Detecting Deep Neural Network Defects with Data Flow Analysis
arxiv(2021)
摘要
Deep neural networks (DNNs) are shown to be promising solutions in many challenging artificial intelligence tasks, including object recognition, natural language processing, and even unmanned driving. A DNN model, generally based on statistical summarization of in-house training data, aims to predict correct output given an input encountered in the wild. In general, 100% precision is therefore impossible due to its probabilistic nature. For DNN practitioners, it is very hard, if not impossible, to figure out whether the low precision of a DNN model is an inevitable result, or caused by defects such as bad network design or improper training process. This paper aims at addressing this challenging problem. We approach with a careful categorization of the root causes of low precision. We find that the internal data flow footprints of a DNN model can provide insights to locate the root cause effectively. We then develop a tool, namely, DeepMorph (DNN Tomography) to analyze the root cause, which can instantly guide a DNN developer to improve the model. Case studies on four popular datasets show the effectiveness of DeepMorph.
更多查看译文
关键词
data flow analysis,artificial intelligence,object recognition,natural language processing,unmanned driving,statistical summarization,in-house training data,probabilistic nature,network design,internal data flow footprints,DNN developer,DNN tomography,deep neural network defects detection,DeepMorph
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