J. Semicond. > 2021, Volume 42 > Issue 6 > 064101, doi: 10.1088/1674-4926/42/6/064101

ARTICLES

Oscillation neuron based on a low-variability threshold switching device for high-performance neuromorphic computing

Yujia Li1, 2, Jianshi Tang2, 3, , Bin Gao2, 3, Xinyi Li2, Yue Xi2, Wanrong Zhang1, He Qian2, 3 and Huaqiang Wu2, 3,

+ Author Affiliations

 Corresponding author: Jianshi Tang, jtang@tsinghua.edu.cn; Huaqiang Wu, wuhq@tsinghua.edu.cn

PDF

Turn off MathJax

Abstract: Low-power and low-variability artificial neuronal devices are highly desired for high-performance neuromorphic computing. In this paper, an oscillation neuron based on a low-variability Ag nanodots (NDs) threshold switching (TS) device with low operation voltage, large on/off ratio and high uniformity is presented. Measurement results indicate that this neuron demonstrates self-oscillation behavior under applied voltages as low as 1 V. The oscillation frequency increases with the applied voltage pulse amplitude and decreases with the load resistance. It can then be used to evaluate the resistive random-access memory (RRAM) synaptic weights accurately when the oscillation neuron is connected to the output of the RRAM crossbar array for neuromorphic computing. Meanwhile, simulation results show that a large RRAM crossbar array (> 128 × 128) can be supported by our oscillation neuron owing to the high on/off ratio (> 108) of Ag NDs TS device. Moreover, the high uniformity of the Ag NDs TS device helps improve the distribution of the output frequency and suppress the degradation of neural network recognition accuracy (< 1%). Therefore, the developed oscillation neuron based on the Ag NDs TS device shows great potential for future neuromorphic computing applications.

Key words: threshold switching, Ag nanodots, oscillation neuron, neuromorphic computing



[1]
Indiveri G, Linares-Barranco B, Legenstein R, et al. Integration of nanoscale memristor synapses in neuromorphic computing architectures. Nanotechnology, 2013, 24, 384010 doi: 10.1088/0957-4484/24/38/384010
[2]
Ambrogio S, Balatti S, Milo V, et al. Neuromorphic learning and recognition with one-transistor-one-resistor synapses and bistable metal oxide RRAM. IEEE Trans Electron Devices, 2016, 63, 1508 doi: 10.1109/TED.2016.2526647
[3]
Burr G W, Shelby R M, Sebastian A, et al. Neuromorphic computing using non-volatile memory. Adv Phys X, 2017, 2, 89 doi: 10.1080/23746149.2016.1259585
[4]
Zidan M A, Strachan J P, Lu W D. The future of electronics based on memristive systems. Nat Electron, 2018, 1, 22 doi: 10.1038/s41928-017-0006-8
[5]
Merrikh B F, Prezioso M, Chakrabarti B, et al. Implementation of multilayer perceptron network with highly uniform passive memristive crossbar circuits. Nat Commun, 2017, 9, 2331 doi: 10.1038/s41467-018-04482-4
[6]
Yao P, Wu H Q, Gao B, et al. Fully hardware-implemented memristor convolutional neural network. Nature, 2020, 577, 641 doi: 10.1038/s41586-020-1942-4
[7]
Choi S, Yang J, Wang G. Emerging memristive artificial synapses and neurons for energy-efficient neuromorphic computing. Adv Mater, 2020, 32, 2004659 doi: 10.1002/adma.202004659
[8]
Zhu J D, Zhang T, Yang Y C, et al. A comprehensive review on emerging artificial neuromorphic devices. Appl Phys Rev, 2020, 7, 011312 doi: 10.1063/1.5118217
[9]
Kadetotad D, Xu Z H, Mohanty A, et al. Parallel architecture with resistive crosspoint array for dictionary learning acceleration. IEEE J Emerg Sel Top Circuits Syst, 2015, 5, 194 doi: 10.1109/JETCAS.2015.2426495
[10]
Hua Q L, Wu H Q, Gao B, et al. Low-voltage oscillatory neurons for memristor-based neuromorphic systems. Glob Challenges, 2019, 3, 1900015 doi: 10.1002/gch2.201900015
[11]
Dang B J, Liu K Q, Zhu J D, et al. Stochastic neuron based on IGZO Schottky diodes for neuromorphic computing. APL Mater, 2019, 7, 071114 doi: 10.1063/1.5109090
[12]
Li S, Liu X J, Nandi S K, et al. High-endurance MHz electrical self-oscillation in Ti/NbOx bilayer structures. Appl Phys Lett, 2015, 106, 212902 doi: 10.1063/1.4921745
[13]
Gao L G, Chen P Y, Yu S M. NbOx based oscillation neuron for neuromorphic computing. Appl Phys Lett, 2017, 111, 103503 doi: 10.1063/1.4991917
[14]
Duan Q X, Jing Z K, Yang K, et al. Oscillation neuron based on threshold switching characteristics of niobium oxide films. 2019 IEEE International Workshop on Future Computing, 2019, 1
[15]
Woo J, Wang P N, Yu S M. Integrated crossbar array with resistive synapses and oscillation neurons. IEEE Electron Device Lett, 2019, 40, 1313 doi: 10.1109/LED.2019.2921656
[16]
Wang P N, Khan A I, Yu S M. Cryogenic behavior of NbO2 based threshold switching devices as oscillation neurons. Appl Phys Lett, 2020, 116, 162108 doi: 10.1063/5.0006467
[17]
Luo Q, Xu X, Lv H, et al. Cu BEOL compatible selector with high selectivity (> 107), extremely low off-current (pA) and high endurance (> 1010). 2015 IEEE International Electron Devices Meeting (IEDM), 2015, 10.4.1
[18]
Yoo J, Woo J, Song J, et al. Threshold switching behavior of Ag-Si based selector device and hydrogen doping effect on its characteristics. AIP Adv, 2015, 5, 127221 doi: 10.1063/1.4938548
[19]
Du G, Wang C, Li H X, et al. Bidirectional threshold switching characteristics in Ag/ZrO2/Pt electrochemical metallization cells. AIP Adv, 2016, 6, 085316 doi: 10.1063/1.4961709
[20]
Wang Z R, Rao M Y, Midya R, et al. Threshold switching: Threshold switching of Ag or Cu in dielectrics: Materials, mechanism, and applications. Adv Funct Mater, 2018, 28, 1870036 doi: 10.1002/adfm.201870036
[21]
Yoo J, Park J, Song J, et al. Field-induced nucleation in threshold switching characteristics of electrochemical metallization devices. Appl Phys Lett, 2017, 111, 063109 doi: 10.1063/1.4985165
[22]
Wang W, Wang M, Ambrosi E, et al. Surface diffusion-limited lifetime of silver and copper nanofilaments in resistive switching devices. Nat Commun, 2019, 10, 81 doi: https://doi.org/10.1038/s41467-018-07979-0
[23]
Hua Q L, Wu H Q, Gao B, et al. Threshold switching selectors: A threshold switching selector based on highly ordered Ag nanodots for X-point memory applications. Adv Sci, 2019, 6, 1970058 doi: 10.1002/advs.201970058
[24]
Li Y J, Tang J S, Gao B, et al. High-uniformity threshold switching HfO2 -based selectors with patterned Ag nanodots. Adv Sci, 2020, 7, 2002251 doi: 10.1002/advs.202002251
[25]
Xi Y, Gao B, Tang J S, et al. In-memory learning with analog resistive switching memory: A review and perspective. Proc IEEE, 2021, 109, 14 doi: 10.1109/JPROC.2020.3004543
Fig. 1.  (Color online) (a) Schematic diagram of a typical artificial neural network. (b) Circuit implementation of the oscillation neuron with a TS device.

DownLoad: Full-Size Img PowerPoint
Fig. 2.  (Color online) (a) TEM image of the Ag NDs TS device. (b) Schematic illustration of the threshold switching process in the device. (c) Typical current–voltage (I–V) curves for the Ag NDs TS device. (d) Cumulative probability of Vth and Vhold distributions for the Ag NDs TS device. (e) Endurance test of the Ag NDs TS device with over 108 cycles. (f) Measured oscillation waveform of the oscillation neuron.

DownLoad: Full-Size Img PowerPoint
Fig. 3.  (Color online) (a) Oscillation waveforms of the oscillation neuron with different Vin when RL = 50 kΩ, CL = 750 pF. (b) The oscillation frequency as a function of Vin. (c) Oscillation waveforms of the oscillation neuron with different RL when Vin = 1.2 V, CL = 750 pF. (d) The oscillation frequency as a function of RL.

DownLoad: Full-Size Img PowerPoint
Fig. 4.  (Color online) The oscillation frequency as a function of the RRAM crossbar array size under different on/off ratios of the TS device.

DownLoad: Full-Size Img PowerPoint
Fig. 5.  (Color online) (a) The oscillation frequency distribution under different CV. (b) The oscillation frequency distribution of different RL when CV = 7% (top panel) and CV = 30% (bottom panel).

DownLoad: Full-Size Img PowerPoint
Fig. 6.  (Color online) (a) The structure of MLP neural network. (b) Simulation results of the MNIST recognition accuracy loss as a function of the variability of the TS device.

DownLoad: Full-Size Img PowerPoint
[1]
Indiveri G, Linares-Barranco B, Legenstein R, et al. Integration of nanoscale memristor synapses in neuromorphic computing architectures. Nanotechnology, 2013, 24, 384010 doi: 10.1088/0957-4484/24/38/384010
[2]
Ambrogio S, Balatti S, Milo V, et al. Neuromorphic learning and recognition with one-transistor-one-resistor synapses and bistable metal oxide RRAM. IEEE Trans Electron Devices, 2016, 63, 1508 doi: 10.1109/TED.2016.2526647
[3]
Burr G W, Shelby R M, Sebastian A, et al. Neuromorphic computing using non-volatile memory. Adv Phys X, 2017, 2, 89 doi: 10.1080/23746149.2016.1259585
[4]
Zidan M A, Strachan J P, Lu W D. The future of electronics based on memristive systems. Nat Electron, 2018, 1, 22 doi: 10.1038/s41928-017-0006-8
[5]
Merrikh B F, Prezioso M, Chakrabarti B, et al. Implementation of multilayer perceptron network with highly uniform passive memristive crossbar circuits. Nat Commun, 2017, 9, 2331 doi: 10.1038/s41467-018-04482-4
[6]
Yao P, Wu H Q, Gao B, et al. Fully hardware-implemented memristor convolutional neural network. Nature, 2020, 577, 641 doi: 10.1038/s41586-020-1942-4
[7]
Choi S, Yang J, Wang G. Emerging memristive artificial synapses and neurons for energy-efficient neuromorphic computing. Adv Mater, 2020, 32, 2004659 doi: 10.1002/adma.202004659
[8]
Zhu J D, Zhang T, Yang Y C, et al. A comprehensive review on emerging artificial neuromorphic devices. Appl Phys Rev, 2020, 7, 011312 doi: 10.1063/1.5118217
[9]
Kadetotad D, Xu Z H, Mohanty A, et al. Parallel architecture with resistive crosspoint array for dictionary learning acceleration. IEEE J Emerg Sel Top Circuits Syst, 2015, 5, 194 doi: 10.1109/JETCAS.2015.2426495
[10]
Hua Q L, Wu H Q, Gao B, et al. Low-voltage oscillatory neurons for memristor-based neuromorphic systems. Glob Challenges, 2019, 3, 1900015 doi: 10.1002/gch2.201900015
[11]
Dang B J, Liu K Q, Zhu J D, et al. Stochastic neuron based on IGZO Schottky diodes for neuromorphic computing. APL Mater, 2019, 7, 071114 doi: 10.1063/1.5109090
[12]
Li S, Liu X J, Nandi S K, et al. High-endurance MHz electrical self-oscillation in Ti/NbOx bilayer structures. Appl Phys Lett, 2015, 106, 212902 doi: 10.1063/1.4921745
[13]
Gao L G, Chen P Y, Yu S M. NbOx based oscillation neuron for neuromorphic computing. Appl Phys Lett, 2017, 111, 103503 doi: 10.1063/1.4991917
[14]
Duan Q X, Jing Z K, Yang K, et al. Oscillation neuron based on threshold switching characteristics of niobium oxide films. 2019 IEEE International Workshop on Future Computing, 2019, 1
[15]
Woo J, Wang P N, Yu S M. Integrated crossbar array with resistive synapses and oscillation neurons. IEEE Electron Device Lett, 2019, 40, 1313 doi: 10.1109/LED.2019.2921656
[16]
Wang P N, Khan A I, Yu S M. Cryogenic behavior of NbO2 based threshold switching devices as oscillation neurons. Appl Phys Lett, 2020, 116, 162108 doi: 10.1063/5.0006467
[17]
Luo Q, Xu X, Lv H, et al. Cu BEOL compatible selector with high selectivity (> 107), extremely low off-current (pA) and high endurance (> 1010). 2015 IEEE International Electron Devices Meeting (IEDM), 2015, 10.4.1
[18]
Yoo J, Woo J, Song J, et al. Threshold switching behavior of Ag-Si based selector device and hydrogen doping effect on its characteristics. AIP Adv, 2015, 5, 127221 doi: 10.1063/1.4938548
[19]
Du G, Wang C, Li H X, et al. Bidirectional threshold switching characteristics in Ag/ZrO2/Pt electrochemical metallization cells. AIP Adv, 2016, 6, 085316 doi: 10.1063/1.4961709
[20]
Wang Z R, Rao M Y, Midya R, et al. Threshold switching: Threshold switching of Ag or Cu in dielectrics: Materials, mechanism, and applications. Adv Funct Mater, 2018, 28, 1870036 doi: 10.1002/adfm.201870036
[21]
Yoo J, Park J, Song J, et al. Field-induced nucleation in threshold switching characteristics of electrochemical metallization devices. Appl Phys Lett, 2017, 111, 063109 doi: 10.1063/1.4985165
[22]
Wang W, Wang M, Ambrosi E, et al. Surface diffusion-limited lifetime of silver and copper nanofilaments in resistive switching devices. Nat Commun, 2019, 10, 81 doi: https://doi.org/10.1038/s41467-018-07979-0
[23]
Hua Q L, Wu H Q, Gao B, et al. Threshold switching selectors: A threshold switching selector based on highly ordered Ag nanodots for X-point memory applications. Adv Sci, 2019, 6, 1970058 doi: 10.1002/advs.201970058
[24]
Li Y J, Tang J S, Gao B, et al. High-uniformity threshold switching HfO2 -based selectors with patterned Ag nanodots. Adv Sci, 2020, 7, 2002251 doi: 10.1002/advs.202002251
[25]
Xi Y, Gao B, Tang J S, et al. In-memory learning with analog resistive switching memory: A review and perspective. Proc IEEE, 2021, 109, 14 doi: 10.1109/JPROC.2020.3004543

    • Search

    Advanced Search >>

    GET CITATION

    shu

    Export: BibTex EndNote

    Article Metrics

    Article views: 3467 Times PDF downloads: 120 Times Cited by: 0 Times

    History

    Received: 06 January 2021 Revised: 08 February 2021 Online: Accepted Manuscript: 17 March 2021Uncorrected proof: 27 March 2021Published: 01 June 2021

    Catalog

      Email This Article

      User name:
      Email:*请输入正确邮箱
      Code:*验证码错误
      Send
      Article Navigation >  Journal of Semiconductors  > 2021  >  42(6): 064101
      Yujia Li, Jianshi Tang, Bin Gao, Xinyi Li, Yue Xi, Wanrong Zhang, He Qian, Huaqiang Wu. Oscillation neuron based on a low-variability threshold switching device for high-performance neuromorphic computing[J]. Journal of Semiconductors, 2021, 42(6): 064101. doi: 10.1088/1674-4926/42/6/064101 Y J Li, J S Tang, B Gao, X Y Li, Y Xi, W R Zhang, H Qian, H Q Wu, Oscillation neuron based on a low-variability threshold switching device for high-performance neuromorphic computing[J]. J. Semicond., 2021, 42(6): 064101. doi: 10.1088/1674-4926/42/6/064101.Export: BibTex EndNote
      Citation:
      Yujia Li, Jianshi Tang, Bin Gao, Xinyi Li, Yue Xi, Wanrong Zhang, He Qian, Huaqiang Wu. Oscillation neuron based on a low-variability threshold switching device for high-performance neuromorphic computing[J]. Journal of Semiconductors, 2021, 42(6): 064101. doi: 10.1088/1674-4926/42/6/064101

      Y J Li, J S Tang, B Gao, X Y Li, Y Xi, W R Zhang, H Qian, H Q Wu, Oscillation neuron based on a low-variability threshold switching device for high-performance neuromorphic computing[J]. J. Semicond., 2021, 42(6): 064101. doi: 10.1088/1674-4926/42/6/064101.
      Export: BibTex EndNote
      shu

      Oscillation neuron based on a low-variability threshold switching device for high-performance neuromorphic computing

      doi: 10.1088/1674-4926/42/6/064101
      • 1.

        Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China

      • 2.

        Institute of Microelectronics, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing 100084, China

      • 3.

        Beijing Innovation Center for Future Chips (ICFC), Tsinghua University, Beijing 100084, China

      More Information
      • Author Bio:

        Yujia Li is currently a joint PhD. student of Faculty of Information Technology, Beijing University of Technology and Institute of Microelectronics, Tsinghua University from 2016. Her current research interests include design and optimization of resistive switching memory and selector devices as well as their applications in neuromorphic computing

        Jianshi Tang (Senior Member, IEEE) received the B.S. degree in microelectronics and nano-electronics from Tsinghua University, Beijing, China, in 2008, and the Ph.D. degree in electrical engineering from the University of California at Los Angeles, Los Angeles, CA, USA, in 2014. From 2015 to 2019, he worked at the IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA. He is currently an Assistant Professor with the Institute of Microelectronics, Tsinghua University. He has published over 100 journal articles and conference proceedings, and filed over 60 patents, 20 of which have been granted. His current research interests include emerging memory and neuromorphic computing and carbon nanotube electronics. Prof. Tang has received many awards, including the National Young Thousand Talents Plan, the NT18 Best Young Scientist Award, the IEEE Best Lightning Talk, and the IBM Invention Achievement Awards

        Bin Gao (Senior Member, IEEE) received the B.S. degree in physics and the Ph.D. degree in microelectronics from Peking University, Beijing, China, in 2008 and 2013, respectively. He is currently an Associate Professor of microelectronics with Tsinghua University, Beijing. His current research interests include emerging memory devices and neuromorphic computing

        Xinyi Li received the Ph.D. degree in Microelectronics and Solid State Electronics from TianJin University, TianJin, China, in 2010. She is currently working with the Institute of Microelectronics, Tsinghua University. Her current research interests include neuromorphic devices and their application in neuromorphic computing

        Yue Xi (Student Member, IEEE) received the bachelor’s degree in microelectronics from Xi’an Jiaotong University, Xi’an, China, in 2017. He is currently pursuing the Ph.D. degree in microelectronics with Tsinghua University, Beijing, China. His current research interests include ana-log resistive switching memory devices and memristor-based neuromorphic computing

        Wanrong Zhang received the B.S. and M.S. degrees in microelectronics and solid-state electronics from Lanzhou University, Lanzhou, China, in 1987 and 1990, respectively, and the Ph.D. degree in microelectronics and solid-state electronics from Xi’an Jiaotong University, Xi’an, China, in 1996. He is currently a Professor and a Ph.D. Supervisor with the Faculty of Information Technology, Beijing University of Technology, Beijing, China. His current research interests include RF/microwave/ millimeter-wave devices and circuits, mixed-signal circuits, cryogenic electronics, device-to-circuit interactions, noise and linearity, reliability physics, device-level simulation, and compact circuit modeling

        He Qian (Member, IEEE) received the Ph.D. degree in microelectronics from Xi’an Jiao-tong University, Xi’an, China, in 1990. From 1990 to 2006, he worked with the Institute of Microelectronics, Chinese Academy of Sciences (IMECAS), Beijing, China, where he became a Professor in 1996 and the Director in 2001. From 2006 to 2008, he worked for the Samsung Semiconductor China Research and Development Center (SSCR), Nanjing, China, as the Director. In 2009, he joined the Institute of Micro-electronics, Tsinghua University (IMTU), Beijing, as a Professor. His current research interests include resistive random access memory (RRAM), 3-D NAND, and neuromorphic computing based on RRAM array

        Huaqiang Wu (Senior Member, IEEE) received the double B.S. degrees in material science and engineering and enterprise management from Tsinghua University, Beijing, China, in 2000, and the Ph.D. degree in electrical engineering from Cornell University, Ithaca, NY, USA, in 2005. From 2006 to 2008, he was a Senior Engineer with Spansion LLC, Sunnyvale, CA, USA. He joined the Institute of Microelectronics, Tsinghua University, in 2009, where he is currently a Professor and the Director of the Institute of Microelectronics. He also serves as the Deputy Director of the Beijing Innovation Center for Future Chip (ICFC). He has published more than 100 technical articles and owns more than 60 patents. His research interests include emerging memories and neuromorphic computing

      • Corresponding author: jtang@tsinghua.edu.cn; wuhq@tsinghua.edu.cn
      • Received Date: 2021-01-06
      • Revised Date: 2021-02-08
      • Published Date: 2021-06-10

      Catalog

        Journal of Semiconductors © 2017 All Rights Reserved   京ICP备05085259号-2

        /

        DownLoad:  Full-Size Img  PowerPoint
        Return
        Return