Sonia Buckley, Alexander Tait, Adam McCaughan, Bhavin Shastri
Neuromorphic systems promise to solve certain problems faster and with higher energy efficiency than traditional computing, by using the physics of the devices themselves for information processing. While initial results in photonic neuromorphic hardware are very promising, such hardware requires programming or ''training'' that is often power-hungry and time-consuming. In this article, we examine the online learning paradigm, where the machinery for training is built deeply into the hardware itself. We argue that some form of online learning will be necessary if photonic neuromorphic hardware is to achieve its true potential.
, Tait, A.
, McCaughan, A.
and Shastri, B.
Photonic Online Learning: A Perspective, Nanophotonics, [online], https://doi.org/10.1515/nanoph-2022-0553, https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=935486
(Accessed December 8, 2023)