嵌入式深度神经网络:“所有东西的成本和没有价值”

2016 IEEE Hot Chips 28 Symposium (HCS) Pub Date : 2016-08-01 DOI:10.1109/HOTCHIPS.2016.7936219

D. Moloney

{"title":"嵌入式深度神经网络:“所有东西的成本和没有价值”","authors":"D. Moloney","doi":"10.1109/HOTCHIPS.2016.7936219","DOIUrl":null,"url":null,"abstract":"•Deep Learning for Embedded is all about Inference •Standard Networks are designed to achieve high-accuracy •Embedded implementation on architectures such as Movidius VPU can achieve significant performance results at the network edge •Next challenge is to further optimise networks to maximise performance per Watt","PeriodicalId":363333,"journal":{"name":"2016 IEEE Hot Chips 28 Symposium (HCS)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"8","resultStr":"{\"title\":\"Embedded deep neural networks: “The cost of everything and the value of nothing”\",\"authors\":\"D. Moloney\",\"doi\":\"10.1109/HOTCHIPS.2016.7936219\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"•Deep Learning for Embedded is all about Inference •Standard Networks are designed to achieve high-accuracy •Embedded implementation on architectures such as Movidius VPU can achieve significant performance results at the network edge •Next challenge is to further optimise networks to maximise performance per Watt\",\"PeriodicalId\":363333,\"journal\":{\"name\":\"2016 IEEE Hot Chips 28 Symposium (HCS)\",\"volume\":\"9 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2016-08-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"8\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2016 IEEE Hot Chips 28 Symposium (HCS)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/HOTCHIPS.2016.7936219\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2016 IEEE Hot Chips 28 Symposium (HCS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/HOTCHIPS.2016.7936219","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 8

摘要

•嵌入式深度学习是关于推理的•标准网络旨在实现高精度•在诸如Movidius VPU等架构上的嵌入式实现可以在网络边缘实现显着的性能结果•下一个挑战是进一步优化网络以最大限度地提高每瓦特的性能

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

Embedded deep neural networks: “The cost of everything and the value of nothing”

•Deep Learning for Embedded is all about Inference •Standard Networks are designed to achieve high-accuracy •Embedded implementation on architectures such as Movidius VPU can achieve significant performance results at the network edge •Next challenge is to further optimise networks to maximise performance per Watt

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

2016 IEEE Hot Chips 28 Symposium (HCS)

自引率

0.00%

发文量