pith. sign in

arxiv: 1904.01399 · v1 · pith:MDJMZKVZnew · submitted 2019-04-02 · 💻 cs.LG · stat.ML

On Geometric Structure of Activation Spaces in Neural Networks

classification 💻 cs.LG stat.ML
keywords networksneuralactivationgeometricspacesstructurealgorithmclassification
0
0 comments X
read the original abstract

In this paper, we investigate the geometric structure of activation spaces of fully connected layers in neural networks and then show applications of this study. We propose an efficient approximation algorithm to characterize the convex hull of massive points in high dimensional space. Based on this new algorithm, four common geometric properties shared by the activation spaces are concluded, which gives a rather clear description of the activation spaces. We then propose an alternative classification method grounding on the geometric structure description, which works better than neural networks alone. Surprisingly, this data classification method can be an indicator of overfitting in neural networks. We believe our work reveals several critical intrinsic properties of modern neural networks and further gives a new metric for evaluating them.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.