Leveraging Sparse Linear Layers for Debuggable Deep Networks
INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 139(2021)
摘要
We show how fitting sparse linear models over learned deep feature representations can lead to more debuggable deep networks. These networks remain highly accurate while also being more amenable to human interpretation, as we demonstrate quantitatively via numerical and human experiments. We further illustrate how the resulting sparse explanations can help to identify spurious correlations, explain misclassifications, and diagnose model biases in vision and language tasks.(1)
更多查看译文
关键词
sparse linear layers,networks,deep
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