深度光子水库计算递归网络

IF 8.4 1区 物理与天体物理 Q1 OPTICS
Optica Pub Date : 2023-12-19 DOI:10.1364/optica.506635
Yi-Wei Shen, Rui-Qian Li, Guan-Ting Liu, Jingyi Yu, Xuming He, Lilin Yi, and Cheng Wang
{"title":"深度光子水库计算递归网络","authors":"Yi-Wei Shen, Rui-Qian Li, Guan-Ting Liu, Jingyi Yu, Xuming He, Lilin Yi, and Cheng Wang","doi":"10.1364/optica.506635","DOIUrl":null,"url":null,"abstract":"Deep neural networks usually process information through multiple hidden layers. However, most hardware reservoir computing recurrent networks only have one hidden reservoir layer, which significantly limits the capability of solving practical complex tasks. Here we show a deep photonic reservoir computing (PRC) architecture, which is constructed by cascading injection-locked semiconductor lasers. In particular, the connection between successive hidden layers is all optical, without any optical-electrical conversion or analog-digital conversion. The proof of concept PRC consisting of 4 hidden layers and a total of 320 interconnected neurons (80 neurons per layer) is demonstrated in experiment. The deep PRC is applied in solving the real-world problem of signal equalization in an optical fiber communication system. It is found that the deep PRC exhibits strong capability in compensating for the nonlinear impairment of optical fibers.","PeriodicalId":19515,"journal":{"name":"Optica","volume":"12 1","pages":""},"PeriodicalIF":8.4000,"publicationDate":"2023-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Deep photonic reservoir computing recurrent network\",\"authors\":\"Yi-Wei Shen, Rui-Qian Li, Guan-Ting Liu, Jingyi Yu, Xuming He, Lilin Yi, and Cheng Wang\",\"doi\":\"10.1364/optica.506635\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Deep neural networks usually process information through multiple hidden layers. However, most hardware reservoir computing recurrent networks only have one hidden reservoir layer, which significantly limits the capability of solving practical complex tasks. Here we show a deep photonic reservoir computing (PRC) architecture, which is constructed by cascading injection-locked semiconductor lasers. In particular, the connection between successive hidden layers is all optical, without any optical-electrical conversion or analog-digital conversion. The proof of concept PRC consisting of 4 hidden layers and a total of 320 interconnected neurons (80 neurons per layer) is demonstrated in experiment. The deep PRC is applied in solving the real-world problem of signal equalization in an optical fiber communication system. It is found that the deep PRC exhibits strong capability in compensating for the nonlinear impairment of optical fibers.\",\"PeriodicalId\":19515,\"journal\":{\"name\":\"Optica\",\"volume\":\"12 1\",\"pages\":\"\"},\"PeriodicalIF\":8.4000,\"publicationDate\":\"2023-12-19\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Optica\",\"FirstCategoryId\":\"101\",\"ListUrlMain\":\"https://doi.org/10.1364/optica.506635\",\"RegionNum\":1,\"RegionCategory\":\"物理与天体物理\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"OPTICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Optica","FirstCategoryId":"101","ListUrlMain":"https://doi.org/10.1364/optica.506635","RegionNum":1,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"OPTICS","Score":null,"Total":0}
引用次数: 0

摘要

深度神经网络通常通过多个隐藏层处理信息。然而,大多数硬件储层计算递归网络只有一个隐藏储层,这大大限制了解决实际复杂任务的能力。在这里,我们展示了一种深度光子存储计算(PRC)架构,该架构由级联注入锁定半导体激光器构建而成。特别是,连续隐藏层之间的连接全部是光连接,不需要任何光电转换或模数转换。实验演示了由 4 个隐藏层和总共 320 个相互连接的神经元(每层 80 个神经元)组成的概念验证 PRC。深度 PRC 被应用于解决光纤通信系统中信号均衡的实际问题。实验发现,深度 PRC 在补偿光纤的非线性损伤方面表现出很强的能力。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Deep photonic reservoir computing recurrent network
Deep neural networks usually process information through multiple hidden layers. However, most hardware reservoir computing recurrent networks only have one hidden reservoir layer, which significantly limits the capability of solving practical complex tasks. Here we show a deep photonic reservoir computing (PRC) architecture, which is constructed by cascading injection-locked semiconductor lasers. In particular, the connection between successive hidden layers is all optical, without any optical-electrical conversion or analog-digital conversion. The proof of concept PRC consisting of 4 hidden layers and a total of 320 interconnected neurons (80 neurons per layer) is demonstrated in experiment. The deep PRC is applied in solving the real-world problem of signal equalization in an optical fiber communication system. It is found that the deep PRC exhibits strong capability in compensating for the nonlinear impairment of optical fibers.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Optica
Optica OPTICS-
CiteScore
19.70
自引率
2.90%
发文量
191
审稿时长
2 months
期刊介绍: Optica is an open access, online-only journal published monthly by Optica Publishing Group. It is dedicated to the rapid dissemination of high-impact peer-reviewed research in the field of optics and photonics. The journal provides a forum for theoretical or experimental, fundamental or applied research to be swiftly accessed by the international community. Optica is abstracted and indexed in Chemical Abstracts Service, Current Contents/Physical, Chemical & Earth Sciences, and Science Citation Index Expanded.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信