BriefGPT.xyz
Oct, 2019
神经网络行为验证：电力系统应用的形式保证
Verification of Neural Network Behaviour: Formal Guarantees for Power System Applications
HTML
PDF
Andreas Venzke, Spyros Chatzivasileiadis
TL;DR
本文提出一种基于混合整数线性规划的框架，首次在电力系统应用中验证神经网络行为，能够确定神经网络分类为安全或不安全的输入范围，并且能够系统地识别对抗性示例，从而提高神经网络在电力系统中的鲁棒性和可靠性。
Abstract
This paper presents for the first time, to our knowledge, a framework for verifying neural network behavior in
power systems
applications. Up to this moment,
neural networks
have been applied in
→