Methods for Interpreting and Understanding Deep Neural Networks
Digital Signal Processing(2017)
摘要
This paper provides an entry point to the problem of interpreting a deep neural network model and explaining its predictions. It is based on a tutorial given at ICASSP 2017. It introduces some recently proposed techniques of interpretation, along with theory, tricks and recommendations, to make most efficient use of these techniques on real data. It also discusses a number of practical applications.
更多查看译文
关键词
Deep neural networks,Activation maximization,Sensitivity analysis,Taylor decomposition,Layer-wise relevance propagation
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络