Please wait a minute...
Chin. Phys. B, 2023, Vol. 32(7): 078505    DOI: 10.1088/1674-1056/ac9cbc
INTERDISCIPLINARY PHYSICS AND RELATED AREAS OF SCIENCE AND TECHNOLOGY Prev   Next  

Lightweight and highly robust memristor-based hybrid neural networks for electroencephalogram signal processing

Peiwen Tong(童霈文), Hui Xu(徐晖), Yi Sun(孙毅), Yongzhou Wang(汪泳州), Jie Peng(彭杰),Cen Liao(廖岑), Wei Wang(王伟), and Qingjiang Li(李清江)
College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China
Abstract  Memristor-based neuromorphic computing shows great potential for high-speed and high-throughput signal processing applications, such as electroencephalogram (EEG) signal processing. Nonetheless, the size of one-transistor one-resistor (1T1R) memristor arrays is limited by the non-ideality of the devices, which prevents the hardware implementation of large and complex networks. In this work, we propose the depthwise separable convolution and bidirectional gate recurrent unit (DSC-BiGRU) network, a lightweight and highly robust hybrid neural network based on 1T1R arrays that enables efficient processing of EEG signals in the temporal, frequency and spatial domains by hybridizing DSC and BiGRU blocks. The network size is reduced and the network robustness is improved while ensuring the network classification accuracy. In the simulation, the measured non-idealities of the 1T1R array are brought into the network through statistical analysis. Compared with traditional convolutional networks, the network parameters are reduced by 95% and the network classification accuracy is improved by 21% at a 95% array yield rate and 5% tolerable error. This work demonstrates that lightweight and highly robust networks based on memristor arrays hold great promise for applications that rely on low consumption and high efficiency.
Keywords:  memristor      lightweight      robust      hybrid neural networks      depthwise separable convolution      bidirectional gate recurrent unit (BiGRU)      one-transistor one-resistor (1T1R) arrays  
Received:  02 August 2022      Revised:  22 September 2022      Accepted manuscript online:  21 October 2022
PACS:  85.35.-p (Nanoelectronic devices)  
  84.37.+q (Measurements in electric variables (including voltage, current, resistance, capacitance, inductance, impedance, and admittance, etc.))  
  07.05.Mh (Neural networks, fuzzy logic, artificial intelligence)  
  87.19.lv (Learning and memory)  
Fund: Project supported by the National Key Research and Development Program of China (Grant No. 2019YFB2205102) and the National Natural Science Foundation of China (Grant Nos. 61974164, 62074166, 61804181, 62004219, 62004220, and 62104256).
Corresponding Authors:  Wei Wang, Qingjiang Li     E-mail:  wangwei_esss@nudt.edu.cn;qingjiangli@nudt.edu.cn

Cite this article: 

Peiwen Tong(童霈文), Hui Xu(徐晖), Yi Sun(孙毅), Yongzhou Wang(汪泳州), Jie Peng(彭杰),Cen Liao(廖岑), Wei Wang(王伟), and Qingjiang Li(李清江) Lightweight and highly robust memristor-based hybrid neural networks for electroencephalogram signal processing 2023 Chin. Phys. B 32 078505

[1] Shanechi M M 2019 Nat. Neurosci. 22 1554
[2] Kao J C, Stavisky S D, Sussillo D, Nuyujukian P and Shenoy K V 2014 Proc. IEEE 102 666
[3] Hong G and Lieber C M 2019 Nat. Rev. Neurosci. 20 330
[4] Maharbiz M M, Muller R, Alon E, Rabaey J M and Carmena J M 2017 Proc. IEEE 105 73
[5] Brandman D M, Cash S S and Hochberg L R 2017 IEEE Trans. Neural Syst. Rehabil. Eng. 25 1687
[6] Liu X, Zhang M, Xiong T, Richardson A G, Lucas T H, Chin P S, Etienne-Cummings R, Tran T D and Van Der Spiegel J 2016 IEEE Trans. Biomed. Circuits Syst. 10 874
[7] Cheng C H, Tsai P Y, Yang T Y, Cheng W H, Yen T Y, Luo Z, Qian X H, Chen Z X, Lin T H, Chen W H, Chen W M, Liang S F, Shaw F Z, Chang C S, Hsin Y L, Lee C Y, Ker M D and Wu C Y 2018 IEEE J. Solid-State Circuits 53 3314
[8] Merkel C, Saleh Q, Donahue C and Kudithipudi D 2014 Procedia Comput. Sci. 41 249
[9] Park S, Chu M, Kim J, Noh J, Jeon M, Hun Lee B, Hwang H, Lee B and Lee B G 2015 Sci. Rep. 5 1
[10] Zhang J, Xu H, Long H, Hou K, Li Z, Yang Z, Wang Y and Li Q 2021 IEEE 4th Int. Conf. Electron. Technol. ICET 2021 851
[11] Liu Z, Tang J, Hong B, Wu H and Gao B 2020 Nat. Commun. 11 4234
[12] Liu J, Ye F and Xiong H 2021 J. Neural Eng. 18
[13] Cai H 2018 ACS Appl. Mater. Interfaces 10 22408
[14] Lawhern V J, Solon A J, Waytowich N R, Gordon S M, Hung C P and Lance B J 2018 J. Neural Eng. 15 056013
[15] Schirrmeister R T, Springenberg J T, Fiederer L D J, Glasstetter M, Eggensperger K, Tangermann M, Hutter F, Burgard W and Ball T 2017 Hum. Brain Mapp. 38 5391
[16] Ang K K, Chin Z Y, Zhang H and Guan C 2008 Proc. Int. Jt. Conf. Neural Networks 2390
[17] Gramfort A, Luessi M, Larson E, Engemann D A, Strohmeier D, Brodbeck C, Parkkonen L and Hämäläinen M S 2014 Neuroimage 86 446
[18] Gramfort A, Luessi M, Larson E, Engemann D A, Strohmeier D, Brodbeck C, Goj R, Jas M, Brooks T, Parkkonen L and Hämäläinen M 2013 Front. Neurosci. 7
[19] Chen J, Wu H, Gao B, Tang J, Zhang W and Qian H 2019 IEEE Int. Work. Futur. Comput. IWOFC 2019 2019
[1] Dynamical analysis, geometric control and digital hardware implementation of a complex-valued laser system with a locally active memristor
Yi-Qun Li(李逸群), Jian Liu(刘坚), Chun-Biao Li(李春彪),Zhi-Feng Hao(郝志峰), and Xiao-Tong Zhang(张晓彤). Chin. Phys. B, 2023, 32(8): 080503.
[2] A progressive surrogate gradient learning for memristive spiking neural network
Shu Wang(王姝), Tao Chen(陈涛), Yu Gong(龚钰), Fan Sun(孙帆), Si-Yuan Shen(申思远), Shu-Kai Duan(段书凯), and Li-Dan Wang(王丽丹). Chin. Phys. B, 2023, 32(6): 068704.
[3] Synchronization coexistence in a Rulkov neural network based on locally active discrete memristor
Ming-Lin Ma(马铭磷), Xiao-Hua Xie(谢小华), Yang Yang(杨阳), Zhi-Jun Li(李志军), and Yi-Chuang Sun(孙义闯). Chin. Phys. B, 2023, 32(5): 058701.
[4] Doping-enhanced robustness of anomaly-related magnetoresistance in WTe2±α flakes
Jianchao Meng(孟建超), Xinxiang Chen(陈鑫祥), Tingna Shao(邵婷娜), Mingrui Liu(刘明睿), Weimin Jiang(姜伟民), Zitao Zhang(张子涛), Changmin Xiong(熊昌民), Ruifen Dou(窦瑞芬), and Jiacai Nie(聂家财). Chin. Phys. B, 2023, 32(4): 047502.
[5] A robust method for performance evaluation of the vapor cell for magnetometry
Zhi Liu(柳治), Sheng Zou(邹升), Kaifeng Yin(尹凯峰), Tao Shi(石韬),Junjian Tang(唐钧剑), and Heng Yuan(袁珩). Chin. Phys. B, 2023, 32(4): 040703.
[6] Hopf bifurcation and phase synchronization in memristor-coupled Hindmarsh-Rose and FitzHugh-Nagumo neurons with two time delays
Zhan-Hong Guo(郭展宏), Zhi-Jun Li(李志军), Meng-Jiao Wang(王梦蛟), and Ming-Lin Ma(马铭磷). Chin. Phys. B, 2023, 32(3): 038701.
[7] Research on the model of high robustness computational optical imaging system
Yun Su(苏云), Teli Xi(席特立), and Xiaopeng Shao(邵晓鹏). Chin. Phys. B, 2023, 32(2): 024202.
[8] Engineering topological state transfer in four-period Su-Schrieffer-Heeger chain
Xi-Xi Bao(包茜茜), Gang-Feng Guo(郭刚峰), and Lei Tan(谭磊). Chin. Phys. B, 2023, 32(2): 020301.
[9] Memristor's characteristics: From non-ideal to ideal
Fan Sun(孙帆), Jing Su(粟静), Jie Li(李杰), Shukai Duan(段书凯), and Xiaofang Hu(胡小方). Chin. Phys. B, 2023, 32(2): 028401.
[10] High-performance artificial neurons based on Ag/MXene/GST/Pt threshold switching memristors
Xiao-Juan Lian(连晓娟), Jin-Ke Fu(付金科), Zhi-Xuan Gao(高志瑄),Shi-Pu Gu(顾世浦), and Lei Wang(王磊). Chin. Phys. B, 2023, 32(1): 017304.
[11] Firing activities in a fractional-order Hindmarsh-Rose neuron with multistable memristor as autapse
Zhi-Jun Li(李志军), Wen-Qiang Xie(谢文强), Jin-Fang Zeng(曾金芳), and Yi-Cheng Zeng(曾以成). Chin. Phys. B, 2023, 32(1): 010503.
[12] Memristor hyperchaos in a generalized Kolmogorov-type system with extreme multistability
Xiaodong Jiao(焦晓东), Mingfeng Yuan(袁明峰), Jin Tao(陶金), Hao Sun(孙昊), Qinglin Sun(孙青林), and Zengqiang Chen(陈增强). Chin. Phys. B, 2023, 32(1): 010507.
[13] High throughput N-modular redundancy for error correction design of memristive stateful logic
Xi Zhu(朱熙), Hui Xu(徐晖), Weiping Yang(杨为平), Zhiwei Li(李智炜), Haijun Liu(刘海军), Sen Liu(刘森), Yinan Wang(王义楠), and Hongchang Long(龙泓昌). Chin. Phys. B, 2023, 32(1): 018502.
[14] Robustness measurement of scale-free networks based on motif entropy
Yun-Yun Yang(杨云云), Biao Feng(冯彪), Liao Zhang(张辽), Shu-Hong Xue(薛舒红), Xin-Lin Xie(谢新林), and Jian-Rong Wang(王建荣). Chin. Phys. B, 2022, 31(8): 080201.
[15] Pulse coding off-chip learning algorithm for memristive artificial neural network
Ming-Jian Guo(郭明健), Shu-Kai Duan(段书凯), and Li-Dan Wang(王丽丹). Chin. Phys. B, 2022, 31(7): 078702.
No Suggested Reading articles found!