光电神经网络系统的训练

Imaging and Applied Optics Congress 2022 (3D, AOA, COSI, ISA, pcAOP) Pub Date : 1900-01-01 DOI:10.1364/3d.2022.jw2a.18

Zibo Hu, Russell L. T. Schwartz, Maria Solyanik-Gorgone, V. Sorger

{"title":"光电神经网络系统的训练","authors":"Zibo Hu, Russell L. T. Schwartz, Maria Solyanik-Gorgone, V. Sorger","doi":"10.1364/3d.2022.jw2a.18","DOIUrl":null,"url":null,"abstract":"Neural Networks have been proven successful in many fields. Optical systems show potential for high-speed low-power Neural Networks. However, optical alignment is very demanding for wavelength-level coherent systems. Here we present Training-on-System methods to learn the imperfectly aligned system to increase the system’s performance.","PeriodicalId":286361,"journal":{"name":"Imaging and Applied Optics Congress 2022 (3D, AOA, COSI, ISA, pcAOP)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"10","resultStr":"{\"title\":\"Training on System for Opto-Electrical Neural Network\",\"authors\":\"Zibo Hu, Russell L. T. Schwartz, Maria Solyanik-Gorgone, V. Sorger\",\"doi\":\"10.1364/3d.2022.jw2a.18\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Neural Networks have been proven successful in many fields. Optical systems show potential for high-speed low-power Neural Networks. However, optical alignment is very demanding for wavelength-level coherent systems. Here we present Training-on-System methods to learn the imperfectly aligned system to increase the system’s performance.\",\"PeriodicalId\":286361,\"journal\":{\"name\":\"Imaging and Applied Optics Congress 2022 (3D, AOA, COSI, ISA, pcAOP)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1900-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"10\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Imaging and Applied Optics Congress 2022 (3D, AOA, COSI, ISA, pcAOP)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1364/3d.2022.jw2a.18\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Imaging and Applied Optics Congress 2022 (3D, AOA, COSI, ISA, pcAOP)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1364/3d.2022.jw2a.18","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 10

摘要

神经网络在许多领域已经被证明是成功的。光学系统显示出高速低功耗神经网络的潜力。然而，对于波长级相干系统，光学对准的要求非常高。在这里，我们提出了系统上训练的方法来学习不完全对齐系统，以提高系统的性能。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Training on System for Opto-Electrical Neural Network

Neural Networks have been proven successful in many fields. Optical systems show potential for high-speed low-power Neural Networks. However, optical alignment is very demanding for wavelength-level coherent systems. Here we present Training-on-System methods to learn the imperfectly aligned system to increase the system’s performance.

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

Imaging and Applied Optics Congress 2022 (3D, AOA, COSI, ISA, pcAOP)

自引率

0.00%

发文量