Distilling a Neural Network Into a Soft Decision TreeEI

摘要

Deep neural networks have proved to be a very effective way to perform classification tasks. They excel when the input data is high dimensional, the relationship between the input and the output is complicated, and the number of labeled training examples is large. But it is hard to explain why a learned network makes a particular classification decision on a particular test case. This is due to their reliance on distributed hierarchical representations. If we could take the knowledge acquired by the neural net and express the same kno...更多
个人信息

 

您的评分 :

2017.

被引用次数20|引用|2
标签
作者
评论