优化边缘计算的深度学习应用

S. Niar
{"title":"优化边缘计算的深度学习应用","authors":"S. Niar","doi":"10.1109/EDiS57230.2022.9996494","DOIUrl":null,"url":null,"abstract":"eep learning (DL) models such as convolutional neural networks (CNN) are being deployed to solve various computer vision and natural language processing tasks at the edge. It is a challenge to find the right DL architecture that simultaneously meets the accuracy, power and performance budgets of such resource-constrained devices. Hardware-aware Neural Architecture Search (HW-NAS) has recently gained steam by automating the design of efficient DL models for a variety of target hardware platform.However, such algorithms require excessive computational resources. Thousands of GPU days are required to evaluate and explore modern DL architecture search space. In this talk I will present state-of-the-art approaches that are based on two components: a) Surrogate models to predict quickly architecture accuracy and hardware performances to speed up HW-NAS, b) Efficient search algorithm that explores only promising hardware and software regions of the search space.","PeriodicalId":288133,"journal":{"name":"2022 3rd International Conference on Embedded & Distributed Systems (EDiS)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Optimizing Deep Learning Application for Edge Computing\",\"authors\":\"S. Niar\",\"doi\":\"10.1109/EDiS57230.2022.9996494\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"eep learning (DL) models such as convolutional neural networks (CNN) are being deployed to solve various computer vision and natural language processing tasks at the edge. It is a challenge to find the right DL architecture that simultaneously meets the accuracy, power and performance budgets of such resource-constrained devices. Hardware-aware Neural Architecture Search (HW-NAS) has recently gained steam by automating the design of efficient DL models for a variety of target hardware platform.However, such algorithms require excessive computational resources. Thousands of GPU days are required to evaluate and explore modern DL architecture search space. In this talk I will present state-of-the-art approaches that are based on two components: a) Surrogate models to predict quickly architecture accuracy and hardware performances to speed up HW-NAS, b) Efficient search algorithm that explores only promising hardware and software regions of the search space.\",\"PeriodicalId\":288133,\"journal\":{\"name\":\"2022 3rd International Conference on Embedded & Distributed Systems (EDiS)\",\"volume\":\"6 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-11-02\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2022 3rd International Conference on Embedded & Distributed Systems (EDiS)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/EDiS57230.2022.9996494\",\"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 3rd International Conference on Embedded & Distributed Systems (EDiS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/EDiS57230.2022.9996494","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(CNN)等深度学习(DL)模型正被用于解决边缘的各种计算机视觉和自然语言处理任务。找到合适的深度学习架构,同时满足这种资源受限设备的精度、功耗和性能预算是一个挑战。硬件感知神经架构搜索(HW-NAS)最近通过自动化设计各种目标硬件平台的高效深度学习模型而获得了发展。然而,这种算法需要大量的计算资源。评估和探索现代DL架构搜索空间需要数千个GPU天。在这次演讲中,我将介绍基于两个组件的最先进的方法:a)代理模型,用于快速预测架构准确性和硬件性能,以加速HW-NAS; b)高效的搜索算法,仅探索搜索空间中有前途的硬件和软件区域。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Optimizing Deep Learning Application for Edge Computing
eep learning (DL) models such as convolutional neural networks (CNN) are being deployed to solve various computer vision and natural language processing tasks at the edge. It is a challenge to find the right DL architecture that simultaneously meets the accuracy, power and performance budgets of such resource-constrained devices. Hardware-aware Neural Architecture Search (HW-NAS) has recently gained steam by automating the design of efficient DL models for a variety of target hardware platform.However, such algorithms require excessive computational resources. Thousands of GPU days are required to evaluate and explore modern DL architecture search space. In this talk I will present state-of-the-art approaches that are based on two components: a) Surrogate models to predict quickly architecture accuracy and hardware performances to speed up HW-NAS, b) Efficient search algorithm that explores only promising hardware and software regions of the search space.
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
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信