Please use this identifier to cite or link to this item: http://hdl.handle.net/10497/22920
Full metadata record
DC FieldValueLanguage
dc.contributor.authorZhang, Huien
dc.contributor.authorThompson, Jayneen
dc.contributor.authorGu, Mileen
dc.contributor.authorJiang, Xu Dongen
dc.contributor.authorCai, Hongen
dc.contributor.authorLiu, Patricia Yangen
dc.contributor.authorShi, Yuzhien
dc.contributor.authorZhang, Yien
dc.contributor.authorMuhammad Faeyz Karimen
dc.contributor.authorLo, Guo Qiangen
dc.contributor.authorLuo, Xianshuen
dc.contributor.authorDong, Binen
dc.contributor.authorKwek, Leong Chuanen
dc.contributor.authorLiu, Ai Qunen
dc.date.accessioned2021-05-17T06:52:06Z-
dc.date.available2021-05-17T06:52:06Z-
dc.date.issued2021-
dc.identifier.citationZhang, H., Thompson, J., Gu, M., Jiang, X. D., Cai, H., Liu, P. Y., Shi, Y., Zhang, Y., Muhammad Faeyz Karim, Lo, G. Q., Luo, X., Dong, B., Kwek, L.C. & Liu, A. Q. (2021). Efficient on-chip training of optical neural networks using genetic algorithm. ACS Photonics. Advance online publication. https://doi.org/10.1021/acsphotonics.1c00035en
dc.identifier.issn2330-4022-
dc.identifier.urihttp://hdl.handle.net/10497/22920-
dc.descriptionThis is the final draft, after peer-review, of a manuscript published in ACS Photonics. The published version is available online at https://doi.org/10.1021/acsphotonics.1c00035en
dc.description.abstractRecent advances in silicon photonic chips have made huge progress in optical computing owing to their flexibility in the reconfiguration of various tasks. Its deployment of neural networks serves as an alternative for mitigating the rapidly increased demand for computing resources in electronic platforms. However, it remains a formidable challenge to train the online programmable optical neural networks efficiently, being restricted by the difficulty in obtaining gradient information on a physical device when executing a gradient descent algorithm. Here, we experimentally demonstrate an efficient, physics-agnostic, and closed-loop protocol for training optical neural networks on chip. A gradient-free algorithm, that is, the genetic algorithm, is adopted. The protocol is on-chip implementable, physical agnostic (no need to rely on characterization and offline modeling), and gradient-free. The protocol works for various types of chip structures and is especially helpful to those that cannot be analytically decomposed and characterized. We confirm its viability using several practical tasks, including the crossbar switch and the Iris classification. Finally, by comparing our physics-agonistic and gradient-free method to the off-chip and gradient-based training methods, we demonstrate the robustness of our system to perturbations such as imperfect phase implementation and photodetection noise. Optical processors with gradient-free genetic algorithms have broad application potentials in pattern recognition, reinforcement learning, quantum computing, and realistic applications (such as facial recognition, natural language processing, and autonomous vehicles).en
dc.language.isoenen
dc.subjectOptical neural networksen
dc.subjectOn-chip trainingen
dc.subjectGradient-freeen
dc.subjectGenetic algorithmen
dc.subjectDeep learningen
dc.subjectOptical computingen
dc.titleEfficient on-chip training of optical neural networks using genetic algorithmen
dc.typeArticleen
dc.identifier.doi10.1021/acsphotonics.1c00035-
local.message.claim2021-12-22T11:17:05.052+0800|||rp00041|||submit_approve|||dc_contributor_author|||None*
item.openairecristypehttp://purl.org/coar/resource_type/c_18cf-
item.fulltextWith file-
item.languageiso639-1en-
item.openairetypeArticle-
item.grantfulltextOpen-
item.cerifentitytypePublications-
Appears in Collections:Journal Articles
Files in This Item:
File Description SizeFormat 
ACSP-2021-c00035.pdf515.96 kBAdobe PDFThumbnail
View/Open
Show simple item record

SCOPUSTM   
Citations

22
checked on Nov 25, 2022

WEB OF SCIENCETM
Citations

7
checked on Nov 17, 2022

Page view(s)

81
checked on Nov 24, 2022

Download(s) 50

75
checked on Nov 24, 2022

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.