BriefGPT.xyz
Jul, 2020
使用集成网络和噪声层实现鲁棒深度学习
Towards Robust Deep Learning with Ensemble Networks and Noisy Layers
HTML
PDF
Yuting Liang, Reza Samavi
TL;DR
本篇论文提出了一种深度学习方法,可以在图像分类类型的网络中保护并提高其鲁棒性,同时实现了准确性和鲁棒性的平衡,通过实验验证了该方法的有效性和鲁棒性保障。
Abstract
In this paper we provide an approach for
deep learning
that protects against
adversarial examples
in
image classification
-type networks. T
→