ReLU Neural Networks, Polyhedral Decompositions, and Persistent Homolog

06/30/2023
by   Yajing Liu, et al.
0

A ReLU neural network leads to a finite polyhedral decomposition of input space and a corresponding finite dual graph. We show that while this dual graph is a coarse quantization of input space, it is sufficiently robust that it can be combined with persistent homology to detect homological signals of manifolds in the input space from samples. This property holds for a variety of networks trained for a wide range of purposes that have nothing to do with this topological application. We found this feature to be surprising and interesting; we hope it will also be useful.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset