Unsupervised character recognition with graphene memristive synapses
Authors: 
Ben Walters, Corey Lammie, Shuangming Yang, Mohan V Jacob, Mostafa Rahimi AzghadiAuthors Info & Claims
Ben Walters, Corey Lammie, Shuangming Yang, Mohan V Jacob, Mostafa Rahimi AzghadiAuthors Info & ClaimsPages 1569 - 1584
Abstract
Memristive devices being applied in neuromorphic computing are envisioned to significantly improve the power consumption and speed of future computing platforms. The materials used to fabricate such devices will play a significant role in their viability. Graphene is a promising material, with superb electrical properties and the ability to be produced in large volumes. In this paper, we demonstrate that a graphene-based memristive device could potentially be used as synapses within spiking neural networks (SNNs) to realise spike timing-dependant plasticity for unsupervised learning in an efficient manner. Specifically, we verify the operation of two SNN architectures tasked for single-digit (0–9) classification: (i) a single layer network, where inputs are presented in pixel resolution, and (ii) a larger network capable of classifying the dataset. Our work presents the first investigation and large-scale simulation of the use of graphene memristive devices to perform a complex pattern classification task. In favour of reproducible research, we will make our code and data publicly available. This can pave the way for future research in using graphene devices with memristive capabilities in neuromorphic computing architectures.
References
[1]
Chua L Memristor—the missing circuit element IEEE Trans Circuit Theory 1971 18 5 507-519
[2]
Maranhão G and Guimarães JG Low-power hybrid memristor-CMOS spiking neuromorphic STDP learning system IET Circuits Devices Syst 2021 15 3 237-250
[3]
Rahimi Azghadi M, Chen YC, Eshraghian JK, Chen J, Lin CY, Amirsoleimani A, et al. Complementary metal-oxide semiconductor and memristive hardware for neuromorphic computing Adv Intell Syst 2020 2 5 1900189
[4]
Strukov DB, Snider GS, Stewart DR, and Williams RS The missing memristor found Nature 2008 453 7191 80-83
[5]
Sun K, Chen J, and Yan X The future of memristors: materials engineering and neural networks Adv Funct Mater 2021 31 8 2006773
[6]
Ambrogio S, Ciocchini N, Laudato M, Milo V, Pirovano A, Fantini P, et al. Unsupervised learning by spike timing dependent plasticity in phase change memory (PCM) synapses Front Neurosci 2016 10 56
[7]
Velev JP, Duan CG, Burton JD, Smogunov A, Niranjan MK, Tosatti E, et al. Magnetic tunnel junctions with ferroelectric barriers: prediction of four resistance states from first principles Nano Lett 2009 9 1 427-432
[8]
Garcia V, Fusil S, Bouzehouane K, Enouz-Vedrenne S, Mathur ND, Barthélémy A, et al. Giant tunnel electroresistance for non-destructive readout of ferroelectric states Nature 2009 460 7251 81-84
[9]
Solanki A, Guerrero A, Zhang Q, Bisquert J, and Sum TC Interfacial mechanism for efficient resistive switching in ruddlesden-popper perovskites for non-volatile memories J Phys Chem Lett 2020 11 2 463-470
[10]
Ahn M, Park Y, Lee SH, Chae S, Lee J, Heron JT, et al. Memristors based on (Zr, Hf, Nb, Ta, Mo, W) high-entropy oxides Adv Electronic Mater 2021 7 5 2001258
[11]
Zhang C, Zhou H, Chen S, Zhang G, Yu ZG, Chi D et al (2021) Recent progress on 2D materials-based artificial synapses. Critical Reviews in Solid State and Materials Sciences. 1–26.
[12]
Kwon KC, Baek JH, Hong K, Kim SY, and Jang HW Memristive devices based on two-dimensional transition metal chalcogenides for neuromorphic computing Nano Micro Lett 2022 14 1 58
[13]
Zhou Z, Yang F, Wang S, Wang L, Wang X, Wang C, et al. Emerging of two-dimensional materials in novel memristor Front Phys 2021 17 2 23204
[14]
Jacob MV, Rawat RS, Ouyang B, Bazaka K, Kumar DS, Taguchi D et al (2015) Catalyst-free plasma enhanced growth of graphene from sustainable sources. Nano Lett 15(9):5702–5708. 26263025.
[15]
Burr GW A role for analogue memory in AI hardware Nat Mach Intell 2019 1 1 10-11
[16]
Wang J and Zhuge F Memristive synapses for brain-inspired computing Adv Mater Technol 2019 4 3 1800544
[17]
Xiao Z, Yan B, Zhang T, Huang R, Yang Y (2022) Memristive devices based hardware for unlabeled data processing. Neuromorphic Comput Eng 2(2):022003.
[18]
Huang M, Li Z, and Zhu H Recent advances of graphene and related materials in artificial intelligence Adv Intell Syst 2022 4 10 2200077
[19]
Li R, Huang P, Feng Y, Zhou Z, Zhang Y, Ding X, et al. Hardware demonstration of srdp neuromorphic computing with online unsupervised learning based on memristor synapses Micromachines 2022 13 3 433
[20]
Xiang Y, Huang P, Zhao Y, Zhao M, Gao B, Wu H, et al. Impacts of state instability and retention failure of filamentary analog rram on the performance of deep neural network IEEE Trans Electron Dev 2019 66 11 4517-4522
[21]
Vaila R, Chiasson J, and Saxena V A deep unsupervised feature learning spiking neural network with binarized classification layers for the emnist classification IEEE Trans Emerg Top Comput Intell 2020 6 1 124-135
[22]
Chellappa R, Theodoridis S, and van Schaik A Advances in machine learning and deep neural networks Proc IEEE 2021 109 5 607-611
[23]
Zhang W and Li P Information-theoretic intrinsic plasticity for online unsupervised learning in spiking neural networks Front Neurosci 2019 13 31
[24]
Zambrano D, Nusselder R, Scholte HS, and Bohté SM Sparse computation in adaptive spiking neural networks Front Neurosci 2019 12 987
[25]
Zenke F and Ganguli S SuperSpike: supervised learning in multilayer spiking neural networks Neural Comput 2017 05 30
[26]
Neftci EO, Mostafa H, and Zenke F Surrogate gradient learning in spiking neural networks: bringing the power of gradient-based optimization to spiking neural networks IEEE Signal Process Mag 2019 36 6 51-63
[27]
Eshraghian JK, Ward M, Neftci E, Wang X, Lenz G, Dwivedi G, et al. (2021) Training spiking neural networks using lessons from deep learning. arXiv preprint arXiv:2109.12894
[28]
Azghadi MR, Linares-Barranco B, Abbott D, and Leong PH A hybrid CMOS-memristor neuromorphic synapse IEEE Trans Biomed Circuits Syst 2017 11 2 434-445
[29]
Rahimi Azghadi M, Al-Sarawi S, Abbott D, Iannella N (2013) A neuromorphic VLSI design for spike timing and rate based synaptic plasticity. Neural Netw 45:70–82. Neuromorphic Engineering: From Neural Systems to Brain-Like Engineered Systems.
[30]
Gq Bi, Mm Poo (1998) Synaptic modifications in cultured hippocampal neurons: dependence on spike timing, synaptic strength, and postsynaptic cell type. J Neurosci 18(24):10464–10472. www.jneurosci.org/content/18/24/10464.full.pdf
[31]
Diehl P and Cook M Unsupervised learning of digit recognition using spike-timing-dependent plasticity Front Comput Neurosci 2015 9 99
[32]
Brivio S, Ly DRB, Vianello E, and Spiga S Non-linear memristive synaptic dynamics for efficient unsupervised learning in spiking neural networks Front Neurosci 2021 15 27
[33]
Querlioz D, Bichler O, Dollfus P, and Gamrat C Immunity to device variations in a spiking neural network with memristive nanodevices IEEE Trans Nanotechnol 2013 05 12 288-295
[34]
Kim S, Yoon J, Kim HD, and Choi SJ Carbon nanotube synaptic transistor network for pattern recognition ACS Appl Mater Interfaces 2015 7 45 25479-25486
[35]
Hansen M, Zahari F, Ziegler M, and Kohlstedt H Double-barrier memristive devices for unsupervised learning and pattern recognition Front Neurosci 2017 11 91
[36]
Guo Y, Wu H, Gao B, and Qian H Unsupervised learning on resistive memory array based spiking neural networks Front Neurosci 2019 13 812
[37]
Nandakumar SR, Rajendran B (2020) Bio-mimetic synaptic plasticity and learning in a sub-500mV Cu/SiO2/W memristor. Microelectronic Eng, 226.
[38]
Boybat I, Le Gallo M, Nandakumar SR, Moraitis T, Parnell T, Tuma T, et al. Neuromorphic computing with multi-memristive synapses Nat Commun 2018 9 1 2514
[39]
Bill J, Legenstein R (2014) A compound memristive synapse model for statistical learning through STDP in spiking neural networks. Front Neurosci, 8.
[40]
Covi E, Brivio S, Serb A, Prodromakis T, Fanciulli M, and Spiga S Analog memristive synapse in spiking networks implementing unsupervised learning Front Neurosci 2016 10 482
[41]
Qu L, Zhao Z, Wang L, and Wang Y Efficient and hardware-friendly methods to implement competitive learning for spiking neural networks Neural Comput Appl 2020 32 17 13479-13490
[42]
Demin VA, Nekhaev DV, Surazhevsky IA, Nikiruy KE, Emelyanov AV, Nikolaev SN, et al. Necessary conditions for STDP-based pattern recognition learning in a memristive spiking neural network Neural Netw 2021 134 64-75
[43]
Hajiabadi Z and Shalchian M Memristor-based synaptic plasticity and unsupervised learning of spiking neural networks J Comput Electronics 2021 20 4 1625-1636
[44]
Kopelevich Y, Bud’ko S, Cooper DR, D’Anjou B, Ghattamaneni N, Harack B, et al. Experimental review of graphene ISRN Condensed Matter Phys 2012 2012
[45]
Akinwande D, Brennan CJ, Bunch JS, Egberts P, Felts JR, Gao H, et al. A review on mechanics and mechanical properties of 2D materials-Graphene and beyond Extreme Mech Lett 2017 13 42-77
[46]
Chen Y, Zhou Y, Zhuge F, Tian B, Yan M, Li Y, et al (2019) Graphene-ferroelectric transistors as complementary synapses for supervised learning in spiking neural network. 2D Mater Appl 3(1):31.
[47]
Schranghamer TF, Oberoi A, and Das S Graphene memristive synapses for high precision neuromorphic computing Nat Commun 2020 11 1 5474
[48]
Sun Y, Lin Y, Zubair A, Xie D, Palacios T (2021) WSe2/graphene heterojunction synaptic phototransistor with both electrically and optically tunable plasticity. 2D Mater 8(3):035034.
[49]
Abunahla H, Halawani Y, Alazzam A, and Mohammad B NeuroMem: analog graphene-based resistive memory for artificial neural networks Sci Rep 2020 10 1 9473
[50]
Qi M, Cao S, Yang L, You Q, Shi L, and Wu Z Uniform multilevel switching of graphene oxide-based RRAM achieved by embedding with gold nanoparticles for image pattern recognition Appl Phys Lett 2020 116 16
[51]
Romero FJ, Toral A, Medina-Rull A, Moraila-Martinez CL, Morales DP, Ohata A, et al. Resistive switching in graphene oxide Front Mater 2020 7 17
[52]
Porro S, Accornero E, Pirri CF, and Ricciardi C Memristive devices based on graphene oxide Carbon 2015 85 383-396
[53]
Liu B, Liu Z, Chiu IS, Di M, Wu Y, Wang JC, et al. Programmable synaptic metaplasticity and below femtojoule spiking energy realized in graphene-based neuromorphic memristor ACS Appl Mater Interfaces 2018 10 24 20237-20243
[54]
Krishnaprasad A, Choudhary N, Das S, Dev D, Kalita H, Chung HS, et al. Electronic synapses with near-linear weight update using MoS2/graphene memristors Appl Phys Lett 2019 115 10
[55]
Feng X, Liu X, Ang KW (2020) 2D photonic memristor beyond graphene: progress and prospects. Nanophotonics.
[56]
Cao G, Meng P, Chen J, Liu H, Bian R, Zhu C, et al. 2D material based synaptic devices for neuromorphic computing Adv Funct Mater 2021 31 4 2005443
[57]
Yalagala B, Khandelwal S, J D, Badhulika S (2019) Wirelessly destructible MgO-PVP-Graphene composite based flexible transient memristor for security applications. Mater Sci Semiconductor Process 104:104673.
[58]
Bi G and Poo M Synaptic modification by correlated activity: Hebb’s postulate revisited Annu Rev Neurosci 2001 24 139-66
[59]
Sahu DP, Jetty P, Jammalamadaka SN (2021) Graphene oxide based synaptic memristor device for neuromorphic computing. Nanotechnology 32(15):155701.
[60]
Wang H, Laurenciu NC, Jiang Y, and Cotofana SD Compact graphene-based spiking neural network with unsupervised learning capabilities IEEE Open J Nanotechnol 2020 1 135-144
[61]
Wang H, Laurenciu NC, Jiang Y, Cotofana S (2021) Graphene-based artificial synapses with tunable plasticity. J Emerg Technol Comput Syst 17(4).
[62]
Wang Z, Liu C, Deng Y, Huang Z, He S, Guo D (2020) Carbon-based spiking neural network implemented with single-electron transistor and memristor for visual perception. In: 2020 IEEE 14th international conference on anti-counterfeiting, security, and identification (ASID), pp 143–146
[63]
Wang H, Cucu Laurenciu N, Cotofana S (2021) A reconfigurable graphene-based spiking neural network architecture. IEEE Open J Nanotechnol, p 1.
[64]
Hajri B, Aziza H, Mansour MM, and Chehab A RRAM device models: a comparative analysis with experimental validation IEEE Access 2019 7 168963-168980
[65]
Pershin Y and Di Ventra M SPICE model of memristive devices with threshold Radioengineering 2012 04 22
[66]
Kvatinsky S, Ramadan M, Friedman EG, and Kolodny A VTEAM: a general model for voltage-controlled memristors IEEE Trans Circuits Syst II Exp Briefs 2015 62 8 786-790
[67]
Messaris I, Serb A, Stathopoulos S, Khiat A, Nikolaidis S, and Prodromakis T A data-driven verilog-A ReRAM model IEEE Trans Comput Aided Design Integrated Circuits Syst 2018 37 12 3151-3162
[68]
Jacob MV, Taguchi D, Iwamoto M, Bazaka K, and Rawat RS Resistive switching in graphene-organic device: charge transport properties of graphene-organic device through electric field induced optical second harmonic generation and charge modulation spectroscopy [Journal Article] Carbon 2017 112 111-116
[69]
Rahimi Azghadi M, Moradi S, Fasnacht D, Ozdas M, Indiveri G (2015) Programmable spike-timing-dependent plasticity learning circuits in neuromorphic VLSI architectures. ACM J Emerg Technol Comput Syst 12(2).
[70]
Izhikevich EM Simple model of spiking neurons IEEE Trans Neural Netw 2003 14 6 1569-1572
[71]
Hodgkin AL and Huxley AF A quantitative description of membrane current and its application to conduction and excitation in nerve Bull Math Biol 1990 52 1 25-71
[72]
Lapique L Recherches quantitatives sur l’excitation electrique des nerfs traitee comme une polarization J Physiol Pathol 1907 9 620-635
[73]
Zamarreno-Ramos C, Camunas-Mesa LA, Perez-Carrasco JA, Masquelier T, Serrano-Gotarredona T, and Linares-Barranco B On spike-timing-dependent-plasticity, memristive devices, and building a self-learning visual cortex Front Neurosci 2011 5 26
[74]
Lammie C, Hamilton T, Azghadi MR (2018 ) Unsupervised character recognition with a simplified FPGA neuromorphic system. IEEE Explore, pp 1–5.
[75]
Song S, Miller KD, and Abbott LF Competitive Hebbian learning through spike-timing-dependent synaptic plasticity Nat Neurosci 2000 3 9 919-926
[76]
Shi X, Zeng Z, Yang L, and Huang Y Memristor-based circuit design for neuron with homeostatic plasticity IEEE Trans Emer Top Comput Intell 2018 2 5 359-370
[77]
Lazar A, Pipa G, Triesch J (2007) Fading memory and time series prediction in recurrent networks with different forms of plasticity. Neural Netw 20(3):312–322. Echo State Networks and Liquid State Machines.
[78]
Mihalas S, Niebur E (2009) A generalized linear integrate-and-fire neural model produces diverse spiking behaviors. Neural Comput 21(3):704–718. 18928368.
[79]
Akiba T, Sano S, Yanase T, Ohta T, Koyama M (2019) Optuna: a next-generation hyperparameter optimization framework. In: Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery; data mining. KDD ’19. New York, NY, USA: Association for Computing Machinery, pp 2623–2631. Available from:
[80]
Naous R, Al-Shedivat M, and Salama KN Stochasticity modeling in memristors IEEE Trans Nanotechnol 2016 15 1 15-28
[81]
Payvand M, Nair MV, Müller LK, and Indiveri G A neuromorphic systems approach to in-memory computing with non-ideal memristive devices: from mitigation to exploitation Faraday Discussions 2019 213 487-510
[82]
Rieck JL, Hensling FV, and Dittmann R Trade-off between variability and retention of memristive epitaxial SrTiO3 devices APL Mater 2021 9 2
[83]
Ford AJ, Jha R (2020) Memristive device variability performance impact on neuromorphic machine learning hardware. In: (2020) 11th International green and sustainable computing workshops (IGSC). IEEE, pp 1–7
Index Terms
- Unsupervised character recognition with graphene memristive synapses
Index terms have been assigned to the content through auto-classification.
Recommendations
Electron Beam Induced Deposition on graphene on silicon oxide and hexagonal boron nitride: A comparison of substrates
Graphene, a monolayer of carbon atoms arranged in a hexagonal lattice, is an interesting material because of its unique electronic properties. Electron Beam Induced Deposition (EBID) is an attractive direct-write technique to fabricate graphene devices ...
Graphene-Based Artificial Synapses with Tunable Plasticity
Design and implementation of artificial neuromorphic systems able to provide brain akin computation and/or bio-compatible interfacing ability are crucial for understanding the human brain’s complex functionality and unleashing brain-inspired computation’s ...
Fabrication of graphene and graphite thin films from organic coating
Monolayer graphene and graphite thin films were fabricated on SiO"2/Si substrates by organic coating and post annealing. Pure nickel (Ni) was deposited on the substrate surface as the catalyst. Then the samples were dipped in the Orange II organic ...
Comments
Information & Contributors
Information
Published In
© The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 11 November 2023
Accepted: 16 October 2023
Received: 20 July 2022
Author Tags
Qualifiers
- Research-article
Funding Sources
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 16 Jan 2025