Network Analysis for Explanation
arXiv (Cornell University)(2018)
摘要
Safety critical systems strongly require the quality aspects of artificial intelligence including explainability. In this paper, we analyzed a trained network to extract features which mainly contribute the inference. Based on the analysis, we developed a simple solution to generate explanations of the inference processes.
更多查看译文
关键词
Computational Research,Data Provenance,Semantic Web Services,Scientific Workflows
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要