JSTS:Journal of Semiconductor Technology and Science

The Institute of Electronics and Information Engineers (대한전자공학회)
권호 표지
DOI QR코드

DOI QR Code

New Memristor-Based Crossbar Array Architecture with 50-% Area Reduction and 48-% Power Saving for Matrix-Vector Multiplication of Analog Neuromorphic Computing

  • Received : 2014.02.18
  • Accepted : 2014.05.08
  • Published : 2014.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we propose a new memristor-based crossbar array architecture, where a single memristor array and constant-term circuit are used to represent both plus-polarity and minus-polarity matrices. This is different from the previous crossbar array architecture which has two memristor arrays to represent plus-polarity and minus-polarity connection matrices, respectively. The proposed crossbar architecture is tested and verified to have the same performance with the previous crossbar architecture for applications of character recognition. For areal density, however, the proposed crossbar architecture is twice better than the previous architecture, because only single memristor array is used instead of two crossbar arrays. Moreover, the power consumption of the proposed architecture can be smaller by 48% than the previous one because the number of memristors in the proposed crossbar architecture is reduced to half compared to the previous crossbar architecture. From the high areal density and high energy efficiency, we can know that this newly proposed crossbar array architecture is very suitable to various applications of analog neuromorphic computing that demand high areal density and low energy consumption.

Keywords

References

  1. C. Mead, "Neuromorphic electronic systems," Proceedings of the IEEE, vol. 78, no. 10, pp. 1629-1636, Oct. 1990. https://doi.org/10.1109/5.58356
  2. C. Mead, Analog VLSI and neural system, Addison-Wesley, 1989.
  3. I. P. Morns and S. S. Dlay, "Analog design of a new neural network for optical character recognition," IEEE Trans. Neural Netw., vol. 10, no. 4, pp. 951-953, Jul. 1999. https://doi.org/10.1109/72.774269
  4. J. B. Lont and W. Guggenbühl, "Analog CMOS implementation of a multilayer perceptron with nonlinear synapses," IEEE Trans. Neural Network, vol. 3, no. 3, May 1992.
  5. J. Mirsa and I. Saha, "Artificial neural networks in hardware: A survey of two decades of progress," Neurocomputing, vol .74, iss. 1-3, pp. 239-255, Dec. 2010. https://doi.org/10.1016/j.neucom.2010.03.021
  6. K. Mohamad, M. F. O. Mahmud, F. H. Adnan, and W. F. H. Abdullah, "Design of single neuron on FPGA," IEEE Symposium on Humanities, Science and Engineering Research, pp. 133-136, Jun. 2012.
  7. S. Himavathi, D. Anitha, and A. Muthuramalingam, "Feedforward neural network implementation in FPGA using layer multiplexing for effective resource utilization," IEEE Trans. Neural Netw., vol. 18, no. 3, pp. 880-888, May 2007. https://doi.org/10.1109/TNN.2007.891626
  8. S. A. Al-Kazzaz, "FPGA implementation of artificial neuron: Comparison study," International Conference on Information and Communication Technologies, pp. 1-6, Apr. 2008.
  9. J. M. Granado, M. A. Vega, R. Perez, J. M. Sanchez, and J. A. Gomez, "Using FPGAs to implement artificial neural networks," IEEE International Conference on Electronics, Circuit and System, pp. 934-937, Dec. 2006.
  10. T. Shima, T.Kimura, Y.Kamatani, T.Itakura, Y.Fujita, and T.Iida, "Neuro chips with on-chip back-propagation and/or Hebbian learning," IEEE J. Solid-State Circuits, vol. 27, no. 12, pp. 1868-1875, Dec. 1992. https://doi.org/10.1109/4.173117
  11. C. Kügeler, M. Meier, R. Rosezin, S. Gilles, and R. Waser, "High density 3D memory architecture based on the resistive switching effect," Solid State Electron, vol. 53, no. 12, pp. 1287-1292, Dec. 2009. https://doi.org/10.1016/j.sse.2009.09.034
  12. S. H. Jo, T. Chang, I. Ebong, B. Bhadviya, P. Mazumder, and W. Lu, "Nanoscale memristor device as synapse in neuromorphic systems," Nano Lett., vol. 10, no. 4, pp. 1297-1301, Mar. 2010. https://doi.org/10.1021/nl904092h
  13. W. Lu, K. H. Kim, T. Chang, and S. Gaba, "Twoterminal resistive switches (memristors) for memory and logic applications," Design Automation Conf., pp. 217-223, Jan. 2011.
  14. L. O. Chua, "Memristor - the missing circuit element," IEEE Trans. Circuit Theory, vol. CT-18, no. 5, pp. 507-519, Sep. 1971.
  15. D. B. Strukov, G. S. Sinder, D. R. Stewart, and R. S. Williams, "The missing memristor found," Nature, vol. 453, pp. 80-83, May 2008. https://doi.org/10.1038/nature06932
  16. Y. Kim and K. Min, "Synaptic weighting circuits for cellular neural networks," 13th International Workshop on Cellular Nanoscale Networks and Their Applications, pp. 1-6, Aug. 2012.
  17. H. Wang, H. Li, and R. E. Pino, "Memristor-based synapse design and training scheme for neuromorphic computing architecture," International Joint Conference on Neural Networks, pp. 1-5, Jun. 2012.
  18. H. Kim, M, Pd. Sad, C. Yang, T. Roska, and L. O. Chua, "Neural synapse weighting with a pulsebased memristor circuit," IEEE Trans. Circuit and System, vol. 59, no. 1, pp. 148-158, Jan. 2012. https://doi.org/10.1109/TCSI.2011.2161360
  19. S. P. Adhikari, C. Yang, H. Kim, and L. O. Chua, "Memristor bridge synapse-based neural network and its learning," Trans. Neural Network and Learning System, vol. 23, no. 9, pp. 1426-1435, Sep. 2012. https://doi.org/10.1109/TNNLS.2012.2204770
  20. M. Hu, H, Li, Q. Wu, G. S. Rose, and Y. Chen, "Memristor crossbar based hardware realization of BSB recall function," International Joint Conference on Neural Networks, pp. 1-7, Jun. 2012.
  21. K. Min, "Memristor circuits for neuromorphic systems," Workshop on Memristor-based Systems for Neuromorphic Applications, Turin in Italy, Sep. 2013.
  22. S. M. Tam, B. Gupta, H. A. Castro, and M. Holler, "Learning on analog VLSI network chip," in Proc. IEEE Int. Conf. Syst., Man and Cybern., pp. 701-703, Nov. 1990.
  23. S. J. Ham, H. S. Mo, and K. S. Min, "Low-power VDD/3 write scheme with inversion coding circuit for complementary memristor array," IEEE Trans. Nanotechnology, vol. 12, no. 5, pp. 851-857, Sep. 2013. https://doi.org/10.1109/TNANO.2013.2274529

Cited by

  1. Mapping weight matrix of a neural network’s layer onto memristor crossbar vol.24, pp.2, 2015, https://doi.org/10.3103/S1060992X15020125
  2. Synaptic Characteristics of Ag/AgInSbTe/Ta-Based Memristor for Pattern Recognition Applications vol.64, pp.4, 2017, https://doi.org/10.1109/TED.2017.2671433
  3. Memristor-Based Circuit Design for Multilayer Neural Networks vol.65, pp.2, 2018, https://doi.org/10.1109/TCSI.2017.2729787
  4. Modeling and Analysis of Passive Switching Crossbar Arrays vol.65, pp.1, 2018, https://doi.org/10.1109/TCSI.2017.2714101
  5. Neuromorphic Computing with Memristor Crossbar vol.215, pp.13, 2018, https://doi.org/10.1002/pssa.201700875