Subwavelength neuromorphic nanophotonic integrated circuits for spike-based computing: challenges and prospects

B. Romeira; J. B. Nieder; B. Jacob; R. M. R. Adão; F. Camarneiro; J. Arturo Alanis; M. Hejda; A. Hurtado; J. Lourenço; D. Castro Alves; J. M. L. Figueiredo; I. Ortega-Piwonka; J. Javaloyes

doi:10.1117/12.2591852

Subwavelength neuromorphic nanophotonic integrated circuits for spike-based computing: challenges and prospects

B. Romeira, J. B. Nieder, B. Jacob, R. M. R. Adão, F. Camarneiro, J. Arturo Alanis, M. Hejda, A. Hurtado, J. Lourenço, D. Castro Alves, J. M. L. Figueiredo, I. Ortega-Piwonka, J. Javaloyes

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution book

4 Downloads (Pure)

Abstract

Event-activated biological-inspired subwavelength (sub-λ) optical neural networks are of paramount importance for energy-efficient and high-bandwidth artificial intelligence (AI) systems. Despite the significant advances to build active optical artificial neurons using for example phase-change materials, lasers, photodetectors, and modulators, miniaturized integrated sources and detectors suited for few-photon spike-based operation and of interest for neuromorphic optical computing are still lacking. In this invited paper we outline the main challenges, opportunities, and recent results towards the development of interconnected neuromorphic nanoscale light-emitting diodes (nanoLEDs) as key-enabling artificial spiking neuron circuits in photonic neural networks. This method of spike generation in neuromorphic nanoLEDs paves the way for sub-λ incoherent neural circuits for fast and efficient asynchronous brain-inspired computation.

Original language	English
Title of host publication	Proceedings Volume 11804, Emerging Topics in Artificial Intelligence (ETAI) 2021
Place of Publication	San Diego, California, United States
Chapter	118040D
Volume	11804
ISBN (Electronic)	9781510644472
DOIs	https://doi.org/10.1117/12.2591852
Publication status	Published - 2 Sep 2021
Event	Emerging Topics in Artificial Intelligence 2021 - San Diego, United States Duration: 1 Aug 2021 → 5 Aug 2021

Publication series

Name	Emerging Topics in Artificial Intelligence
Publisher	SPIE
Volume	11804

Conference

Conference	Emerging Topics in Artificial Intelligence 2021
Abbreviated title	ETAI 2021
Country/Territory	United States
City	San Diego
Period	1/08/21 → 5/08/21

Keywords

neural networks
nanophotonics
light emitting diodes
integrated circuits
nanoLEDs
neuromorphic computing
optical interconnects
resonant tunnelling diodes (RTDs)
spiking neural networks

Access to Document

10.1117/12.2591852

Romeira-etal-SPIE-2021-Subwavelength-neuromorphic-nanophotonic-integrated-circuits-for-spike-based-computingAccepted author manuscript, 576 KBLicence: Strath_1

1 Finished
1 Active

Turing AI Fellowship: PHOTONics for ultrafast Artificial Intelligence
Hurtado, A.
EPSRC (Engineering and Physical Sciences Research Council)
1/01/21 → 31/12/25
Project: Research Fellowship
Energy-efficient and high-bandwidth neuromorphic nanophotonic chips for artificial intelligence systems (ChipAI) H2020-FETOPEN
Hurtado, A. & Strain, M.
European Commission - Horizon 2020
1/03/19 → 28/02/22
Project: Research

Cite this

Romeira, B., Nieder, J. B., Jacob, B., Adão, R. M. R., Camarneiro, F., Alanis, J. A., Hejda, M., Hurtado, A., Lourenço, J., Castro Alves, D., Figueiredo, J. M. L., Ortega-Piwonka, I., & Javaloyes, J. (2021). Subwavelength neuromorphic nanophotonic integrated circuits for spike-based computing: challenges and prospects. In Proceedings Volume 11804, Emerging Topics in Artificial Intelligence (ETAI) 2021 (Vol. 11804). (Emerging Topics in Artificial Intelligence; Vol. 11804).. https://doi.org/10.1117/12.2591852

@inproceedings{d9e899e8007244b598ab74365c92f65d,

title = "Subwavelength neuromorphic nanophotonic integrated circuits for spike-based computing: challenges and prospects",

abstract = "Event-activated biological-inspired subwavelength (sub-λ) optical neural networks are of paramount importance for energy-efficient and high-bandwidth artificial intelligence (AI) systems. Despite the significant advances to build active optical artificial neurons using for example phase-change materials, lasers, photodetectors, and modulators, miniaturized integrated sources and detectors suited for few-photon spike-based operation and of interest for neuromorphic optical computing are still lacking. In this invited paper we outline the main challenges, opportunities, and recent results towards the development of interconnected neuromorphic nanoscale light-emitting diodes (nanoLEDs) as key-enabling artificial spiking neuron circuits in photonic neural networks. This method of spike generation in neuromorphic nanoLEDs paves the way for sub-λ incoherent neural circuits for fast and efficient asynchronous brain-inspired computation.",

keywords = "neural networks, nanophotonics, light emitting diodes, integrated circuits, nanoLEDs, neuromorphic computing, optical interconnects, resonant tunnelling diodes (RTDs), spiking neural networks",

author = "B. Romeira and Nieder, {J. B.} and B. Jacob and Ad{\~a}o, {R. M. R.} and F. Camarneiro and Alanis, {J. Arturo} and M. Hejda and A. Hurtado and J. Louren{\c c}o and {Castro Alves}, D. and Figueiredo, {J. M. L.} and I. Ortega-Piwonka and J. Javaloyes",

year = "2021",

month = sep,

day = "2",

doi = "10.1117/12.2591852",

language = "English",

isbn = "9781510644465",

volume = "11804",

series = "Emerging Topics in Artificial Intelligence",

publisher = "SPIE",

booktitle = "Proceedings Volume 11804, Emerging Topics in Artificial Intelligence (ETAI) 2021",

note = "Emerging Topics in Artificial Intelligence 2021, ETAI 2021 ; Conference date: 01-08-2021 Through 05-08-2021",

}

Romeira, B, Nieder, JB, Jacob, B, Adão, RMR, Camarneiro, F, Alanis, JA, Hejda, M , Hurtado, A, Lourenço, J, Castro Alves, D, Figueiredo, JML, Ortega-Piwonka, I & Javaloyes, J 2021, Subwavelength neuromorphic nanophotonic integrated circuits for spike-based computing: challenges and prospects. in Proceedings Volume 11804, Emerging Topics in Artificial Intelligence (ETAI) 2021. vol. 11804, Emerging Topics in Artificial Intelligence, vol. 11804, San Diego, California, United States, Emerging Topics in Artificial Intelligence 2021, San Diego, United States, 1/08/21. https://doi.org/10.1117/12.2591852

Subwavelength neuromorphic nanophotonic integrated circuits for spike-based computing : challenges and prospects. / Romeira, B.; Nieder, J. B.; Jacob, B. et al.

Proceedings Volume 11804, Emerging Topics in Artificial Intelligence (ETAI) 2021. Vol. 11804 San Diego, California, United States, 2021. (Emerging Topics in Artificial Intelligence; Vol. 11804).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution book

TY - GEN

T1 - Subwavelength neuromorphic nanophotonic integrated circuits for spike-based computing

T2 - Emerging Topics in Artificial Intelligence 2021

AU - Romeira, B.

AU - Nieder, J. B.

AU - Jacob, B.

AU - Adão, R. M. R.

AU - Camarneiro, F.

AU - Alanis, J. Arturo

AU - Hejda, M.

AU - Hurtado, A.

AU - Lourenço, J.

AU - Castro Alves, D.

AU - Figueiredo, J. M. L.

AU - Ortega-Piwonka, I.

AU - Javaloyes, J.

PY - 2021/9/2

Y1 - 2021/9/2

N2 - Event-activated biological-inspired subwavelength (sub-λ) optical neural networks are of paramount importance for energy-efficient and high-bandwidth artificial intelligence (AI) systems. Despite the significant advances to build active optical artificial neurons using for example phase-change materials, lasers, photodetectors, and modulators, miniaturized integrated sources and detectors suited for few-photon spike-based operation and of interest for neuromorphic optical computing are still lacking. In this invited paper we outline the main challenges, opportunities, and recent results towards the development of interconnected neuromorphic nanoscale light-emitting diodes (nanoLEDs) as key-enabling artificial spiking neuron circuits in photonic neural networks. This method of spike generation in neuromorphic nanoLEDs paves the way for sub-λ incoherent neural circuits for fast and efficient asynchronous brain-inspired computation.

AB - Event-activated biological-inspired subwavelength (sub-λ) optical neural networks are of paramount importance for energy-efficient and high-bandwidth artificial intelligence (AI) systems. Despite the significant advances to build active optical artificial neurons using for example phase-change materials, lasers, photodetectors, and modulators, miniaturized integrated sources and detectors suited for few-photon spike-based operation and of interest for neuromorphic optical computing are still lacking. In this invited paper we outline the main challenges, opportunities, and recent results towards the development of interconnected neuromorphic nanoscale light-emitting diodes (nanoLEDs) as key-enabling artificial spiking neuron circuits in photonic neural networks. This method of spike generation in neuromorphic nanoLEDs paves the way for sub-λ incoherent neural circuits for fast and efficient asynchronous brain-inspired computation.

KW - neural networks

KW - nanophotonics

KW - light emitting diodes

KW - integrated circuits

KW - nanoLEDs

KW - neuromorphic computing

KW - optical interconnects

KW - resonant tunnelling diodes (RTDs)

KW - spiking neural networks

U2 - 10.1117/12.2591852

DO - 10.1117/12.2591852

M3 - Conference contribution book

SN - 9781510644465

VL - 11804

T3 - Emerging Topics in Artificial Intelligence

BT - Proceedings Volume 11804, Emerging Topics in Artificial Intelligence (ETAI) 2021

CY - San Diego, California, United States

Y2 - 1 August 2021 through 5 August 2021

ER -

Romeira B, Nieder JB, Jacob B, Adão RMR, Camarneiro F, Alanis JA et al. Subwavelength neuromorphic nanophotonic integrated circuits for spike-based computing: challenges and prospects. In Proceedings Volume 11804, Emerging Topics in Artificial Intelligence (ETAI) 2021. Vol. 11804. San Diego, California, United States. 2021. (Emerging Topics in Artificial Intelligence). Epub 2021 May 4. doi: 10.1117/12.2591852

Subwavelength neuromorphic nanophotonic integrated circuits for spike-based computing: challenges and prospects

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Projects

Turing AI Fellowship: PHOTONics for ultrafast Artificial Intelligence

Energy-efficient and high-bandwidth neuromorphic nanophotonic chips for artificial intelligence systems (ChipAI) H2020-FETOPEN

Cite this