access icon free Spintronic memristor synapse and its RWC learning algorithm

© The Institution of Engineering and Technology
Received 04/10/2017, Accepted 19/12/2017, Revised 06/12/2017, Published 05/01/2018

As one of the most widely used memristor models, the spintronic memristor has become a promising candidate for the electronic synapse. Non-volatility, nanoscale geometries, binary data and multi-level information storage make the circuit simpler and consume less electricity. In this study, a new spintronic memristor synaptic circuit is proposed which can realise positive, zero and negative weights successfully. Furthermore, the circuits of the presented synaptic-based neuron and compact neural network are designed and an improved random weight change (RWC) algorithm is proposed. Compared with the traditional RWC algorithm, it has faster training speed and less training error. In addition, the neural network is applied to data prediction, the result of which is closer to real data. Finally, the correctness and effectiveness of the proposed network are verified via a series of computer simulations.

Inspec keywords: memristor circuits; magnetoelectronics; neural chips; learning (artificial intelligence)

Other keywords: compact neural network; RWC learning algorithm; nanoscale geometries; synaptic-based neuron; data prediction; electronic synapse; traditional RWC algorithm; zero weights; improved random weight change algorithm; synaptic-based neuron network; multilevel information storage; binary data; positive weights; computer simulations; spintronic memristor synaptic circuit; negative weights

Subjects: Neural nets (circuit implementations); Neural net devices; Magneto-acoustic, magnetoresistive, magnetostrictive and magnetostatic wave devices

References

    1. 1)
      • 26. Hameed, A.A., Karlik, B., Salman, M.S.: ‘Back-propagation algorithm with variable adaptive momentum’, Knowl.-Based Syst., 2016, 114, pp. 79–87.
    2. 2)
      • 29. Cantley, K.D., Subramaniam, A., Stiegler, H., et al: ‘Hebbian learning in spiking neural networks with nano-crystalline silicon TFTs and memristive synapses’, IEEE Trans. Nano-technol., 2011, 10, (5), pp. 1066–1073.
    3. 3)
      • 5. Li, T., Duan, S., Liu, J., et al: ‘A spintronic memristor-based neural network with radial basis function for robotic manipulator control implementation’, IEEE Trans. Syst. Man Cybern. Syst., 2016, 46, (4), pp. 582–588.
    4. 4)
      • 7. Mazumder, P., Kang, S.M., Waser, R.: ‘Memristors: devices, models, and applications’, Proc. IEEE, 2012, 100, (6), pp. 1911–1919.
    5. 5)
      • 11. Wang, H., Duan, S., Huang, T., et al: ‘Exponential stability of complex-valued memristive recurrent neural networks’, IEEE Trans. Neural Netw. Learn. Syst., 2017, 28, (3), pp. 766–771.
    6. 6)
      • 15. Wang, L., Wang, X., Duan, S., et al: ‘A spintronic memristor bridge synapse circuit and the application in memrisitive cellular automata’, Neurocomputing, 2015, 167, pp. 346–351.
    7. 7)
      • 8. Volos, C.K., Kyprianidis, I.M., Stouboulos, I.N.: ‘The memristor as an electric synapse-synchronization phenomena’. 2011 17th Int. Conf. on Digital Signal Processing (DSP), Corfu, Greece, July 2011, pp. 1–6.
    8. 8)
      • 21. Querlioz, D., Bichler, O., Gamrat, C.: ‘Simulation of a memristor-based spiking neural network immune to device variations’. The 2011 Int. Joint Conf. on Neural Networks, San Jose, USA, August 2011, pp. 1775–1781.
    9. 9)
      • 13. Kim, H., Sah, M.P., Yang, C., et al: ‘Neural synaptic weighting with a pulse-based memristor circuit’, IEEE Trans. Circuits Syst., 2012, 59, (1), pp. 148–158.
    10. 10)
      • 2. Strukov, D.B., Snider, G.S., Stewart, D.R., et al: ‘The missing memristor found’, Nature, 2008, 453, (7191), pp. 80–83.
    11. 11)
      • 1. Chua, L.: ‘Memristor-the missing circuit element’, IEEE Trans. Circuit Theory, 1971, 18, (5), pp. 507–519.
    12. 12)
      • 23. Hirotsu, K., Brooke, M.A.: ‘An analog neural network chip with random weight change learning algorithm’. Proc. of 1993 Int. Conf. on Neural Networks, Nagoya, Japan, October 1993, pp. 3031–3034.
    13. 13)
      • 4. Hu, M., Li, H., Chen, Y., et al: ‘Geometry variations analysis of TiO2 thin-film and spintronic memristors’. Proc. Int. Conf. on Design Automation, Chiba, Japan, January 2011, pp. 25–30.
    14. 14)
      • 25. Liu, J., Brooke, M.A.: ‘Fully parallel on-chip learning hardware neural network for real-time control’. ISCAS'99. Prof. of the 1999 IEEE Int. Symp. on Circuits and Systems VLSI (Cat. No. 99CH36349), Orlando, USA, May 1999, vol. 5, pp. 371–374.
    15. 15)
      • 22. Adhikari, S.P., Kim, H., Budhathoki, R.K., et al: ‘A circuit-based learning architecture for multilayer neural networks with memristor bridge synapses’, IEEE Trans. Circuits Syst., 2015, 62, (1), pp. 215–223.
    16. 16)
      • 17. Sah, M.P., Yang, C., Kim, H., et al: ‘Memristor bridge circuit for neural synaptic weighting’. 2012 13th Int. Workshop on Cellular Nanoscale Networks and their Applications, Turin, Italy, August 2012, pp. 29–31.
    17. 17)
      • 27. Burton, B., Kamran, F., Harley, R.G., et al: ‘Identification and control of induction motor stator currents using fast on-line random training of a neural network’, IEEE Trans. Ind. Appl., 1997, 33, (3), pp. 697–704.
    18. 18)
      • 9. Wang, X., Chen, Y.: ‘Spintronic memristor devices and application’. Proc. Int. Conf. on Design and Automation Association, Europe, March 2010, pp. 667–672.
    19. 19)
      • 10. Ascoli, A., Corinto, F., Gilli, M., et al: ‘Memristor for neuromorphic applications: models and circuit implementations’, in Tetzlaff, R. (ED.): ‘Memristors and memristive systems’ (Springer, New York, 2014), pp. 379–403.
    20. 20)
      • 20. Tetzlaff, R., Schmidt, T.: ‘Memristors and memristive circuits-an overview’. 2012 IEEE Int. Symp. on Circuits and Systems, Seoul, South Korea, May 2012, pp. 1590–1595.
    21. 21)
      • 3. Wang, X., Chen, Y., Xi, H., et al: ‘Spintronic memristor through spin-torque-induced magnetization motion’, IEEE Electron Device Lett.., 2009, 30, (3), pp. 294–297.
    22. 22)
      • 24. Yang, C., Kim, H., Adhikari, S.P., et al: ‘A circuit-based neural network with hybrid learning of backpropagation and random weight change algorithms’, Sensors, 2016, 17, (1), pp. 1–18, doi:10.3390/s17010016.
    23. 23)
      • 12. Kim, H., Sah, M.P., Yang, C., et al: ‘Memristor bridge synapses’, Proc. IEEE, 2012, 100, (6), pp. 2061–2070.
    24. 24)
      • 14. Adhikari, S.P., Yang, C., Kim, H., et al: ‘Memristor bridge synapse-based neural network and its learning’, IEEE Trans. Neural Netw. Learn Syst., 2012, 23, (9), pp. 1426–1435.
    25. 25)
      • 6. Duan, S., Wang, H., Wang, L., et al: ‘Impulsive effects and stability analysis on memristive neural networks with variable delays’, IEEE Trans. Neural Netw. Learn Syst., 2017, 28, (2), pp. 476–481.
    26. 26)
      • 19. Thomas, A.: ‘Memristor-based neural networks’, J. Phys. D, Appl. Phys., 2013, 46, (9), p. 093001.
    27. 27)
      • 16. Luo, L., Hu, X., Duan, S., et al: ‘Multiple memristor series–parallel connections with use in synaptic circuit design’, IET Circuits Devices Syst., 2016, 11, (2), pp. 123–134, doi:10.1049/iet-cds.2015.0357.
    28. 28)
      • 28. Liu, J., Brooke, M., Hirotsu, K.: ‘A CMOS feedforward neural-network chip with on-chip parallel learning for oscillation cancellation’, IEEE Trans. Neural Netw., 2002, 13, (5), pp. 1178–1186.
    29. 29)
      • 18. Duan, S., Hu, X., Dong, Z., et al: ‘Memristor-based cellular nonlinear/neural network: design, analysis, and applications’, IEEE Trans. Neural Netw. Learn. Syst., 2015, 26, (6), pp. 1202–1213.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cds.2017.0427
Loading

Related content

content/journals/10.1049/iet-cds.2017.0427
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading