TY - JOUR
T1 - Temporal information processing with an integrated laser neuron
AU - Peng, Hsuan Tung
AU - Angelatos, Gerasimos
AU - de Lima, Thomas Ferreira
AU - Nahmias, Mitchell A.
AU - Tait, Alexander N.
AU - Abbaslou, Siamak
AU - Shastri, Bhavin J.
AU - Prucnal, Paul R.
N1 - Funding Information:
Manuscript received April 17, 2019; revised June 27, 2019; accepted July 2, 2019. Date of publication July 12, 2019; date of current version August 28, 2019. This work was supported by National Science Foundation (NSF) Enhancing Access to the Radio Spectrum (EARS award 1642991) and Energy-Efficient Computing: From Devices to Architectures (E2CDA award 1740262) programs. The work of B. J. Shastri was supported by the Natural Sciences and Engineering Research Council of Canada (NSERC). (Corresponding author: Hsuan-Tung Peng.) H.-T. Peng, G. Angelatos, T. F. de Lima, M. A. Nahmias, S. Abbaslou, and P. R. Prucnal are with the Department of Electrical Engineering, Princeton University, Princeton, NJ 08544 USA (e-mail: hpeng@princeton.edu; ga4@ princeton.edu; tlima@princeton.edu; mnahmias@princeton.edu; siamaka@ princeton.edu; prucnal@princeton.edu).
Publisher Copyright:
© 2019 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See http://www.ieee.org/publications_standards/publications/rights/index.html for more information.
PY - 2020/1/1
Y1 - 2020/1/1
N2 - Spiking neural networks enable efficient information processing in real-time. Excitable lasers can exhibit ultrafast spiking dynamics, and when preceded by a photodetector in an O/E/O link, can process optical spikes at different wavelengths and thus be interconnected in large neural networks. Here, we experimentally demonstrate and numerically simulate the spiking dynamics of a laser neuron fabricated in a photonic integrated circuit. Our spiking laser neuron is shown to perform coincidence detection with nanosecond time resolution, and we observe refractory periods in the order of 0.1 ns. We propose a method to implement XOR classification using our laser neurons, and simulations of the resultant dynamics indicate robust tolerance to timing jitter.
AB - Spiking neural networks enable efficient information processing in real-time. Excitable lasers can exhibit ultrafast spiking dynamics, and when preceded by a photodetector in an O/E/O link, can process optical spikes at different wavelengths and thus be interconnected in large neural networks. Here, we experimentally demonstrate and numerically simulate the spiking dynamics of a laser neuron fabricated in a photonic integrated circuit. Our spiking laser neuron is shown to perform coincidence detection with nanosecond time resolution, and we observe refractory periods in the order of 0.1 ns. We propose a method to implement XOR classification using our laser neurons, and simulations of the resultant dynamics indicate robust tolerance to timing jitter.
KW - Excitable lasers
KW - IndexTerms-Neuromorphicphotonics
KW - Photonic neural networks
KW - Photonicintegratedcircuits
KW - Spiking neural networks
UR - http://www.scopus.com/inward/record.url?scp=85105827879&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85105827879&partnerID=8YFLogxK
U2 - 10.1109/JSTQE.2019.2927582
DO - 10.1109/JSTQE.2019.2927582
M3 - Article
AN - SCOPUS:85105827879
SN - 1077-260X
VL - 26
JO - IEEE Journal of Selected Topics in Quantum Electronics
JF - IEEE Journal of Selected Topics in Quantum Electronics
IS - 1
M1 - 8760358
ER -