BriefGPT.xyz
Jan, 2018
面向安全关键深度神经网络的可扩展验证
Toward Scalable Verification for Safety-Critical Deep Networks
HTML
PDF
Lindsey Kuper, Guy Katz, Justin Gottschlich, Kyle Julian, Clark Barrett...
TL;DR
本篇论文介绍了在安全重要应用领域中使用深度神经网络的问题，针对其可靠性和安全性的担忧，提出了采用形式化验证来保证其运行符合预期，并通过两个方向，即设计可扩展性的验证技术和识别可验证的深度学习系统的设计选择来缓解这一挑战。
Abstract
The increasing use of
deep neural networks
for
safety-critical applications
, such as autonomous driving and flight control, raises concerns about their safety and reliability.
→