用于高速图像处理的光子脉冲卷积神经网络*注:在Xplore中不捕获字幕，不应使用

2021 IEEE Photonics Society Summer Topicals Meeting Series (SUM) Pub Date : 2021-07-01 DOI:10.1109/SUM48717.2021.9505862

M. Skontranis, G. Sarantoglou, A. Bogris, C. Mesaritakis

{"title":"用于高速图像处理的光子脉冲卷积神经网络*注:在Xplore中不捕获字幕，不应使用","authors":"M. Skontranis, G. Sarantoglou, A. Bogris, C. Mesaritakis","doi":"10.1109/SUM48717.2021.9505862","DOIUrl":null,"url":null,"abstract":"A multi-layer photonic spiking convolutional neural network is presented, based on miniaturized VCSELs, targeting image classification. Spatial information is encoded using a time multiplexing scheme providing a radical reduction of physical neuron-count. Hardware-friendliness is enhanced by exploiting unsupervised spike-timing dependent plasticity.","PeriodicalId":359978,"journal":{"name":"2021 IEEE Photonics Society Summer Topicals Meeting Series (SUM)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Photonic Spiking Convolutional Neural Networks for High-Speed Image Processing *Note: Sub-titles are not captured in Xplore and should not be used\",\"authors\":\"M. Skontranis, G. Sarantoglou, A. Bogris, C. Mesaritakis\",\"doi\":\"10.1109/SUM48717.2021.9505862\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"A multi-layer photonic spiking convolutional neural network is presented, based on miniaturized VCSELs, targeting image classification. Spatial information is encoded using a time multiplexing scheme providing a radical reduction of physical neuron-count. Hardware-friendliness is enhanced by exploiting unsupervised spike-timing dependent plasticity.\",\"PeriodicalId\":359978,\"journal\":{\"name\":\"2021 IEEE Photonics Society Summer Topicals Meeting Series (SUM)\",\"volume\":\"32 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-07-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2021 IEEE Photonics Society Summer Topicals Meeting Series (SUM)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/SUM48717.2021.9505862\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 IEEE Photonics Society Summer Topicals Meeting Series (SUM)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SUM48717.2021.9505862","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

提出了一种基于小型化vcsel的多层光子脉冲卷积神经网络，用于图像分类。空间信息使用时间复用方案进行编码，从而大大减少了物理神经元计数。硬件友好性通过利用无监督的峰值时间依赖的可塑性得到增强。

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

Photonic Spiking Convolutional Neural Networks for High-Speed Image Processing *Note: Sub-titles are not captured in Xplore and should not be used

A multi-layer photonic spiking convolutional neural network is presented, based on miniaturized VCSELs, targeting image classification. Spatial information is encoded using a time multiplexing scheme providing a radical reduction of physical neuron-count. Hardware-friendliness is enhanced by exploiting unsupervised spike-timing dependent plasticity.

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

2021 IEEE Photonics Society Summer Topicals Meeting Series (SUM)

自引率

0.00%

发文量