Superconducting Nanowire Spiking Element for Neural Networks
- 23 September 2020
- journal article
- research article
- Published by American Chemical Society (ACS) in Nano Letters
- Vol. 20 (11), 8059-8066
- https://doi.org/10.1021/acs.nanolett.0c03057
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.Funding Information
- Division of Graduate Education (1122374)
- Bose Foundation
This publication has 26 references indexed in Scilit:
- Towards spike-based machine intelligence with neuromorphic computingNature, 2019
- Design of a Power Efficient Artificial Neuron Using Superconducting NanowiresFrontiers in Neuroscience, 2019
- Fast Spiking of a Mott VO2–Carbon Nanotube Composite DeviceNano Letters, 2019
- Chaos and Relaxation Oscillations in Spin-Torque Windmill Spiking OscillatorsPhysical Review Applied, 2019
- Superconducting Neuromorphic Computing Using Quantum Phase-Slip JunctionsIEEE Transactions on Applied Superconductivity, 2019
- Spiking neuron circuits using superconducting quantum phase-slip junctionsJournal of Applied Physics, 2018
- Energy-efficient single-flux-quantum based neuromorphic computingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2017
- A 4-fJ/Spike Artificial Neuron in 65 nm CMOS TechnologyFrontiers in Neuroscience, 2017
- Large-scale neuromorphic computing systemsJournal of Neural Engineering, 2016
- Josephson junction simulation of neuronsPhysical Review E, 2010