Superconducting Nanowire Spiking Element for Neural Networks
Name
2007.15101.pdf
Description
Submitted version
Size
1.86 MB
Format
Adobe PDF
Checksum (MD5)
59cd4f70d5bd9b7f3e4a653b30aba08d
Author(s)
Toomey, E
Segall, K
Castellani, M
Colangelo, M
Lynch, N
Berggren, KK
Date Issued
2020
Journal
Nano Letters
Publisher
American Chemical Society (ACS)
Version
Original manuscript
Abstract
© 2020 American Chemical Society. All rights reserved. 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 â 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.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1021/acs.nanolett.0c03057
