Issues

 / 

2023

 / 

December

  

Reviews of topical problems


Photonics approaches to the implementation of neuromorphic computing

, , , , , , ,  
Lomonosov Moscow State University, Faculty of Physics, Leninskie Gory 1 build. 2, Moscow, 119991, Russian Federation

Physical limitations on the operation speed of electronic devices has motivated the search for alternative ways to process information. The past few years have seen the development of neuromorphic photonics — a branch of photonics where the physics of optical and optoelectronic devices is combined with mathematical algorithms of artificial neural networks. Such a symbiosis allows certain classes of computation problems, including some involving artificial intelligence, to be solved with greater speed and higher energy efficiency than can be reached with electronic devices based on the von Neumann architecture. We review optical analog computing, photonic neural networks, and methods of matrix multiplication by optical means, and discuss the advantages and disadvantages of existing approaches.

Fulltext pdf (1.6 MB)
Fulltext is also available at DOI: 10.3367/UFNe.2023.07.039505
Keywords: neuromorphic photonics, artificial intelligence, machine learning, reservoir computing, matrix—vector multiplication, photonic computing, neural networks, optical coprocessor, photonic tensor computing, optical Fourier transform, integrated photonics, Mach—Zehnder interferometer, ring resonators, waveguides
PACS: 07.05.Mh, 42.79.Hp (all)
DOI: 10.3367/UFNe.2023.07.039505
URL: https://ufn.ru/en/articles/2023/12/b/
001172931200006
2-s2.0-85183055912
2023PhyU...66.1211M
Citation: Musorin A I, Shorokhov A S, Chezhegov A A, Baluyan T G, Safronov K R, Chetvertukhin A V, Grunin A A, Fedyanin A A "Photonics approaches to the implementation of neuromorphic computing" Phys. Usp. 66 1211–1223 (2023)
BibTexBibNote ® (generic)BibNote ® (RIS)MedlineRefWorks

Received: 8th, November 2022, revised: 4th, July 2023, 5th, July 2023

:   ,   ,   ,   ,   ,   ,   ,    « » 193 1284–1297 (2023); DOI: 10.3367/UFNr.2023.07.039505

© 1918–2024 Uspekhi Fizicheskikh Nauk
Email: ufn@ufn.ru Editorial office contacts About the journal Terms and conditions