Superconducting Nanowire Spiking Element for Neural Networks
Source abstract
Abstract
As the limits of traditional von Neumann computing come into view, the brain's ability to communicate vast quantities of information using low-power spikes has become an increasing source of inspiration for alternative architectures. Key to the success of these largescale neural networks is a power-efficient spiking element that is scalable and easily interfaced with traditional control electronics. In this work, we present a spiking element fabricated from superconducting nanowires that has pulse energies on the order of ∼10 aJ. We demonstrate that the device reproduces essential characteristics of biological neurons, such as a refractory period and a firing threshold. Through simulations using experimentally measured device parameters, we show how nanowire-based networks may be used for inference in image recognition and that the probabilistic nature of nanowire switching may be exploited for modeling biological processes and for applications that rely on stochasticity.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Advanced Memory and Neural Computing · Ferroelectric and Negative Capacitance Devices · Advancements in Semiconductor Devices and Circuit Design
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States
Department of Physics and Astronomy, Colgate University, Hamilton, New York 13346, United States
Funding
Division of Graduate Education · Bose Foundation
References (30)
Show source-provided references
1. Semiconductor Industry Association · 2020
2. 10.1088/1741-2560/13/5/05100110.1088/1741-2560/13/5/051001 ↗
3. 10.3389/fnins.2017.0012310.3389/fnins.2017.00123 ↗
4. 10.1103/PhysRevApplied.11.04409310.1103/PhysRevApplied.11.044093 ↗
5. 10.1038/s41586-019-1677-210.1038/s41586-019-1677-2 ↗
6. 10.1021/acs.nanolett.9b0155410.1021/acs.nanolett.9b01554 ↗
7. 10.1109/ICRC.2017.812363410.1109/ICRC.2017.8123634 ↗
8. 10.1063/1.504242110.1063/1.5042421 ↗
9. 10.1109/TASC.2019.289211110.1109/TASC.2019.2892111 ↗
10. Bozbey A. · 2020
11. 10.1103/PhysRevE.82.01191410.1103/PhysRevE.82.011914 ↗
12. 10.3389/fnins.2019.0093310.3389/fnins.2019.00933 ↗
13. 10.1103/PhysRevApplied.9.06402110.1103/PhysRevApplied.9.064021 ↗
14. 10.1021/nl502629x10.1021/nl502629x ↗
15. 10.1088/1361-6668/aa5f3310.1088/1361-6668/aa5f33 ↗
16. Ermentrout G. B. · 2010 · 35 · 110.1007/978-0-387-87708-2_1 ↗
17. 10.1088/1361-6668/aab14910.1088/1361-6668/aab149 ↗
18. 10.1016/0013-4694(72)90058-210.1016/0013-4694(72)90058-2 ↗
19. 10.1109/TNN.2004.83271910.1109/TNN.2004.832719 ↗
20. 10.1109/TASC.2019.289204910.1109/TASC.2019.2892049 ↗
21. 10.1038/nature1444110.1038/nature14441 ↗
22. Nielsen M. · 2015
23. 10.3389/fncom.2017.0002010.3389/fncom.2017.00020 ↗
24. 10.3389/fncom.2014.0006810.3389/fncom.2014.00068 ↗
25. Lynch N. · 2019
26. 10.1088/1361-6668/aaa82010.1088/1361-6668/aaa820 ↗
27. 10.1088/1367-2630/aa733110.1088/1367-2630/aa7331 ↗
28. 10.1103/PhysRevApplied.11.03400610.1103/PhysRevApplied.11.034006 ↗
29. 10.1109/MM.2015.4310.1109/MM.2015.43 ↗
30. Tzimpragos, G. A Computational Temporal Logic for Superconducting Accelerators. In Proceedings of the Twenty-Fifth International Conference on Architectural Support for Programming Languages and Operating Systems; Association for Computing Machinery, 2020; pp 435–448.10.1145/3373376.3378517 ↗