Analyzing and Improving Representations with the Soft Nearest Neighbor Loss

arXiv: Machine Learning, 2019.

Cited by: 16|Bibtex|Views127|Links
EI

Abstract:

We explore and expand the $textit{Soft Nearest Neighbor Loss}$ to measure the $textit{entanglement}$ of class manifolds in representation space: i.e., how close pairs of points from the same class are relative to pairs of points from different classes. We demonstrate several use cases of the loss. As an analytical tool, it provides insigh...More

Code:

Data:

Your rating :
0

 

Tags
Comments