用于卷积神经网络的硅光子JTC的设计、封装和测试

2023 IEEE Silicon Photonics Conference (SiPhotonics) Pub Date : 2023-04-01 DOI:10.1109/SiPhotonics55903.2023.10141918

N. Peserico, Hangbo Yang, Xiaoxuan Ma, Shurui Li, M. Hosseini, J. George, Puneet Gupta, C. Wong, V. Sorger

{"title":"用于卷积神经网络的硅光子JTC的设计、封装和测试","authors":"N. Peserico, Hangbo Yang, Xiaoxuan Ma, Shurui Li, M. Hosseini, J. George, Puneet Gupta, C. Wong, V. Sorger","doi":"10.1109/SiPhotonics55903.2023.10141918","DOIUrl":null,"url":null,"abstract":"Convolution Neural Networks are one of the most powerful types of Neural Networks. However, the 2D convolution task is computationally heavy. Here, we present an integrated Silicon Photonic chip that can perform the Joint Transfer Convolution, using the properties of light propagation.","PeriodicalId":105710,"journal":{"name":"2023 IEEE Silicon Photonics Conference (SiPhotonics)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Design, Packaging, and Testing of Silicon Photonics JTC for Convolution Neural Network\",\"authors\":\"N. Peserico, Hangbo Yang, Xiaoxuan Ma, Shurui Li, M. Hosseini, J. George, Puneet Gupta, C. Wong, V. Sorger\",\"doi\":\"10.1109/SiPhotonics55903.2023.10141918\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Convolution Neural Networks are one of the most powerful types of Neural Networks. However, the 2D convolution task is computationally heavy. Here, we present an integrated Silicon Photonic chip that can perform the Joint Transfer Convolution, using the properties of light propagation.\",\"PeriodicalId\":105710,\"journal\":{\"name\":\"2023 IEEE Silicon Photonics Conference (SiPhotonics)\",\"volume\":\"16 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-04-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2023 IEEE Silicon Photonics Conference (SiPhotonics)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/SiPhotonics55903.2023.10141918\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 IEEE Silicon Photonics Conference (SiPhotonics)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SiPhotonics55903.2023.10141918","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

摘要

卷积神经网络是神经网络中最强大的类型之一。然而，二维卷积任务的计算量很大。在这里，我们提出了一个集成的硅光子芯片，可以执行联合传递卷积，利用光的传播特性。

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

Design, Packaging, and Testing of Silicon Photonics JTC for Convolution Neural Network

Convolution Neural Networks are one of the most powerful types of Neural Networks. However, the 2D convolution task is computationally heavy. Here, we present an integrated Silicon Photonic chip that can perform the Joint Transfer Convolution, using the properties of light propagation.

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

2023 IEEE Silicon Photonics Conference (SiPhotonics)

自引率

0.00%

发文量