nach oben

Neural Computing and Applications

Erschienen in:

07.08.2021 | Original Article

Memristor-based circuit implementation of Competitive Neural Network based on online unsupervised Hebbian learning rule for pattern recognition

verfasst von: Mian Li, Qinghui Hong, Xiaoping Wang

Erschienen in: Neural Computing and Applications | Ausgabe 1/2022

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config

KI-gestützte Suche

Aus

Abstract

In this paper, a Competitive Neural Network circuit based on voltage-controlled memristors is proposed, of which the synapse structure is one memristor (1M). The designed circuit consists of the forward calculation part and the weight updating part. The forward calculation part is designed according to the winner-take-all mechanism, in which the m-LIF model and PMOS transistors with switching characteristics are combined to achieve the lateral inhibition. The weight updating part is designed based on the Hebbian learning rule. By using the voltage controlled switches, only the synaptic memristors connected to the winner output neuron obtained from the forward calculation part are adjusted. The whole circuit does not require the participation of CPU, FPGA or other microcontrollers, providing the possibility to realize computing-in-memory and parallel computing. We perform simulation experiments of unsupervised online learning of 5*3 pixels patterns and 28*28 pixels patterns based on the designed circuit in PSPICE. The changing trend of the network weights during the training phase and the high recognition accuracy in the recognition phase verify the network can effectively learn and recognize different patterns.

Vorheriger Artikel A novel nature-inspired maximum power point tracking (MPPT) controller based on ACO-ANN algorithm for photovoltaic (PV) system fed arc welding machines

Nächster Artikel Thermal-based early breast cancer detection using inception V3, inception V4 and modified inception MV4

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 340 Zeitschriften

aus folgenden Fachgebieten:

Bauwesen + Immobilien
Business IT + Informatik
Finance + Banking
Management + Führung
Marketing + Vertrieb
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 390 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Maschinenbau + Werkstoffe

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

über 102.000 Bücher
über 537 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Finance + Banking
Management + Führung
Marketing + Vertrieb
Maschinenbau + Werkstoffe
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Schmidhuber J (2015) Deep learning in neural networks: an overview. Neural Netw 61:85CrossRef

Ji Y, Zhang H, Zhang Z, Liu M (2021) CNN-based encoder-decoder networks for salient object detection: A comprehensive review and recent advances. Inf Sci 546:835MathSciNetCrossRef

Poulos J, Valle R (2021) Character-based handwritten text transcription with attention networks. Neural Comput Appl 33(16):10563–10573CrossRef

Chen HY, Chen CC, Hwang WJ (2017) An efficient hardware circuit for spike sorting based on competitive learning networks. Sensors 17(10):2232. https://doi.org/10.3390/s17102232CrossRef

Hasan R, Taha TM (2017) Memristor crossbar based winner take all circuit design for self-organization. In: Proceedings of the neuromorphic computing symposium. ACM, pp 1–4. https://doi.org/10.1145/3183584.3183622

Wu LS, Jain L (2007) Size invariant shape recognition by modulated competitive neural circuit. Int J Inf Commun Technol 1(1):76. https://doi.org/10.1504/IJICT.2007.013319CrossRef

Chang CY, Lin SY, Jeng M (2005) Using a two-layer competitive hopfield neural network for semiconductor wafer defect detection. In: IEEE international conference on automation science and engineering. IEEE, pp 301–306. https://doi.org/10.1109/coase.2005.1506786

Gong S, Yang S, Guo Z, Huang T (2019) Global exponential synchronization of memristive competitive neural networks with time-varying delay via nonlinear control. Neural Process Lett 49(1):103. https://doi.org/10.1007/s11063-017-9777-1CrossRef

Merolla PA, Arthur JV, Alvarez-Icaza R et al (2014) A million spiking-neuron integrated circuit with a scalable communication network and interface. Science 345(6197):668. https://doi.org/10.1126/science.1254642CrossRef

10.

Eberhardt SP, Daud T, Kerns D, Brown TX, Thakoor A (1991) Competitive neural architecture for hardware solution to the assignment problem. Neural Netw 4(4):431. https://doi.org/10.1016/0893-6080(91)90039-8CrossRef

11.

Oniga S, Tisan A, Attila B, Lung C (2007) Hardware implementation of simple competitive artificial neural networks with neuron parallelism. In: Proceedings of regional conference on embedded and ambient systems, RCEAS, pp 27–32

12.

Asai T, Ohtani M, Yonezu H (1999) Analog integrated circuits for the Lotka–Volterra competitive neural networks. IEEE Trans Neural Networks 10(5):1222. https://doi.org/10.1109/72.788661CrossRef

13.

Fang Y, Cohen MA, Kincaid TG (2010) Dynamic analysis of a general class of winner-take-all competitive neural networks. IEEE Trans Neural Networks 21(5):771. https://doi.org/10.1109/TNN.2010.2041671CrossRef

14.

Hollis PW, Paulos JJ (1990) Artificial neural networks using MOS analog multipliers. IEEE J Solid-State Circuits 25(3):849. https://doi.org/10.1109/4.102684CrossRef

15.

Chua L (1971) Memristor-the missing circuit element. IEEE Trans Circuit Theory 18(5):507. https://doi.org/10.1109/TCT.1971.1083337CrossRef

16.

Strukov DB, Snider GS, Stewart DR, Williams RS (2008) The missing memristor found. Nature 453(7191):80. https://doi.org/10.1038/nature06932CrossRef

17.

Zhou Z, Yan X, Zhao J et al (2019) Synapse behavior characterization and physical mechanism of a TiN/SiO x/p-Si tunneling memristor device. J Mater Chem C 7(6):1561. https://doi.org/10.1039/C8TC04903CCrossRef

18.

Cantley KD, Subramaniam A, Stiegler HJ, Chapman RA, Vogel EM (2011) Hebbian learning in spiking neural networks with nanocrystalline silicon TFTs and memristive synapses. IEEE Trans Nanotechnol 10(5):1066. https://doi.org/10.1109/TNANO.2011.2105887CrossRef

19.

Ohno T, Hasegawa T, Tsuruoka T, Terabe K, Gimzewski JK, Aono M (2011) Short-term plasticity and long-term potentiation mimicked in single inorganic synapses. Nat Mater 10(8):591. https://doi.org/10.1038/nmat3054CrossRef

20.

Jo SH, Chang T, Ebong I, Bhadviya BB, Mazumder P, Lu W (2010) Nanoscale memristor device as synapse in neuromorphic systems. Nano Lett 10(4):1297. https://doi.org/10.1021/nl904092hCrossRef

21.

Zhao L, Hong Q, Wang X (2018) Novel designs of spiking neuron circuit and STDP learning circuit based on memristor. Neurocomputing 314:207. https://doi.org/10.1016/j.neucom.2018.06.062CrossRef

22.

Pedretti G, Milo V, Ambrogio S et al (2017) Memristive neural network for on-line learning and tracking with brain-inspired spike timing dependent plasticity. Sci Rep 7(1):1. https://doi.org/10.1038/s41598-017-05480-0CrossRef

23.

Hu S, Liu Y, Liu Z, Chen T, Wang J, Yu Q, Deng L, Yin Y, Hosaka S (2015) Associative memory realized by a reconfigurable memristive Hopfield neural network. Nat Commun 6(1):1. https://doi.org/10.1038/ncomms8522CrossRef

24.

Garbin D, Vianello E, Bichler O, Rafhay Q, Gamrat C, Ghibaudo G, DeSalvo B, Perniola L (2015) HfO 2-based OxRAM devices as synapses for convolutional neural networks. IEEE Trans Electron Devices 62(8):2494. https://doi.org/10.1109/TED.2015.2440102CrossRef

25.

Li C, Wang Z, Rao M, Belkin D, Song W, Jiang H, Yan P, Li Y, Lin P, Hu M et al (2019) Long short-term memory networks in memristor crossbar arrays. Nat Mach Intell 1(1):49. https://doi.org/10.1038/s42256-018-0001-4CrossRef

26.

Prezioso M, Mahmoodi M, Bayat FM, Nili H, Kim H, Vincent A, Strukov D (2018) Spike-timing-dependent plasticity learning of coincidence detection with passively integrated memristive circuits. Nat Commun 9(1):1. https://doi.org/10.1038/s41467-018-07757-yCrossRef

27.

Qu L, Zhao Z, Wang L, Wang Y (2020) Efficient and hardware-friendly methods to implement competitive learning for spiking neural networks. Neural Comput Appl 32:13479–13490. https://doi.org/10.1007/s00521-020-04755-4CrossRef

28.

Hong Q, Yan R, Wang C, Sun J (2020) Memristive circuit implementation of biological nonassociative learning mechanism and its applications. IEEE Trans Biomed Circuits Syst. https://doi.org/10.1109/TBCAS.2020.3018777CrossRef

29.

Yan X, Wang J, Zhao M, Li X, Wang H, Zhang L, Lu C, Ren D (2018) Artificial electronic synapse characteristics of a Ta/Ta₂O₅-x/Al₂O₃/InGaZnO₄ memristor device on flexible stainless steel substrate. Appl Phys Lett 113(1):013503. https://doi.org/10.1063/1.5027776CrossRef

30.

Hansen M, Zahari F, Kohlstedt H, Ziegler M (2018) Unsupervised Hebbian learning experimentally realized with analogue memristive crossbar arrays. Sci Rep 8(1):1. https://doi.org/10.1038/s41598-018-27033-9CrossRef

31.

Yu S, Gao B, Fang Z, Yu H, Kang J, Wong HSP (2013) Stochastic learning in oxide binary synaptic device for neuromorphic computing. Front Neurosci 7:186. https://doi.org/10.3389/fnins.2013.00186CrossRef

32.

Serb A, Bill J, Khiat A, Berdan R, Legenstein R, Prodromakis T (2016) Unsupervised learning in probabilistic neural networks with multi-state metal-oxide memristive synapses. Nat Commun 7(1):1. https://doi.org/10.1038/ncomms12611CrossRef

33.

Jiang Y, Huang P, Zhu D et al (2018) Design and hardware implementation of neuromorphic systems with RRAM synapses and threshold-controlled neurons for pattern recognition. IEEE Trans Circuits Syst I Regul Pap 65(9):2726. https://doi.org/10.1109/TCSI.2018.2812419CrossRef

34.

Biolek Z, Biolek D, Biolkova V (2009) SPICE model of memristor with nonlinear dopant drift. Radioengineering 18(2):210MATH

35.

Kvatinsky S, Friedman EG, Kolodny A, Weiser UC (2012) TEAM: threshold adaptive memristor model. IEEE Trans Circuits Syst I Regul Pap 60(1):211. https://doi.org/10.1109/TCSI.2012.2215714MathSciNetCrossRefMATH

36.

Zhang Y, Wang X, Li Y, Friedman EG (2016) Memristive model for synaptic circuits. IEEE Trans Circuits Syst II Express Briefs 64(7):767. https://doi.org/10.1109/TCSII.2016.2605069CrossRef

37.

Li Y, Zhong Y, Xu L, Zhang J, Xu X, Sun H, Miao X (2013) Ultrafast synaptic events in a chalcogenide memristor. Sci Rep 3:1619. https://doi.org/10.1038/srep01619CrossRef

38.

Li Y, Zhong Y, Zhang J, Xu L, Wang Q, Sun H, Tong H, Cheng X, Miao X (2014) Activity-dependent synaptic plasticity of a chalcogenide electronic synapse for neuromorphic systems. Sci Rep 4:4906. https://doi.org/10.1038/srep04906CrossRef

39.

Hebb DO (2005) The organization of behavior: a neuropsychological theory. Taylor and Francis, London

40.

Chu M, Kim B, Park S, Hwang H, Jeon M, Lee BH, Lee BG (2015) Neuromorphic hardware system for visual pattern recognition with memristor array and CMOS neuron. IEEE Trans Ind Electron 62(4):2410–2419. https://doi.org/10.1109/TIE.2014.2356439CrossRef

Titel: Memristor-based circuit implementation of Competitive Neural Network based on online unsupervised Hebbian learning rule for pattern recognition
verfasst von: Mian Li
Qinghui Hong
Xiaoping Wang
Publikationsdatum: 07.08.2021
Verlag: Springer London
Erschienen in: Neural Computing and Applications / Ausgabe 1/2022
Print ISSN: 0941-0643
Elektronische ISSN: 1433-3058
DOI: https://doi.org/10.1007/s00521-021-06361-4

Springer Professional

Abstract

Bitte loggen Sie sich ein, um Zugang zu Ihrer Lizenz zu erhalten.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft"

Springer Professional "Technik"

Springer Professional "Wirtschaft+Technik"

Weitere Artikel der Ausgabe 1/2022

Thermal-based early breast cancer detection using inception V3, inception V4 and modified inception MV4

Correction to: Fault detection in distillation column using NARX neural network

A review of artificial intelligence applied to path planning in UAV swarms

A state-of-the-art review on shading mitigation techniques in solar photovoltaics via meta-heuristic approach

A conjugate gradient algorithm based on double parameter scaled Broyden–Fletcher–Goldfarb–Shanno update for optimization problems and image restoration

Inverse optimal synchronization control of competitive neural networks with constant time delays

Premium Partner