NobleBlocks
Public

Example Perplexity

Published in arXiv (Cornell University) • Mar 16, 2022
NobleIDNI1P76W34R68S91
Authors:
Nevin L. Zhang
,
Weiyan Xie
,
Zhi Lin

Abstract

Some examples are easier for humans to classify than others. The same should be true for deep neural networks (DNNs). We use the term example perplexity to refer to the level of difficulty of classifying an example. In this paper, we propose a method to measure the perplexity of an example and inves...

Finding related papers...

Discussions

(0)

No comments yet

Be the first to share your thoughts!