基于干涉仪的光子电路分类器在不使用非线性激活函数的情况下，对知名虹膜数据集显示了>90%的准确率

2020 Optical Fiber Communications Conference and Exhibition (OFC) Pub Date : 2020-03-01 DOI:10.1364/ofc.2020.w3a.6

G. Cong, N. Yamamoto, Takashi Inoue, Y. Maegami, M. Ohno, M. Okano, S. Namiki, K. Yamada

{"title":"基于干涉仪的光子电路分类器在不使用非线性激活函数的情况下，对知名虹膜数据集显示了>90%的准确率","authors":"G. Cong, N. Yamamoto, Takashi Inoue, Y. Maegami, M. Ohno, M. Okano, S. Namiki, K. Yamada","doi":"10.1364/ofc.2020.w3a.6","DOIUrl":null,"url":null,"abstract":"We demonstrate that interferometer-based photonic circuits can perform classification by only phase control even without activation functions, which can classify well-known Iris dataset with >90% accuracy in simulation, showing simple photonic implementation for machine learning.","PeriodicalId":173355,"journal":{"name":"2020 Optical Fiber Communications Conference and Exhibition (OFC)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Interferometer-Based Photonic Circuit Classifier Showing >90% Accuracy for Well-Known Iris Dataset without Utilizing Nonlinear Activation Function\",\"authors\":\"G. Cong, N. Yamamoto, Takashi Inoue, Y. Maegami, M. Ohno, M. Okano, S. Namiki, K. Yamada\",\"doi\":\"10.1364/ofc.2020.w3a.6\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We demonstrate that interferometer-based photonic circuits can perform classification by only phase control even without activation functions, which can classify well-known Iris dataset with >90% accuracy in simulation, showing simple photonic implementation for machine learning.\",\"PeriodicalId\":173355,\"journal\":{\"name\":\"2020 Optical Fiber Communications Conference and Exhibition (OFC)\",\"volume\":\"3 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-03-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 Optical Fiber Communications Conference and Exhibition (OFC)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1364/ofc.2020.w3a.6\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 Optical Fiber Communications Conference and Exhibition (OFC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1364/ofc.2020.w3a.6","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 1

摘要

我们证明了基于干涉仪的光子电路可以在没有激活函数的情况下仅通过相位控制进行分类，在仿真中对知名的虹膜数据集进行分类，准确率达到bb0 - 90%，展示了简单的光子实现机器学习。

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

Interferometer-Based Photonic Circuit Classifier Showing >90% Accuracy for Well-Known Iris Dataset without Utilizing Nonlinear Activation Function

We demonstrate that interferometer-based photonic circuits can perform classification by only phase control even without activation functions, which can classify well-known Iris dataset with >90% accuracy in simulation, showing simple photonic implementation for machine learning.

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

2020 Optical Fiber Communications Conference and Exhibition (OFC)

自引率

0.00%

发文量