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

Yujia Li; Jianshi Tang; Bin Gao; Xinyi Li; Yue Xi; Wanrong Zhang; He Qian; Huaqiang Wu

doi:10.1088/1674-4926/42/6/064101

J. Semicond. > 2021, Volume 42 > Issue 6 > 064101

ARTICLES

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

Yujia Li^{1, 2}, Jianshi Tang^{2, 3,}, Bin Gao^{2, 3}, Xinyi Li², Yue Xi², Wanrong Zhang¹, He Qian^{2, 3} and Huaqiang Wu^{2, 3,}

+ Author Affiliations

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

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

DOI: 10.1088/1674-4926/42/6/064101

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

References

[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/NbO_x bilayer structures. Appl Phys Lett, 2015, 106, 212902 doi: 10.1063/1.4921745
[13]	Gao L G, Chen P Y, Yu S M. NbO_x 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 V_th and V_hold 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 V_in when R_L = 50 kΩ, C_L = 750 pF. (b) The oscillation frequency as a function of V_in. (c) Oscillation waveforms of the oscillation neuron with different R_L when V_in = 1.2 V, C_L = 750 pF. (d) The oscillation frequency as a function of R_L.

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 C_V. (b) The oscillation frequency distribution of different R_L when C_V = 7% (top panel) and C_V = 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/NbO_x bilayer structures. Appl Phys Lett, 2015, 106, 212902 doi: 10.1063/1.4921745
[13]	Gao L G, Chen P Y, Yu S M. NbO_x 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

GET CITATION

shu

Export: BibTex EndNote

Article Metrics

Article views: 4023 Times PDF downloads: 142 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

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.

Citation:

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.

Citation:

PDF( 1902 KB)

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

DOI: 10.1088/1674-4926/42/6/064101

Yujia Li^1,2,
Jianshi Tang^2,3,,
Bin Gao^2,3,
Xinyi Li²,
Yue Xi²,
Wanrong Zhang¹,
He Qian^2,3,
Huaqiang Wu^2,3,

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

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

Abstract

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.
- threshold switching,
- Ag nanodots,
- oscillation neuron,
- neuromorphic computing

FullText(HTML)

References(25)

References

[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/NbO_x bilayer structures. Appl Phys Lett, 2015, 106, 212902 doi: 10.1063/1.4921745
[13]	Gao L G, Chen P Y, Yu S M. NbO_x 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

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

References

Search

GET CITATION

Share:

Article Metrics

History

Catalog

Email This Article

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

DOI: 10.1088/1674-4926/42/6/064101

Abstract

References

Proportional views

Catalog

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

References

Search

GET CITATION

Share:

Article Metrics

History

Catalog

Email This Article

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

DOI: 10.1088/1674-4926/42/6/064101

Abstract

References

Proportional views

Catalog

Export File

Citation

Format

Content