Curvature-based Comparison of Two Neural Networks

2018 24th International Conference on Pattern Recognition (ICPR)(2018)

引用 10|浏览82
暂无评分
摘要
In this paper we show the similarities and differences of two deep neural networks by comparing the manifolds composed of activation vectors in each fully connected layer of them. The main contribution of this paper includes 1) a new data generating algorithm which is crucial for determining the dimension of manifolds; 2) a systematic strategy to compare manifolds. Especially, we take Riemann curvature and sectional curvature as part of criterion, which can reflect the intrinsic geometric properties of manifolds. Some interesting results and phenomenon are given, which help in specifying the similarities and differences between the features extracted by two networks and demystifying the intrinsic mechanism of deep neural networks.
更多
查看译文
关键词
curvature-based comparison,deep neural networks,activation vectors,data generating algorithm,systematic strategy,sectional curvature,intrinsic geometric properties
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