TY - JOUR
T1 - Noise analysis of photonic modulator neurons
AU - de Lima, Thomas Ferreira
AU - Tait, Alexander N.
AU - Saeidi, Hooman
AU - Nahmias, Mitchell A.
AU - Peng, Hsuan Tung
AU - Abbaslou, Siamak
AU - Shastri, Bhavin J.
AU - Prucnal, Paul R.
N1 - Funding Information:
Manuscript received April 16, 2019; revised July 17, 2019; accepted July 22, 2019. Date of publication July 31, 2019; date of current version August 13, 2019. This work was supported in part by the National Science Foundation (NSF) Enhancing Access to the Radio Spectrum program under EARS Award 1642991 and in part by Energy-Efficient Computing: from Devices to Architectures program under E2CDA Award 1740262. The work of B. J. Shastri was supported by the Natural Sciences and Engineering Research Council of Canada. (Corresponding author: Thomas Ferreira de Lima.) T. F. de Lima, H. Saeidi, M. A. Nahmias, H.-T. Peng, S. Abbaslou, and P. R. Prucnal are with the Department of Electrical Engineering, Princeton University, Princeton, NJ 08544 USA (e-mail: tlima@princeton.edu; hsaeidi@ princeton.edu; mnahmias@princeton.edu; hpeng@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 - Neuromorphic photonics relies on efficiently emulating analog neural networks at high speeds. Prior work showed that transducing signals from the optical to the electrical domain and back with transimpedance gain was an efficient approach to implementing analog photonic neurons and scalable networks. Here, we examine modulator-based photonic neuron circuits with passive and active transimpedance gains, with special attention to the sources of noise propagation. We find that a modulator nonlinear transfer function can suppress noise, which is necessary to avoid noise propagation in hardware neural networks. In addition, while efficient modulators can reduce power for an individual neuron, signal-to-noise ratios must be traded off with power consumption at a system level. Active transimpedance amplifiers may help relax this tradeoff for conventional p-n junction silicon photonic modulators, but a passive transimpedance circuit is sufficient when very efficient modulators (i.e., low C and low V-pi) are employed.
AB - Neuromorphic photonics relies on efficiently emulating analog neural networks at high speeds. Prior work showed that transducing signals from the optical to the electrical domain and back with transimpedance gain was an efficient approach to implementing analog photonic neurons and scalable networks. Here, we examine modulator-based photonic neuron circuits with passive and active transimpedance gains, with special attention to the sources of noise propagation. We find that a modulator nonlinear transfer function can suppress noise, which is necessary to avoid noise propagation in hardware neural networks. In addition, while efficient modulators can reduce power for an individual neuron, signal-to-noise ratios must be traded off with power consumption at a system level. Active transimpedance amplifiers may help relax this tradeoff for conventional p-n junction silicon photonic modulators, but a passive transimpedance circuit is sufficient when very efficient modulators (i.e., low C and low V-pi) are employed.
KW - Analog links
KW - Neural networks
KW - Neuromorphic computing
KW - Neuromorphic photonics
UR - http://www.scopus.com/inward/record.url?scp=85092468143&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85092468143&partnerID=8YFLogxK
U2 - 10.1109/JSTQE.2019.2931252
DO - 10.1109/JSTQE.2019.2931252
M3 - Article
AN - SCOPUS:85092468143
SN - 1077-260X
VL - 26
JO - IEEE Journal on Selected Topics in Quantum Electronics
JF - IEEE Journal on Selected Topics in Quantum Electronics
IS - 1
M1 - 8782580
ER -