基于垂直腔面发射激光器的ghz速率神经形态光子脉冲神经网络

2022 IEEE Photonics Conference (IPC) Pub Date : 2022-11-01 DOI:10.1109/IPC53466.2022.9975722

Dafydd Owen-Newns, M. Hejda, Antonio Hurtado, J. Robertson

{"title":"基于垂直腔面发射激光器的ghz速率神经形态光子脉冲神经网络","authors":"Dafydd Owen-Newns, M. Hejda, Antonio Hurtado, J. Robertson","doi":"10.1109/IPC53466.2022.9975722","DOIUrl":null,"url":null,"abstract":"We report a high-speed (GHz rate) and hardware-friendly Neuromorphic Photonic Spiking Neural Network (pSNN) architecture formed by up to >1000 spiking nodes and built with a single off-the-shelf telecom Vertical-Cavity Surface Emitting Laser (VCSEL). We demonstrate the successful application of the proposed pSNN architecture to a complex nonlinear classification task, running at sub-nanosecond speeds per spike directly in the optical domain.","PeriodicalId":202839,"journal":{"name":"2022 IEEE Photonics Conference (IPC)","volume":"93 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"GHz-Rate Neuromorphic Photonic Spiking Neural Network with a Vertical-Cavity Surface-Emitting Laser\",\"authors\":\"Dafydd Owen-Newns, M. Hejda, Antonio Hurtado, J. Robertson\",\"doi\":\"10.1109/IPC53466.2022.9975722\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We report a high-speed (GHz rate) and hardware-friendly Neuromorphic Photonic Spiking Neural Network (pSNN) architecture formed by up to >1000 spiking nodes and built with a single off-the-shelf telecom Vertical-Cavity Surface Emitting Laser (VCSEL). We demonstrate the successful application of the proposed pSNN architecture to a complex nonlinear classification task, running at sub-nanosecond speeds per spike directly in the optical domain.\",\"PeriodicalId\":202839,\"journal\":{\"name\":\"2022 IEEE Photonics Conference (IPC)\",\"volume\":\"93 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2022 IEEE Photonics Conference (IPC)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/IPC53466.2022.9975722\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 IEEE Photonics Conference (IPC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IPC53466.2022.9975722","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

我们报告了一种高速(GHz速率)和硬件友好的神经形态光子峰值神经网络(pSNN)架构，该架构由多达1000个峰值节点组成，并使用单个现成的电信垂直腔表面发射激光器(VCSEL)构建。我们演示了pSNN架构在复杂非线性分类任务中的成功应用，该架构直接在光域中以亚纳秒的速度运行。

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

GHz-Rate Neuromorphic Photonic Spiking Neural Network with a Vertical-Cavity Surface-Emitting Laser

We report a high-speed (GHz rate) and hardware-friendly Neuromorphic Photonic Spiking Neural Network (pSNN) architecture formed by up to >1000 spiking nodes and built with a single off-the-shelf telecom Vertical-Cavity Surface Emitting Laser (VCSEL). We demonstrate the successful application of the proposed pSNN architecture to a complex nonlinear classification task, running at sub-nanosecond speeds per spike directly in the optical domain.

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

2022 IEEE Photonics Conference (IPC)

自引率

0.00%

发文量