Advances in Physics: X | |
Prospects and applications of photonic neural networks | |
Daniel Brunner1  Alexander N. Tait2  Paul R. Prucnal3  Chaoran Huang3  Thomas Ferreira de Lima3  Bhavin J. Shastri4  Bicky A. Marquez4  Jiahui Wang5  Shanhui Fan5  Volker J. Sorger6  Mario Miscuglio6  Mohammed Al-Qadasi7  Sudip Shekhar7  Lutz Lampe7  Avilash Mukherjee7  Mitchell Nichols7  Lukas Chrostowski7  Mable P. Fok8  | |
[1] Institut FEMTO-ST, Université Bourgogne-Franche-Comté CNRS UMR;National Institute of Standards and Technology;Princeton University;Queen’s University;Stanford University;The George Washington University;The University of British Columbia;University of Georgia; | |
关键词: photonic neural networks; neuromorphic photonics; silicon photonics; neuromorphic computing; machine learning; artificial intelligence; | |
DOI : 10.1080/23746149.2021.1981155 | |
来源: DOAJ |
【 摘 要 】
Neural networks have enabled applications in artificial intelligence through machine learning, and neuromorphic computing. Software implementations of neural networks on conventional computers that have separate memory and processor (and that operate sequentially) are limited in speed and energy efficiency. Neuromorphic engineering aims to build processors in which hardware mimics neurons and synapses in the brain for distributed and parallel processing. Neuromorphic engineering enabled by photonics (optical physics) can offer sub-nanosecond latencies and high bandwidth with low energies to extend the domain of artificial intelligence and neuromorphic computing applications to machine learning acceleration, nonlinear programming, intelligent signal processing, etc. Photonic neural networks have been demonstrated on integrated platforms and free-space optics depending on the class of applications being targeted. Here, we discuss the prospects and demonstrated applications of these photonic neural networks.
【 授权许可】
Unknown