Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Nanoscale photonic artificial neuron with biological signal processing

Sestoft, Joachim Elbeshausen ; Kjellberg Jensen, Thomas LU orcid ; Flodgren, Vidar LU ; Das, Abhijit LU orcid ; Schlosser, Rasmus D. ; Alcer, David LU orcid ; Lamers, Mariia LU orcid ; Kanne, Thomas ; Borgström, Magnus LU orcid and Nygård, Jesper , et al. (2026) In Nature Communications 17(1).
Abstract
Neuromorphic hardware can mitigate the unsustainable energy demand of artificial intelligence infrastructure. Photonic approaches provide high speed, low energy, and high connectivity but existing solutions have large circuit footprints which limits scaling potential and they miss key biological functions, like inhibition. We report a nano-optoelectronic artificial neuron with at least 100-fold reduced circuit footprints compared to existing approaches and picowatt-level operating power. The device deterministically integrates excitatory and inhibitory inputs, performs a nonlinear transfer operation, and exhibits biologically relevant temporal dynamics. Neural weighting is implemented via tunable input gains, enabling controlled summation... (More)
Neuromorphic hardware can mitigate the unsustainable energy demand of artificial intelligence infrastructure. Photonic approaches provide high speed, low energy, and high connectivity but existing solutions have large circuit footprints which limits scaling potential and they miss key biological functions, like inhibition. We report a nano-optoelectronic artificial neuron with at least 100-fold reduced circuit footprints compared to existing approaches and picowatt-level operating power. The device deterministically integrates excitatory and inhibitory inputs, performs a nonlinear transfer operation, and exhibits biologically relevant temporal dynamics. Neural weighting is implemented via tunable input gains, enabling controlled summation and thresholding. The architecture is compatible with commercial silicon technology, supports multi-wavelength operation, and can be used for both computing and optical sensing. This work paves the way for two important research paths: photonic neuromorphic computing with nanosized footprints and low power consumption, and adaptive optical sensing, using the same architecture as a compact, modular front end. (Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; ; ; ; and , et al. (More)
; ; ; ; ; ; ; ; ; and (Less)
organization
publishing date
type
Contribution to journal
publication status
published
subject
in
Nature Communications
volume
17
issue
1
article number
4798
publisher
Nature Publishing Group
external identifiers
  • scopus:105040527621
ISSN
2041-1723
DOI
10.1038/s41467-026-71446-4
project
Insect-Brain inspired Neuromorphic Nanophotonics
language
English
LU publication?
yes
id
f4787f43-4c36-40ac-8fc9-faeb7ffd4093
date added to LUP
2026-06-08 12:26:47
date last changed
2026-06-09 14:50:37
@article{f4787f43-4c36-40ac-8fc9-faeb7ffd4093,
  abstract     = {{Neuromorphic hardware can mitigate the unsustainable energy demand of artificial intelligence infrastructure. Photonic approaches provide high speed, low energy, and high connectivity but existing solutions have large circuit footprints which limits scaling potential and they miss key biological functions, like inhibition. We report a nano-optoelectronic artificial neuron with at least 100-fold reduced circuit footprints compared to existing approaches and picowatt-level operating power. The device deterministically integrates excitatory and inhibitory inputs, performs a nonlinear transfer operation, and exhibits biologically relevant temporal dynamics. Neural weighting is implemented via tunable input gains, enabling controlled summation and thresholding. The architecture is compatible with commercial silicon technology, supports multi-wavelength operation, and can be used for both computing and optical sensing. This work paves the way for two important research paths: photonic neuromorphic computing with nanosized footprints and low power consumption, and adaptive optical sensing, using the same architecture as a compact, modular front end.}},
  author       = {{Sestoft, Joachim Elbeshausen and Kjellberg Jensen, Thomas and Flodgren, Vidar and Das, Abhijit and Schlosser, Rasmus D. and Alcer, David and Lamers, Mariia and Kanne, Thomas and Borgström, Magnus and Nygård, Jesper and Mikkelsen, Anders}},
  issn         = {{2041-1723}},
  language     = {{eng}},
  month        = {{04}},
  number       = {{1}},
  publisher    = {{Nature Publishing Group}},
  series       = {{Nature Communications}},
  title        = {{Nanoscale photonic artificial neuron with biological signal processing}},
  url          = {{http://dx.doi.org/10.1038/s41467-026-71446-4}},
  doi          = {{10.1038/s41467-026-71446-4}},
  volume       = {{17}},
  year         = {{2026}},
}