Neural networks behave as hash encoders: An empirical study

Shiye Lei
Shiye Lei
Jianmin Ji
Jianmin Ji
Cited by: 0|Views9

Abstract:

The input space of a neural network with ReLU-like activations is partitioned into multiple linear regions, each corresponding to a specific activation pattern of the included ReLU-like activations. We demonstrate that this partition exhibits the following encoding properties across a variety of deep learning models: (1) {\it determinis...More

Code:

Data:

Full Text
Bibtex
Your rating :
0

 

Tags
Comments