当前位置:
X-MOL 学术
›
IEEE Des. Test
›
论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Hardware/Algorithm Codesign for Adversarially Robust Deep Learning
IEEE Design & Test ( IF 2 ) Pub Date : 2021-03-02 , DOI: 10.1109/mdat.2021.3063344 Mojan Javaheripi 1 , Mohammad Samragh 1 , Bita Darvish Rouhani 2 , Tara Javidi 1 , Farinaz Koushanfar 1
IEEE Design & Test ( IF 2 ) Pub Date : 2021-03-02 , DOI: 10.1109/mdat.2021.3063344 Mojan Javaheripi 1 , Mohammad Samragh 1 , Bita Darvish Rouhani 2 , Tara Javidi 1 , Farinaz Koushanfar 1
Affiliation
This article describes DeepFense, a framework to make deep learning models automatically and efficiently realizable on constrained devices.
中文翻译:
对抗性强健的深度学习的硬件/算法协同设计
本文介绍了DeepFense,该框架可在受限设备上自动且高效地实现深度学习模型。
更新日期:2021-03-02
中文翻译:
对抗性强健的深度学习的硬件/算法协同设计
本文介绍了DeepFense,该框架可在受限设备上自动且高效地实现深度学习模型。