Gaussian-Based Runtime Detection of Out-of-distribution Inputs for Neural Networks

RUNTIME VERIFICATION (RV 2021)(2021)

引用 4|浏览7
暂无评分
摘要
In this short paper, we introduce a simple approach for run-time monitoring of deep neural networks and show how to use it for out-of-distribution detection. The approach is based on inferring Gaussian models of some of the neurons and layers. Despite its simplicity, it performs better than recently introduced approaches based on interval abstractions which are traditionally used in verification.
更多
查看译文
关键词
runtime detection,neural networks,inputs,gaussian-based,out-of-distribution
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络