logo

SCIENCE CHINA Information Sciences, Volume 64 , Issue 11 : 219402(2021) https://doi.org/10.1007/s11432-020-3127-x

Investigation of weight updating modes on oxide-based resistive switching memory synapse towards neuromorphic computing applications

More info
  • ReceivedSep 24, 2020
  • AcceptedNov 25, 2020
  • PublishedSep 7, 2021

Abstract

There is no abstract available for this article.


Acknowledgment

This work was supported by the National Science and Technology Major Project of China (Grant No. 2017ZX02301007-001), National Natural Science Foundation of China (Grant Nos. 61922083, 61804167, 61834009, 61904200, 62025406, 61821091), and Strategic Priority Research Program of Chinese Academy of Sciences (Grant No. XDB44000000).


Supplement

Appendixes A and B.


References

[1] Park S, Kim H, Choo M, et al. RRAM-based synapse for neuromorphic system with pattern recognition function. In: Proceedings of International Electron Devices Meeting, 2012. Google Scholar

[2] Chang C C, Chen P C, Chou T, et al. Mitigating asymmetric nonlinear weight update effects in hardware neural network based on analog resistive synapse. IEEE Journal on Emerging and Selected Topics in Circuits and Systems, 2017, 8(1): 116-124. Google Scholar

[3] Woo J, Yu S M. Resistive-memory-based analog synapse: the pursuit for linear and symmetric weight update. IEEE Nanotechnol Mag, 2018, 12: 36--44. Google Scholar

[4] Lv H, Xu X, Yuan P, et al. BEOL based RRAM with one extra-mask for low cost, highly reliable embedded application in 28 nm node and beyond. In: Proceedings of IEEE International Electron Devices Meeting (IEDM), 2017. Google Scholar

[5] Woo J, Moon K, Song J. Improved Synaptic Behavior Under Identical Pulses Using AlOx/HfO2Bilayer RRAM Array for Neuromorphic Systems. IEEE Electron Device Lett, 2016, 37: 994-997 CrossRef ADS Google Scholar

[6] Woo J, Moon K, Song J. Optimized Programming Scheme Enabling Linear Potentiation in Filamentary HfO2 RRAM Synapse for Neuromorphic Systems. IEEE Trans Electron Devices, 2016, 63: 5064-5067 CrossRef ADS Google Scholar

[7] Gonzalez M B, Martin-Martinez J, Maestro M. Investigation of Filamentary Current Fluctuations Features in the High-Resistance State of Ni/HfO2-Based RRAM. IEEE Trans Electron Devices, 2016, 63: 3116-3122 CrossRef ADS Google Scholar

[8] Ninomiya T , Wei Z , Muraoka S , et al. Conductive Filament Scaling of TaOx Bipolar ReRAM for Improving Data Retention Under Low Operation Current. IEEE Transactions on Electron Devices, 2013, 60(4):1384-1389. Google Scholar

  • Figure 1

    (Color online) (a) $I$-$V$ curves of the 1T1R RRAM devices for 100 cycles. Inset: schematic of RRAM stack. (b) Cycle-to-cycle resistance distribution measured in 100 cycles. (c) Employed nonidentical programming pulse schemes for potentiation. Releasing current limiting gradually results in many oxygen vacancies move to the CF. (d) Optimized programming schemes with identical SET pulse and RESET pulse pair. The increased conductance measured at 0.1 V. High temperature retention measurement (125$^{\circ}$C) of incremental LRSs programmed by (e) GVR mode, (f) CDV mode.

qqqq

Contact and support