Neural Computing and Applications

, Volume 30, Issue 2, pp 503–508 | Cite as

Design of memristor-based image convolution calculation in convolutional neural network

  • Xiaofen Zeng
  • Shiping WenEmail author
  • Zhigang Zeng
  • Tingwen Huang
Original Article


In this paper, an architecture based on memristors is proposed to implement image convolution computation in convolutional neural networks. This architecture could extract different features of input images when using different convolutional kernels. Bipolar memristors with threshold are employed in this work, which vary their conductance values under different voltages. Various kernels are needed to extract information of input images, while different kernels contain different weights. The memristances of bipolar memristors with threshold are convenient to be varied and kept, which make them suitable to act as the weights of kernels. The performances of the design are verified by simulation results.


Memristor Convolutional neural network Image convolution computation 


  1. 1.
    Chua LO (1971) Memristor-the missing circuit element. IEEE Trans Circuit Theory 18(5):507–519CrossRefGoogle Scholar
  2. 2.
    Strukov DB, Snider GS, Stewartand DR, Williams RS (2008) The missing memristor found. Nature 534(7194):80–83CrossRefGoogle Scholar
  3. 3.
    Adhikari SP, Kim H, Budhathoki R (2015) A circuit-based learning architecture for multilayer neural networks with memristor bridge synapses. IEEE Trans Circuits Syst I 62(1):215–223CrossRefGoogle Scholar
  4. 4.
    Ebong IE, Mazumder P (2012) CMOS and memristor-based neural network design for position detection. Proc IEEE 100(6):2050–2060CrossRefGoogle Scholar
  5. 5.
    Liu XY, Zeng ZG, Wen SP (2016) Implementation of memristive neural network with full-function Pavlov associative memory. IEEE Trans Circuits Syst I Regul Pap 63(9):1454–1463MathSciNetCrossRefGoogle Scholar
  6. 6.
    Li B, Chen L, Li CD, Huang TW, He X, Li H, Chen YR (2014) STDP learning rule Based on memristor with STDP property. In: Proceedings of the international joint conference on neural networksGoogle Scholar
  7. 7.
    Shi L, Pei J, Deng N, Wang D, Deng L (2015) Development of a neuromorphic computing system. In: Proceedings of the IEDM,Google Scholar
  8. 8.
    Hu M, Strachan JP, Li Z, Grafals E, Davila N (2016) Dot-product engine for neuromorphic computing: programming 1T1M crossbar to accelerate matrix-vector multiplication. In: Proceedings of the 53rd annual design automation conferenceGoogle Scholar
  9. 9.
    Li B, Gu P, Shan Y, Wang Y, Chen YR, Yang HZ (2015) RRAM-based analog approximate computing. IEEE Trans Comput Aided Des Integr Circuits Syst 34(12):1905–1917CrossRefGoogle Scholar
  10. 10.
    Ho Y, Huang GM, Li P (2011) Dynamical properties and design analysis for nonvolatile memristor memories. IEEE Trans Circuits Syst I 58(4):724–736MathSciNetCrossRefGoogle Scholar
  11. 11.
    Knag P, Lu W, Zhang Z (2014) A native stochastic computing architecture enabled by memristors. IEEE Trans Nanotechnol 33(2):283–293CrossRefGoogle Scholar
  12. 12.
    Hamdioui S, Xie L, Nguyen H, Taoui M (2015) Memristor based computation-in-memory architecture for data-intensive applications. In: Proceedings of the conference on design, automation and test in EuropeGoogle Scholar
  13. 13.
    Li HH, Liu CC, Yan B, Yang CF, Song LH, Li Z, Chen YR (2015) Spiking-based matrix computation by leveraging memristor crossbar array. In: Proceedings of the IEEE symposium on computational intelligence for security and defense applications (CISDA)Google Scholar
  14. 14.
    Ahmad MS, Hyunsang H, Moongu J, Jeon M (2014) Neuromorphic character recognition system with two PCMO memristors as a synapse. IEEETrans Ind Electron 21(6):2933–2941Google Scholar
  15. 15.
    Nair MV, Dudek P (2015) Practical gradient-descent for memristive crossbars. In: Proceedings of the conference on memristive systems (MEMRISYS)Google Scholar
  16. 16.
    Alibart F, Zamanidoost E, Strukov DB (2013) Pattern classification by memristive crossbar circuits using ex situ and in situ training. Nat Commun 4(3):131–140Google Scholar
  17. 17.
    Abdel-Kader RF, Abuelenin SM (2015) Memristor model based on fuzzy window function. In: Proceedings of the fuzzy systems (FUZZ-IEEE)Google Scholar
  18. 18.
    Li B, Wang Y, Chen YR, Li HH, Yang HZ (2014) ICE: inline calibration for memristor crossbar-based computing engine. In: Proceedings of the conference on design, automation and test in Europe (DATE14)Google Scholar
  19. 19.
    Chen YR, Tian W, Li H, Wang XB, Zhu WZ (2010) PCMO device with high switching stability. IEEE Electron Device Lett 31(8):866–868CrossRefGoogle Scholar
  20. 20.
    Lucia VG, Arturo B, Luigi F, Fortuna L (2015) Memristor-based adaptive coupling for consensus and synchronization. IEEE Trans Circuits Syst I 62(4):1175–1184MathSciNetCrossRefGoogle Scholar
  21. 21.
    Wen SP, Zeng ZG, Chen MZQ, Huang TW (2016) Synchronization of switched neural networks with communication delays via the event-triggered method. IEEE Trans Neural Netw Learn Syst. doi: 10.1109/TNNLS.2016.2580609 Google Scholar
  22. 22.
    Wen GH, Yu WW, Li ZK, Yu XH, Cao JZ (2016) Neuro-adaptive consensus tracking of multiagent systems with a high-dimensional leader. IEEE Trans Cybern. doi: 10.1109/TCYB.2016.2556002
  23. 23.
    Lu JQ, Ho D, Cao J, Kurths J (2011) Exponential synchronization of linearly coupled neural networks with impulsive disturbances. IEEE Trans Neural Netw 22(2):329–336CrossRefGoogle Scholar
  24. 24.
    Wen SP, Zeng ZG, Huang TW, Meng QG, Yao W (2015) Lag synchronization of switched neural networks via neural activation function and applications in image encryption. IEEE Trans Neural Netw Learn Syst 26:1493–1502MathSciNetCrossRefGoogle Scholar
  25. 25.
    Liu D, Li H, Wang D (2013) Neural-network-based zero-sum game for discrete-time nonlinear systems via iterative adaptive dynamic programming algorithm. Neurocomputing 110:92–100CrossRefGoogle Scholar
  26. 26.
    Cheng L, Hou ZG, Tan M, Lin YZ, Zhang WJ (2013) Neural-network-based adaptive leader-following control for multiagent systems with uncertainties. Neurocomputing 110:92–100CrossRefGoogle Scholar
  27. 27.
    Lecun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324CrossRefGoogle Scholar
  28. 28.
    Lawrence S, Giles CL, Tsoi AC, Back AD (1997) Face recognition: a convolutional neural-network approach. IEEE Trans Neural Netw 8(1):98–113CrossRefGoogle Scholar
  29. 29.
    Mian ML, King HL (2015) Malaysia traffic sign recognition with convolutional neural network. In: Proceedings of the DSPGoogle Scholar
  30. 30.
    Wang JH, Lu JJ, Chen WH, Wu XM (2015) Convolutional neural network for 3D object recognition based on RGB-D dataset. In: Proceedings of the ICLRGoogle Scholar
  31. 31.
    Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification with deep convolutional neural networks. In: Proceedings of the NIPSGoogle Scholar
  32. 32.
    Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the CVPRGoogle Scholar
  33. 33.
    Yuriy VP, Dalibor B, Massimiliano DV (2013) Reliable SPICE simulations of memristors, memcapacitors and meminductors, p 2717. arXiv:1307
  34. 34.
    Addison J, Wermter S, MacIntyre J (1999) Effectiveness of feature extraction in neural network architectures for novelty detection. In: Ninth international conference on artificial neural networks (ICANN 99)Google Scholar

Copyright information

© The Natural Computing Applications Forum 2016

Authors and Affiliations

  • Xiaofen Zeng
    • 1
    • 2
  • Shiping Wen
    • 1
    • 2
    Email author
  • Zhigang Zeng
    • 1
    • 2
  • Tingwen Huang
    • 3
  1. 1.School of AutomationHuazhong University of Science and TechnologyWuhanPeople’s Republic of China
  2. 2.Key Laboratory of Image Processing and Intelligent Control of Education Ministry of ChinaWuhanPeople’s Republic of China
  3. 3.Texas A & M University at QatarDohaQatar

Personalised recommendations