Photonic Hopfield neural network for the Ising problem
Optics Express · 19.06.2023 · 31 (13) · 21340
DOI: 10.1364/oe.491554 ↗Kurz gefasst
Fachartikel in der Zeitschrift Optics Express, online erschienen am 09.06.2023. Verfasst von ZeYang Fan und 4 weiteren Autor:innen. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 28 Literaturangaben. Gefördert von: State Key Laboratory of Information Photonics and Optical Communications, National Natural Science Foundation of China.
Abstract (Originalsprache)
The Ising problem, a vital combinatorial optimization problem in various fields, is hard to solve by traditional Von Neumann computing architecture on a large scale. Thus, lots of application-specific physical architectures are reported, including quantum-based, electronics-based, and optical-based platforms. A Hopfield neural network combined with a simulated annealing algorithm is considered one of the effective approaches but is still limited by large resource consumption. Here, we propose to accelerate the Hopfield network on a photonic integrated circuit composed of the arrays of Mach–Zehnder interferometer. Our proposed Photonic Hopfield Neural Network (PHNN), utilizing the massively parallel operations and integrated circuit with ultrafast iteration rate, converges to a stable ground state solution with high probability. The average success probabilities for the MaxCut problem with a problem size of 100 and the Spin-glass problem with a problem size of 60 can both reach more than 80%. Moreover, our proposed architecture is inherently robust to the noise induced by the imperfect characteristics of components on chip.
Förderung
- State Key Laboratory of Information Photonics and Optical Communications
- National Natural Science Foundation of China
Zitieren
APA
Fan, Z., Lin, J., Dai, J., Zhang, T., & Xu, K. (2023). Photonic Hopfield neural network for the Ising problem. Optics Express, 31(13), 21340. https://doi.org/10.1364/oe.491554
Vancouver
Fan Z, Lin J, Dai J, Zhang T, Xu K. Photonic Hopfield neural network for the Ising problem. Optics Express. 2023;31(13):21340. doi:10.1364/oe.491554
BibTeX
@article{Fan2023,
author = {Fan, ZeYang and Lin, JunMin and Dai, Jian and Zhang, Tian and Xu, Kun},
title = {Photonic Hopfield neural network for the Ising problem},
journal = {Optics Express},
year = {2023},
volume = {31},
number = {13},
pages = {21340},
doi = {10.1364/oe.491554}
}
EUVIMED