TY - JOUR
T1 - Machine Learning with Neuromorphic Photonics
AU - De Lima, Thomas Ferreira
AU - Peng, Hsuan Tung
AU - Tait, Alexander N.
AU - Nahmias, Mitchell A.
AU - Miller, Heidi B.
AU - Shastri, Bhavin J.
AU - Prucnal, Paul R.
N1 - Funding Information:
Manuscript received November 7, 2018; revised December 16, 2018 and January 30, 2019; accepted February 25, 2019. Date of publication March 7, 2019; date of current version March 27, 2019. This work was supported in part by the National Science Foundation (NSF) Enhancing Access to the Radio Spectrum (EARS) program (Award 1642991). The work of B.J. Shastri and H.B. Miller was supported by the Natural Sciences and Engineering Research Council of Canada (NSERC). (Corresponding author: Thomas Ferreira de Lima.) T. F. de Lima, H.-T. Peng, M. A. Nahmias, and P. R. Prucnal are with the Department of Electrical Engineering, Princeton University, Princeton, NJ 08544 USA (e-mail:, tlima@princeton.edu; hpeng@princeton.edu; mnahmias@princeton.edu; prucnal@princeton.edu).
Publisher Copyright:
© 1983-2012 IEEE.
PY - 2019/3/1
Y1 - 2019/3/1
N2 - Neuromorphic photonics has experienced a recent surge of interest over the last few years, promising orders of magnitude improvements in both speed and energy efficiency over digital electronics. This paper provides a tutorial overview of neuromorphic photonic systems and their application to optimization and machine learning problems. We discuss the physical advantages of photonic processing systems, and we describe underlying device models that allow practical systems to be constructed. We also describe several real-world applications for control and deep learning inference. Finally, we discuss scalability in the context of designing a full-scale neuromorphic photonic processing system, considering aspects such as signal integrity, noise, and hardware fabrication platforms. The paper is intended for a wide audience and teaches how theory, research, and device concepts from neuromorphic photonics could be applied in practical machine learning systems.
AB - Neuromorphic photonics has experienced a recent surge of interest over the last few years, promising orders of magnitude improvements in both speed and energy efficiency over digital electronics. This paper provides a tutorial overview of neuromorphic photonic systems and their application to optimization and machine learning problems. We discuss the physical advantages of photonic processing systems, and we describe underlying device models that allow practical systems to be constructed. We also describe several real-world applications for control and deep learning inference. Finally, we discuss scalability in the context of designing a full-scale neuromorphic photonic processing system, considering aspects such as signal integrity, noise, and hardware fabrication platforms. The paper is intended for a wide audience and teaches how theory, research, and device concepts from neuromorphic photonics could be applied in practical machine learning systems.
KW - Deep learning
KW - machine learning
KW - more-than-Moore computing
KW - neuromorphic photonics
KW - nonlinear programming
KW - optimization
KW - photonic hardware accelerator
KW - photonic integrated circuits
KW - photonic neural networks
KW - silicon photonics
KW - wavelength-division multiplexing (WDM)
UR - http://www.scopus.com/inward/record.url?scp=85063796668&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85063796668&partnerID=8YFLogxK
U2 - 10.1109/JLT.2019.2903474
DO - 10.1109/JLT.2019.2903474
M3 - Article
AN - SCOPUS:85063796668
SN - 0733-8724
VL - 37
SP - 1515
EP - 1534
JO - Journal of Lightwave Technology
JF - Journal of Lightwave Technology
IS - 5
M1 - 8662590
ER -