忆阻器基神经形态计算器件与系统研究进展

doi:10.16257/j.cnki.1681-1070.2024.0017

摘要/Abstract

摘要： 忆阻器作为新原理器件，与现有互补金属氧化物半导体（CMOS）器件相比，具有结构简单、集成密度高、微缩性好、操作能耗低、易于三维集成等优点，是实现神经形态计算技术的理想存储器件之一。对近年来忆阻器基神经形态计算技术的研究进展进行综述，包括忆阻器基神经突触和神经元功能实现以及忆阻器基神经形态计算系统研究进展，并对当前忆阻器基神经形态计算技术仍然面临的挑战进行总结，对其前景做了展望。

关键词: 忆阻器, 神经形态计算, 突触, 神经元

Abstract: Memristor, as an emerging device with the advantages of simple structure, high integration density, excellent scaling property, low operating energy consumption, and easy three-dimensional integration property, compared with the existing complementary metal-oxide-semiconductor transistor (CMOS) devices, is one of the ideal memory devices for realizing neuromorphic computing technology. The research progress of memristor-based neuromorphic computing technology in recent years is reviewed. The main contents include the realization of memristor-based synapse and neuron functions, and the research of memristor-based neuromorphic computing system. The summary of the challenges faced by the memristor-based neuromorphic computing technology and the prospects are also given.

Key words: memristor, neuromorphic computing, synapse, neuron

中图分类号:

TN389

郭文斌,汪泽清,吴祖恒,蔺智挺. 忆阻器基神经形态计算器件与系统研究进展[J]. 电子与封装, 2024, 24(4): 040401 .

GUO Wenbin , WANG Zeqing, WU Zuheng , LIN Zhiting. Research Progress of Memristor-Based Neuromorphic Computing Devices and Systems[J]. Electronics & Packaging, 2024, 24(4): 040401 .

参考文献

[1] JUNG S, LEE H, MYUNG S, et al. A crossbar array of magnetoresistive memory devices for in-memory computing[J]. Nature, 2022, 601: 211-216.
[2] WANG D W, LIN C T, CHEN G K, et al. DIMC: 2219TOPS/W 2569F2/b digital in-memory computing macro in 28 nm based on approximate arithmetic hardware[C]// 2022 IEEE International Solid- State Circuits Conference (ISSCC), San Francisco, CA, USA, 2022, 65: 266-268.
[3] HU H W, WANG W C, CHEN C K, et al. A 512 Gb in-memory-computing 3D-NAND flash supporting similar-vector-matching operations on edge-AI devices[C]// 2022 IEEE International Solid- State Circuits Conference (ISSCC), San Francisco, CA, USA, 2022, 65: 138-140.
[4] SHI T, WANG R, WU Z H, et al. A review of resistive switching devices: performance improvement, characterization, and applications[J]. Small Structures, 2021, 2(4): 2000109.
[5] PAN F, GAO S, CHEN C, et al. Recent progress in resistive random access memories: materials, switching mechanisms, and performance[J]. Materials Science and Engineering R: Reports, 2014, 83(1): 1-59.
[6] KUNDALE S S, KAMBLE G U, PATIL P P, et al. Review of electrochemically synthesized resistive switching devices: memory storage, neuromorphic computing, and sensing applications[J]. Nanomaterials, 2023, 13(12): 1879.
[7] CHOI S, YANG J, WANG G. Emerging memristive artificial synapses and neurons for energy-efficient neuromorphic computing[J]. Advanced Materials, 2020, 32(51): e2004659.
[8] WANG Z R, WU H Q, BURR G W, et al. Resistive switching materials for information processing[J]. Nature Reviews Materials, 2020, 5(3): 173-195.
[9] WASER R, DITTMANN R, STAIKOV G, et al. Redox-based resistive switching memories-nanoionic mechanisms, prospects, and challenges[J]. Advanced Materials, 2009, 21(25/26): 2632-2663.
[10] JO S H, CHANG T, EBONG I, et al. Nanoscale memristor device as synapse in neuromorphic systems[J]. Nano Letters, 2010, 10(4): 1297-1301.
[11] MARTIN L W, RAPPE A M. Thin-film ferroelectric materials and their applications[J]. Nature Reviews Materials, 2017, 2(2): 16087.
[12] BERGER L. Emission of spin waves by a magnetic multilayer traversed by a current[J]. Physical Review B, Condensed Matter, 1996, 54(13): 9353-9358.
[13] SUN F Q, LU Q F, FENG S M, et al. Flexible artificial sensory systems based on neuromorphic devices[J]. ACS Nano, 2021, 15(3): 3875-3899.
[14] WAN Q Z, SHARBATI M T, ERICKSON J R, et al. Emerging artificial synaptic devices for neuromorphic computing[J]. Advanced Materials Technologies, 2019, 4(4): 1900037.
[15] CHEN H, LI H L, MA T, et al. Biological function simulation in neuromorphic devices: from synapse and neuron to behavior[J]. Science and Technology of Advanced Materials, 2023, 24(1): 2183712.
[16] SOKOLOV A, ALI M, LI H, et al. Partially oxidized MXene Ti3C2Tx sheets for memristor having synapse and threshold resistive switching characteristics[J]. Advanced Electronic Materials, 2021, 7(2): 2000866.
[17] WANG Z R, JOSHI S, SAVEL’EV S E, et al. Memristors with diffusive dynamics as synaptic emulators for neuromorphic computing[J]. Nature Materials, 2017, 16(1): 101-108.
[18] ILYAS N, LI D Y, LI C M, et al. Analog switching and artificial synaptic behavior of Ag/SiOx: Ag/TiOx/p++-Si memristor device[J]. Nanoscale Research Letters, 2020, 15(1): 30.
[19] LEE D H, PARK H, CHO W J. Implementation of highly stable memristive characteristics in an organic-inorganic hybrid resistive switching layer of chitosan-titanium oxide with microwave-assisted oxidation[J]. Molecules, 2023, 28(13): 5174.
[20] EBONG I E, MAZUMDER P. CMOS and memristor-based neural network design for position detection[J]. Proceedings of the IEEE, 2012, 100(6): 2050-2060.
[21] ISMAIL M, CHAND U, MAHATA C, et al. Demonstration of synaptic and resistive switching characteristics in W/TiO2/HfO2/TaN memristor crossbar array for bioinspired neuromorphic computing[J]. Journal of Materials Science & Technology, 2022, 96: 94-102.
[22] MADADI ASL M, RAMEZANI AKBARABADI S. Voltage-dependent plasticity of spin-polarized conductance in phenyl-based single-molecule magnetic tunnel junctions[J]. PLoS One, 2021, 16(9): e0257228.
[23] LI Y, ZHONG Y P, XU L, et al. Ultrafast synaptic events in a chalcogenide memristor[J]. Scientific Reports, 2013, 3: 1619.
[24] NANDAKUMAR S R, RAJENDRAN B. Bio-mimetic synaptic plasticity and learning in a sub-500 mV Cu/SiO2/W memristor[J]. Microelectronic Engineering, 2020, 226: 111290.
[25] YOON C, OH G, KIM S, et al. Implementation of threshold- and memory-switching memristors based on electrochemical metallization in an identical ferroelectric electrolyte[J]. NPG Asia Materials, 2023, 15: 33.
[26] DU C, MA W, CHANG T, et al. Biorealistic implementation of synaptic functions with oxide memristors through internal ionic dynamics[J]. Advanced Functional Materials, 2015, 25(27): 4290-4299.
[27] SANGMIN Y, WU Y T, YONGMO P, et al. Tuning resistive switching behavior by controlling internal ionic dynamics for biorealistic implementation of synaptic plasticity[J]. Advanced Electronic Materials, 2022, 8(8): 2101025.
[28] ABBAS H, ABBAS Y, HASSAN G, et al. The coexistence of threshold and memory switching characteristics of ALD HfO2 memristor synaptic arrays for energy-efficient neuromorphic computing[J]. Nanoscale, 2020, 12(26): 14120-14134.
[29] WANG Z Q, ZENG T, REN Y Y, et al. Toward a generalized Bienenstock-Cooper-Munro rule for spatiotemporal learning via triplet-STDP in memristive devices[J]. Nature Communications, 2020, 11: 1510.
[30] XIONG J, YANG R, SHAIBO J, et al. Bienenstock, Cooper, and Munro learning rules realized in second-order memristors with tunable forgetting rate[J]. Advanced Functional Materials, 2019, 29(9): 1807316.
[31] WU Q T, WANG H, LUO Q, et al. Full imitation of synaptic metaplasticity based on memristor devices[J]. Nanoscale, 2018, 10(13): 5875-5881.
[32] SANGWAN V K, LEE H S, BERGERON H, et al. Multi-terminal memtransistors from polycrystalline monolayer molybdenum disulfide[J]. Nature, 2018, 554: 500-504.
[33] TANG J S, YUAN F, SHEN X K, et al. Bridging biological and artificial neural networks with emerging neuromorphic devices: fundamentals, progress, and challenges[J]. Advanced Materials, 2019, 31(49): e1902761.
[34] FLETCHER A. Action potential: generation and propagation[J]. Anaesthesia & Intensive Care Medicine, 2011, 12(6): 258-262.
[35] ZHANG X M, WANG W, LIU Q, et al. An artificial neuron based on a threshold switching memristor[J]. IEEE Electron Device Letters, 2018, 39(2): 308-311.
[36] INDIVERI G, LINARES-BARRANCO B, HAMILTON T J, et al. Neuromorphic silicon neuron circuits[J]. Frontiers in Neuroscience, 2011, 5: 73.
[37] PICKETT M D, MEDEIROS-RIBEIRO G, WILLIAMS R S. A scalable neuristor built with Mott memristors[J]. Nature Materials, 2013, 12: 114-117.
[38] YI W, TSANG K K, LAM S K, et al. Biological plausibility and stochasticity in scalable VO2 active memristor neurons[J]. Nature Communications, 2018, 9: 4661.
[39] WANG T, WANG X X, WEN J, et al. A bio-inspired neuromorphic sensory system[J]. Advanced Intelligent Systems, 2022, 4(7): 2200047.
[40] ZHANG X M, WU Z H, LU J K, et al. Fully memristive SNNs with temporal coding for fast and low-power edge computing[C]// 2020 IEEE International Electron Devices Meeting (IEDM), San Francisco, CA, USA, 2020.
[41] YUAN R, TIW P J, CAI L, et al. A neuromorphic physiological signal processing system based on VO2 memristor for next-generation human-machine interface[J]. Nature Communications, 2023, 14: 3695.
[42] ZHANG X M, YANG J J, LIU Q, et al. Experimental demonstration of conversion-based SNNs with 1T1R Mott neurons for neuromorphic inference[C]// 2019 IEEE International Electron Devices Meeting (IEDM), San Francisco, CA, USA, 2019.
[43] LI X Y, TANG J S, ZHANG Q T, et al. Power-efficient neural network with artificial dendrites[J]. Nature Nanotechnology, 2020, 15: 776-782.

中国半导体行业协会封装分会会刊

中国电子学会电子制造与封装技术分会会刊