high accuracy in brain-like pattern recognition.

Key words: superlattice-like, phase-change material, artificial synapse, low-power consumption

中图分类号: (Neural networks, fuzzy logic, artificial intelligence)

07.05.Mh

47.20.Hw (Morphological instability; phase changes) 83.10.Tv (Structural and phase changes)

胡庆, 董博义, 王伦, 黄恩铭, 童浩, 何毓辉, 徐明, 缪向水. An artificial synapse by superlattice-like phase-change material for low-power brain-inspired computing[J]. 中国物理B, 2020, 29(7): 70701-070701.

Qing Hu(胡庆), Boyi Dong(董博义), Lun Wang(王伦), Enming Huang(黄恩铭), Hao Tong(童浩), Yuhui He(何毓辉), Ming Xu(徐明), Xiangshui Miao(缪向水). An artificial synapse by superlattice-like phase-change material for low-power brain-inspired computing[J]. Chin. Phys. B, 2020, 29(7): 70701-070701.

参考文献 48

[1]	Yao P, Wu H Q, Gao B, Eryilmaz S B and Qian H 2017 Nat. Commun. 8 15199 doi: 10.1038/ncomms15199
[2]	Yang J J, Strukov D B and Stewart D R 2013 Nat. Nanotechnol. 8 13 doi: 10.1038/nnano.2012.240
[3]	Chi-Sang P and Kuan Z 2011 Frontiers in Neuroscience 5 108
[4]	Yu S M 2018 Proc. IEEE 106 260 doi: 10.1109/JPROC.2018.2790840
[5]	Irem B, Manuel L G, R N S, Timoleon M, Thomas P, Tomas T, Bipin R, Yusuf L, Abu S and Evangelos E 2018 Nat. Commun. 9 1 doi: 10.1038/s41467-017-02088-w
[6]	Merolla P A, Arthur J V, Alvarez-Icaza R, Cassidy A S, Sawada J, Akopyan F, Jackson B L, Imam N, Guo C and Nakamura Y 2014 Science 345 668 doi: 10.1126/science.1254642
[7]	Han S, Liu X Y, Mao H Z, Pu J, Pedram A, Horowitz M A and Dally W J 2016 ACM SIGARCH Comput. Architecture News 44 243 doi: 10.1145/3007787.3001163
[8]	Sebastian A, Le Gallo M, Burr G W, Kim S, BrightSky M and Eleftheriou E 2018 J. Appl. Phys. 124 111101 doi: 10.1063/1.5042413
[9]	Papandreou N, Pantazi A, Sebastian A, Eleftheriou E, Breitwisch M, Lam C and Pozidis H 2010 Solid-State Electron. 54 991 doi: 10.1016/j.sse.2010.04.020
[10]	Wang Z R, Joshi S, Savel'ev S E, Jiang H, Midya R, Lin P, Hu M, Ge N, Strachan J P and Li Z Y 2017 Nat. Mater. 16 101 doi: 10.1038/nmat4756
[11]	Lin C, Tian-Yu W, yawei d, Ming-Yang C, Hao Z, Qing-Qing S, Shi-Jin D, Peng Z, Leon C and Wei Z D 2018 Nanoscale 10 15826 doi: 10.1039/C8NR04734K
[12]	Ambrogio S, Balatti S, Milo V, Carboni R, Wang Z, Calderoni A, Ramaswamy N and Ielmini D 2016 IEEE Symposium on VLSI Technology, June 14-16, 2016, Honolulu, HI, USA, pp. 1-2
[13]	Yang Y C, Yin M H, Yu Z Z, Wang Z W, Zhang T, Cai Y M, Lu W D and Huang R 2017 Adv. Electron. Mater. 3 1700032 doi: 10.1002/aelm.201700032
[14]	Jo S H, Chang T, Ebong I, Bhadviya B B, Mazumder P and Lu W 2010 Nano Letters 10 1297 doi: 10.1021/nl904092h
[15]	Su S, Jian X C, Wang F, Han Y M, Tian Y X, Wang X Y, Zhang H Z and Zhang K L 2016 Chin. Phys. B 25 107302 doi: 10.1088/1674-1056/25/10/107302
[16]	Yao P, Wu H, Gao B, Tang J, Zhang Q, Zhang W, Yang J J and Qian H 2020 Nature 577 641 doi: 10.1038/s41586-020-1942-4
[17]	Wang S, He C, Tang J, Yang R, Shi D and Zhang G 2019 Chin. Phys. B 28 017304 doi: 10.1088/1674-1056/28/1/017304
[18]	Burr G, Narayanan P, Shelby R, Sidler S, Boybat I, di Nolfo C and Leblebici Y 2015 IEEE International Electron Devices Meeting (IEDM), December 7-9, 2015, Washington, DC, USA, pp. 4.4.1-4.4.4
[19]	Choi S, Tan S H, Li Z, Kim Y, Choi C, Chen P Y, Yeon H, Yu S and Kim J 2018 Nat. Mater. 17 335 doi: 10.1038/s41563-017-0001-5
[20]	Xie Y J, Kim W, Kim Y, Kim S, Gonsalves J, BrightSky M, Lam C, Zhu Y and Cha J J 2018 Adv. Mater. 30 1705587 doi: 10.1002/adma.201705587
[21]	Cheng Z G, Carlos R, Nathan Y, David W C, P P W H and Harish B 2018 Adv. Mater. 30 1802435 doi: 10.1002/adma.201802435
[22]	Tuma T, Pantazi A, Le Gallo M, Sebastian A and Eleftheriou E 2016 Nat. Nanotechnol. 11 693 doi: 10.1038/nnano.2016.70
[23]	Sebastian A, Le Gallo M and Krebs D 2014 Nat. Commun. 5 4314 doi: 10.1038/ncomms5314
[24]	Sidler S, Pantazi A, Wózniak S, Leblebici Y and Eleftheriou E 2017 International Conference on Artificial Neural Networks (ICANN), September 11-14, 2017, Alghero, Sardinia, Italy, pp. 281-288
[25]	Ambrogio S, Gallot M, Spoon K, Tsai H, Mackin C, Wesson M, Kariyappa S, Narayanan P, Liu C C and Kumar A 2019 IEEE International Electron Devices Meeting (IEDM), December 9-11, 2019, San Francisco, USA, pp. 6.1.1-6.1.4
[26]	Piveteau C, Le Gallo M, Khaddam-Aljameh R and Sebastian A 2019 IEEE 11th International Memory Workshop (IMW), May 12-15, 2019, Monterey, CA, USA pp. 1-4
[27]	Kim W, Bruce R, Masuda T, Fraczak G, Gong N, Adusumilli P, Ambrogio S, Tsai H, Bruley J and Han J P 2019 Symposium on VLSI Technology, June 9-14, 2019, Kyoto, Japan pp. T66-T67
[28]	Tsai H, Ambrogio S, Mackin C, Narayanan P, Shelby R, Rocki K, Chen A and Burr G 2019 Symposium on VLSI Technology, June 9-14, 2019, Kyoto, Japan pp. T82-T83
[29]	Zhou X L, Xia M J, Rao F, Wu L C and Zhang S B 2014 Acs Appl. Mater Interfaces 6 14207 doi: 10.1021/am503502q
[30]	Burr G W, Kurdi B N, Scott J C, Lam C H, Gopalakrishnan K and Shenoy R S 2008 IBM J. Res. & Dev. 52 449 doi: . Res.
[31]	Bichler O, Suri M, Querlioz D, Vuillaume D, DeSalvo B and Gamrat C 2012 IEEE Trans. Electron. Devices 59 2206 doi: 10.1109/TED.2012.2197951
[32]	Burr G W, Shelby R M, Sidler S, Di Nolfo C, Jang J, Boybat I, Shenoy R S, Narayanan P, Virwani K and Giacometti E U 2015 IEEE Trans. Electron. Devices 62 3498 doi: 10.1109/TED.2015.2439635
[33]	Stefano A, Pritish N, Hsinyu T, M S R, Irem B, Carmelo d N, Severin S, Massimo G, Martina B and P F N C 2018 Nature 558 60 doi: 10.1038/s41586-018-0180-5
[34]	Simpson R E, Fons P, Kolobov A V, Fukaya T, Krbal M, Yagi T and Tominaga J 2011 Nat. Nanotechnol. 6 501 doi: 10.1038/nnano.2011.96
[35]	Kalikka J, Zhou X, Dilcher E, Wall S, Li J and Simpson R E 2016 Nat. Commun. 7 11983 doi: 10.1038/ncomms11983
[36]	Zhou X L, Kalikka J, Ji X L, Wu L C, Song Z T and Simpson R E 2016 Adv. Mater. 28 3007 doi: 10.1002/adma.201505865
[37]	Momand J, Wang R, Boschker J E, Verheijen M A, Calarco R and Kooi B J 2015 Nanoscale 7 19136 doi: 10.1039/C5NR04530D
[38]	Zhang W, Thiess A, Zalden P, Zeller R, Dederichs P H, Raty J Y, Wuttig M, Blügel S and Mazzarello R 2012 Nat. Mater. 11 952 doi: 10.1038/nmat3456
[39]	Xian B L, Nian K C, Xue P W and Hong B S 2018 Adv. Funct. Mater. 28 1803380 doi: 10.1002/adfm.201803380
[40]	Rummelhart D E, Hinton G E and Williams R J 1986 Nature 323 533 doi: 10.1038/323533a0
[41]	Krizhevsky A, Sutskever I and Hinton G 2012 Advances in neural information processing systems 25 1097
[42]	Cireşan D, Meier U and Schmidhuber J 2012 IEEE conference on computer vision and pattern recognition, June 16-21, 2012, Providence, RI, USA p. 3642
[43]	Simard P, Steinkraus D and Platt J C 2003 International Conference on Document Analysis and Recognition, August 6-6, 2003, Edinburgh, UK, UK p. 3
[44]	Ranzato M A, Poultney C, Chopra S and Lecun Y 2007 Advances in Neural Information Processing Systems (Boston: MIT Press) p. 1137
[45]	Tong H, Miao X S, Cheng X M, Wang H, Zhang L, Sun J J, Tong F and Wang J H 2011 Appl. Phys. Lett. 98 101904 doi: 10.1063/1.3562610
[46]	Kuzum D, Jeyasingh R G D, Yu S and Wong H S P 2012 IEEE Trans. Electron. Devices 59 3489
[47]	Kuzum D, Jeyasingh R G D, Lee B and Wong H S P 2012 Nano Lett. 12 2179 doi: 10.1021/nl201040y
[48]	Kang D H, Jun H G, Ryoo K C, Jeong H and Sohn H 2015 Neurocomputing 155 153 doi: 10.1016/j.neucom.2014.12.036

An artificial synapse by superlattice-like phase-change material for low-power brain-inspired computing

An artificial synapse by superlattice-like phase-change material for low-power brain-inspired computing

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

参考文献 48

相关文章 8

Metrics

本文评价

推荐阅读 0

[1]	Shuyuan Lv(吕淑媛), Xinhui Li(李新慧), Wenfeng Luo(罗文峰), and Jie Jia(贾洁). Design of broadband achromatic metasurface device based on phase-change material Ge₂Sb₂Te₅[J]. 中国物理B, 2022, 31(12): 124206-124206.
[2]	Gang Dou(窦刚), Ming-Long Dou(窦明龙), Ren-Yuan Liu(刘任远), and Mei Guo(郭梅). Artificial synaptic behavior of the SBT-memristor[J]. 中国物理B, 2021, 30(7): 78401-078401.
[3]	Bo Liu(刘波), Tao Wei(魏涛), Jing Hu(胡敬), Wanfei Li(李宛飞), Yun Ling(凌云), Qianqian Liu(刘倩倩), Miao Cheng(程淼), and Zhitang Song(宋志棠). Universal memory based on phase-change materials: From phase-change random access memory to optoelectronic hybrid storage[J]. 中国物理B, 2021, 30(5): 58504-058504.
[4]	汪翔, 葛琛, 李格, 郭尔佳, 何萌, 王灿, 杨国桢, 金奎娟. A synaptic transistor with NdNiO₃[J]. 中国物理B, 2020, 29(9): 98101-098101.
[5]	郭延博, 竺立强. Recent progress in optoelectronic neuromorphic devices[J]. 中国物理B, 2020, 29(7): 78502-078502.
[6]	钟海, 孙勤超, 李果, 杜剑宇, 黄河意, 郭尔佳, 何萌, 王灿, 杨国桢, 葛琛, 金奎娟. High-performance synaptic transistors for neuromorphic computing[J]. 中国物理B, 2020, 29(4): 40703-040703.
[7]	王硕培, 何聪丽, 汤建, 杨蓉, 时东霞, 张广宇. Electronic synapses based on ultrathin quasi-two-dimensional gallium oxide memristor[J]. 中国物理B, 2019, 28(1): 17304-017304.
[8]	苏帅, 鉴肖川, 王芳, 韩叶梅, 田雨仙, 王晓旸, 张宏智, 张楷亮. Resistive switching characteristic and uniformity of low-power HfO_x-based resistive random access memory with the BN insertion layer[J]. 中国物理B, 2016, 25(10): 107302-107302.