层选择逼近对cnn可靠性和性能的影响

2020 IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems (DFT) Pub Date : 2020-10-19 DOI:10.1109/DFT50435.2020.9250821

R. L. R. Junior, P. Rech

{"title":"层选择逼近对cnn可靠性和性能的影响","authors":"R. L. R. Junior, P. Rech","doi":"10.1109/DFT50435.2020.9250821","DOIUrl":null,"url":null,"abstract":"In this paper, we evaluate the impact on reliability and performance of the selective approximation of Convolutional Neural Networks (CNNs) layers on NVIDIA mixed-precision architectures. We found that, even without affecting accuracy, the approximation from single to half precision of each layer has a different impact on both performance and output error.","PeriodicalId":340119,"journal":{"name":"2020 IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems (DFT)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Impact of Layers Selective Approximation on CNNs Reliability and Performance\",\"authors\":\"R. L. R. Junior, P. Rech\",\"doi\":\"10.1109/DFT50435.2020.9250821\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this paper, we evaluate the impact on reliability and performance of the selective approximation of Convolutional Neural Networks (CNNs) layers on NVIDIA mixed-precision architectures. We found that, even without affecting accuracy, the approximation from single to half precision of each layer has a different impact on both performance and output error.\",\"PeriodicalId\":340119,\"journal\":{\"name\":\"2020 IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems (DFT)\",\"volume\":\"21 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-10-19\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems (DFT)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/DFT50435.2020.9250821\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems (DFT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/DFT50435.2020.9250821","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 1

摘要

在本文中，我们评估了在NVIDIA混合精度架构上卷积神经网络(cnn)层的选择性逼近对可靠性和性能的影响。我们发现，即使不影响精度，每层从单精度到半精度的近似对性能和输出误差都有不同的影响。

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

Impact of Layers Selective Approximation on CNNs Reliability and Performance

In this paper, we evaluate the impact on reliability and performance of the selective approximation of Convolutional Neural Networks (CNNs) layers on NVIDIA mixed-precision architectures. We found that, even without affecting accuracy, the approximation from single to half precision of each layer has a different impact on both performance and output error.

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

2020 IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems (DFT)

自引率

0.00%

发文量