Hexagonal boron nitride (h-BN) memristor arrays for analog-based machine learning hardware
Source abstract
Abstract
Abstract Recent studies of resistive switching devices with hexagonal boron nitride (h-BN) as the switching layer have shown the potential of two-dimensional (2D) materials for memory and neuromorphic computing applications. The use of 2D materials allows scaling the resistive switching layer thickness to sub-nanometer dimensions enabling devices to operate with low switching voltages and high programming speeds, offering large improvements in efficiency and performance as well as ultra-dense integration. These characteristics are of interest for the implementation of neuromorphic computing and machine learning hardware based on memristor crossbars. However, existing demonstrations of h-BN memristors focus on single isolated device switching properties and lack attention to fundamental machine learning functions. This paper demonstrates the hardware implementation of dot product operations, a basic analog function ubiquitous in machine learning, using h-BN memristor arrays. Moreover, we demonstrate the hardware implementation of a linear regression algorithm on h-BN memristor arrays.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Memory and Neural Computing · Ferroelectric and Negative Capacitance Devices · Transition Metal Oxide Nanomaterials
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (45)
Show source-provided references
1. Huyghebaert, C. et al. 2D materials: Roadmap to CMOS integration. In 2018 Intentional Electron Devices Meeting (IEDM), 512–515 (IEEE, 2018).10.1109/IEDM.2018.8614679 ↗
2. Li, M.-Y., Su, S.-K., Wong, H.-S. P. & Li, L.-J. How 2D semiconductors could extend Moore’s law. Nature 567, 169–170 (2019).10.1038/d41586-019-00793-8 ↗
3. Su, S.-K. et al. Layered semiconducting 2D materials for future transistor applications. Small Struct. 2, 2000103 (2021).10.1002/sstr.202000103 ↗
4. Robinson, J. A. Perspective: 2D for beyond CMOS. APL Mater. 6, 058202 (2018).10.1063/1.5022769 ↗
5. Lemme, M. C., Akinwande, D., Huyghebaert, C. & Stampfer, C. 2D Materials for future heterogeneous electronics. Nat. Commun. 13, 1392 (2021).10.1038/s41467-022-29001-4 ↗
6. Quellmalz, A. et al. Large-area integration of two-dimensional materials and their heterostructures by wafer bonding. Nat. Commun. 12, 1–11 (2021).10.1038/s41467-021-21136-0 ↗
7. Yu, L. et al. High-performance WSe2 complementary metal oxide semiconductor technology and integrated circuits. Nano Lett. 15, 4928–4934 (2015).10.1021/acs.nanolett.5b00668 ↗
8. Lin, Z. et al. Solution-processable 2D semiconductors for high-performance large-area electronics. Nature 562, 254–258 (2018).10.1038/s41586-018-0574-4 ↗
9. Amani, M., Burke, R. A., Proie, R. M. & Dubey, M. Flexible integrated circuits and multifunctional electronics based on single atomic layers of MoS2 and graphene. Nanotechnology 26, 115202 (2015).10.1088/0957-4484/26/11/115202 ↗
10. Xie, J. et al. Analysis of Schottky barrier heights and reduced Fermi-level pinning in monolayer CVD-grown MoS2 field-effect-transistors. Nanotechnology 33, 225702 (2022).10.1088/1361-6528/ac55d2 ↗
11. Chen, S. et al. Wafer-scale integration of two-dimensional materials in high-density memristive crossbar arrays for artificial neural networks. Nat. Electron. 3, 638–645 (2020).10.1038/s41928-020-00473-w ↗
12. Wang, L. et al. Electronic devices and circuits based on wafer-scale polycrystalline monolayer MoS2 by chemical vapor deposition. Adv. Electron. Mater. 5, 1–10 (2019).
13. Das, S., Chen, H. Y., Penumatcha, A. V. & Appenzeller, J. High performance multilayer MoS2 transistors with scandium contacts. Nano Lett. 13, 100–105 (2013).10.1021/nl303583v ↗
14. Lembke, D., Bertolazzi, S. & Kis, A. Single-layer MoS2 electronics. Acc. Chem. Res. 48, 100–110 (2015).10.1021/ar500274q ↗
15. Schwierz, F. Graphene transistors. Nat. Nanotechnol. 5, 487–496 (2010).10.1038/nnano.2010.89 ↗
16. Reddy, D., Register, L. F., Carpenter, G. D. & Banerjee, S. K. Graphene field-effect transistors. J. Phys. D. Appl. Phys. 44, 313001 (2011).10.1088/0022-3727/44/31/313001 ↗
17. Ge, R. et al. Atomristor: Nonvolatile resistance switching in atomic sheets of transition metal dichalcogenides. Nano Lett. 18, 434–441 (2018).10.1021/acs.nanolett.7b04342 ↗
18. Rehman, S. et al. Thickness-dependent resistive switching in black phosphorus CBRAM. J. Mater. Chem. C 7, 725–732 (2019).10.1039/C8TC04538K ↗
19. Ahmed, T. et al. Mixed ionic-electronic charge transport in layered black-phosphorus for low-power memory. Adv. Funct. Mater. 32, 1–11 (2022).10.1002/adfm.202107068 ↗
20. Pradhan, S. K., Xiao, B., Mishra, S., Killam, A. & Pradhan, A. K. Resistive switching behavior of reduced graphene oxide memory cells for low power nonvolatile device application. Sci. Rep. 6, 1–9 (2016).10.1038/srep26763 ↗
21. Romero, F. J. et al. Resistive switching in graphene oxide. Front. Mater. 7, 1–5 (2020).10.3389/fmats.2020.00017 ↗
22. Shi, Y. et al. Electronic synapses made of layered two-dimensional materials. Nat. Electron. 1, 458–465 (2018).10.1038/s41928-018-0118-9 ↗
23. Zhu, K. et al. Graphene-boron nitride-graphene cross-point memristors with three stable resistive states. ACS Appl. Mater. Interfaces 11, 37999–38005 (2019).10.1021/acsami.9b04412 ↗
24. Wu, X. et al. Thinnest nonvolatile memory based on monolayer h-BN. Adv. Mater. 31, 1–7 (2019).
25. Nikam, R. D., Rajput, K. G. & Hwang, H. Single-atom quantum-point contact switch using atomically thin hexagonal boron nitride. Small 17, 1–8 (2021).10.1002/smll.202006760 ↗
26. Derhacobian, N., Hollmer, S. C., Gilbert, N. & Kozicki, M. N. Power and energy perspectives of nonvolatile memory technologies. Proc. IEEE 98, 283–298 (2010).10.1109/JPROC.2009.2035147 ↗
27. Ge, J. et al. A sub-500 mV monolayer hexagonal boron nitride based memory device. Mater. Des. 198, 109366 (2021).10.1016/j.matdes.2020.109366 ↗
28. Lee, J. et al. Synaptic characteristics of amorphous boron nitride-based memristors on a highly doped silicon substrate for neuromorphic engineering. ACS Appl. Mater. Interfaces 12, 33908–33916 (2020).10.1021/acsami.0c07867 ↗
29. Liang, X. et al. 150 nm × 200 nm cross point hexagonal boron nitride based memristors with ultra-low currents in high resistive state. In 2019 Electron Devices Technol. Manuf. Conf. EDTM 2019 258–260 (IEEE, 2019)10.1109/EDTM.2019.8731155 ↗
30. Sanchez Esqueda, I., Zhao, H. & Wang, H. Efficient learning and crossbar operations with atomically-thin 2D material compound synapses. J. Appl. Phys. 124, 152133 (2018).10.1063/1.5042468 ↗
31. Musisi-Nkambwe, M., Afshari, S., Barnaby, H., Kozicki, M., & Sanchez Esqueda, I. The viability of analog-based accelerators for neuromorphic computing: A survey. Neuromorphic Comput. Eng. 1, 012001 (2021).10.1088/2634-4386/ac0242 ↗
32. Huh, W., Lee, D. & Lee, C. H. Memristors based on 2D materials as an artificial synapse for neuromorphic electronics. Adv. Mater. 32, 2002092 (2020).10.1002/adma.202002092 ↗
33. Mahmoodi, M. R., Prezioso, M. & Strukov, D. B. Versatile stochastic dot product circuits based on nonvolatile memories for high performance neurocomputing and neurooptimization. Nat. Commun. 10, 1–10 (2019).10.1038/s41467-019-13103-7 ↗
34. Hu, M. et al. Dot-product engine for neuromorphic computing: Programming 1T1M crossbar to accelerate matrix-vector multiplication. In 2016 53nd ACM/EDAC/IEEE Design Automation Conference (DAC) 1–6 (IEEE, 2016).10.1145/2897937.2898010 ↗
35. Berggren, K. et al. Roadmap on emerging hardware and technology for machine learning. Nanotechnology 32, 012002 (2021).10.1088/1361-6528/aba70f ↗
36. Ma, G. et al. Ultra-high ON/OFF ratio and multi-storage on NiO resistive switching device. J. Mater. Sci. 52, 238–246 (2017).10.1007/s10853-016-0326-5 ↗
37. Wong, H. S. P. et al. Metal-oxide RRAM. Proc. IEEE 100, 1951–1970 (2012).10.1109/JPROC.2012.2190369 ↗
38. Fantini, A. et al. Intrinsic switching variability in HfO2 RRAM. In 2013 5th IEEE Int. Mem. Work. IMW 2013 30–33 (IEEE, 2013).10.1109/IMW.2013.6582090 ↗
39. Merced-Grafals, E. J., Dávila, N., Ge, N., Williams, R. S. & Strachan, J. P. Repeatable, accurate, and high speed multi-level programming of memristor 1T1R arrays for power efficient analog computing applications. Nanotechnology 27, 365202 (2016).10.1088/0957-4484/27/36/365202 ↗
40. Li, C. et al. Analogue signal and image processing with large memristor crossbars. Nat. Electron. 1, 52–59 (2018).10.1038/s41928-017-0002-z ↗
41. Farhan. 50 Startups. https://www.kaggle.com/datasets/farhanmd29/50-startups (2022).
42. Afshari, S., Musisi-Nkambwe, M. & Sanchez Esqueda, I. Analyzing the impact of memristor variability on crossbar implementation of regression algorithms with smart weight update pulsing techniques. IEEE Trans. Circuits Syst. I Regul. Pap. 69, 2025–2034 (2022).10.1109/TCSI.2022.3144240 ↗
43. Nair, M. V. & Dudek, P. Gradient-descent-based learning in memristive crossbar arrays. In Proc. Int. Jt. Conf. Neural Networks 1–7 (IEEE, 2015).10.1109/IJCNN.2015.7280658 ↗
44. Prezioso, M. et al. Training and operation of an integrated neuromorphic network based on metal-oxide memristors. Nature 521, 61–64 (2015).10.1038/nature14441 ↗
45. Wen, S. et al. Adjusting learning rate of memristor-based multilayer neural networks via fuzzy method. IEEE Trans. Comput. Des. Integr. Circuits Syst. 38, 1084–1094 (2019).10.1109/TCAD.2018.2834436 ↗