Design of a Power Efficient Artificial Neuron Using Superconducting Nanowires
With the rising societal demand for more information-processing capacity with lower power consumption, alternative architectures inspired by the parallelism and robustness of the human brain have recently emerged as possible solutions. In particular, spiking neural networks (SNNs) offer a bio-realis...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media SA
2020
|
| Online Access: | https://hdl.handle.net/1721.1/124787 |
| _version_ | 1811071147068882944 |
|---|---|
| author | Toomey, Emily Anne Segall, Ken Berggren, Karl K. |
| author2 | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science |
| author_facet | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Toomey, Emily Anne Segall, Ken Berggren, Karl K. |
| author_sort | Toomey, Emily Anne |
| collection | MIT |
| description | With the rising societal demand for more information-processing capacity with lower power consumption, alternative architectures inspired by the parallelism and robustness of the human brain have recently emerged as possible solutions. In particular, spiking neural networks (SNNs) offer a bio-realistic approach, relying on pulses, analogous to action potentials, as units of information. While software encoded networks provide flexibility and precision, they are often computationally expensive. As a result, hardware SNNs based on the spiking dynamics of a device or circuit represent an increasingly appealing direction. Here, we propose to use superconducting nanowires as a platform for the development of an artificial neuron. Building on an architecture first proposed for Josephson junctions, we rely on the intrinsic non-linearity of two coupled nanowires to generate spiking behavior, and use electrothermal circuit simulations to demonstrate that the nanowire neuron reproduces multiple characteristics of biological neurons. Furthermore, by harnessing the non-linearity of the superconducting nanowire’s inductance, we develop a design for a variable inductive synapse capable of both excitatory and inhibitory control. We demonstrate that this synapse design supports direct fan-out, a feature that has been difficult to achieve in other superconducting architectures, and that the nanowire neuron’s nominal energy performance is competitive with that of current technologies. |
| first_indexed | 2024-09-23T08:46:45Z |
| format | Article |
| id | mit-1721.1/124787 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T08:46:45Z |
| publishDate | 2020 |
| publisher | Frontiers Media SA |
| record_format | dspace |
| spelling | mit-1721.1/1247872022-09-23T14:29:14Z Design of a Power Efficient Artificial Neuron Using Superconducting Nanowires Toomey, Emily Anne Segall, Ken Berggren, Karl K. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science With the rising societal demand for more information-processing capacity with lower power consumption, alternative architectures inspired by the parallelism and robustness of the human brain have recently emerged as possible solutions. In particular, spiking neural networks (SNNs) offer a bio-realistic approach, relying on pulses, analogous to action potentials, as units of information. While software encoded networks provide flexibility and precision, they are often computationally expensive. As a result, hardware SNNs based on the spiking dynamics of a device or circuit represent an increasingly appealing direction. Here, we propose to use superconducting nanowires as a platform for the development of an artificial neuron. Building on an architecture first proposed for Josephson junctions, we rely on the intrinsic non-linearity of two coupled nanowires to generate spiking behavior, and use electrothermal circuit simulations to demonstrate that the nanowire neuron reproduces multiple characteristics of biological neurons. Furthermore, by harnessing the non-linearity of the superconducting nanowire’s inductance, we develop a design for a variable inductive synapse capable of both excitatory and inhibitory control. We demonstrate that this synapse design supports direct fan-out, a feature that has been difficult to achieve in other superconducting architectures, and that the nanowire neuron’s nominal energy performance is competitive with that of current technologies. National Science Foundation (U.S.). GraduateResearch Fellowship Program (NSF GRFP) (Grant No. 1122374). 2020-04-22T14:28:43Z 2020-04-22T14:28:43Z 2019-09 2019-06 2019-11-26T13:46:28Z Article http://purl.org/eprint/type/JournalArticle 2381-2710 2154-5723 https://hdl.handle.net/1721.1/124787 Toomey, Emily, Segall, Ken, and Berggren, Karl K. (2019) Design of a Power Efficient Artificial Neuron Using Superconducting Nanowires. Front. Neurosci. 13:933. © Copyright © 2019 Toomey, Segall and Berggren. en http://dx.doi.org/10.3389/fnins.2019.00933 Frontiers in Neuroscience Creative Commons Attribution 4.0 International license https://creativecommons.org/licenses/by/4.0/ application/pdf Frontiers Media SA Frontiers |
| spellingShingle | Toomey, Emily Anne Segall, Ken Berggren, Karl K. Design of a Power Efficient Artificial Neuron Using Superconducting Nanowires |
| title | Design of a Power Efficient Artificial Neuron Using Superconducting Nanowires |
| title_full | Design of a Power Efficient Artificial Neuron Using Superconducting Nanowires |
| title_fullStr | Design of a Power Efficient Artificial Neuron Using Superconducting Nanowires |
| title_full_unstemmed | Design of a Power Efficient Artificial Neuron Using Superconducting Nanowires |
| title_short | Design of a Power Efficient Artificial Neuron Using Superconducting Nanowires |
| title_sort | design of a power efficient artificial neuron using superconducting nanowires |
| url | https://hdl.handle.net/1721.1/124787 |
| work_keys_str_mv | AT toomeyemilyanne designofapowerefficientartificialneuronusingsuperconductingnanowires AT segallken designofapowerefficientartificialneuronusingsuperconductingnanowires AT berggrenkarlk designofapowerefficientartificialneuronusingsuperconductingnanowires |