What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation

NIPS 2020, 2020.

Cited by: 8|Views12
EI
Weibo:
Our work demonstrates that accuracy of a learning algorithm on long tailed data distributions depends on its ability to memorize the labels

Abstract:

Deep learning algorithms are well-known to have a propensity for fitting the training data very well and often fit even outliers and mislabeled data points. Such fitting requires memorization of training data labels, a phenomenon that has attracted significant research interest but has not been given a compelling explanation so far. A r...More

Code:

Data:

0
Your rating :
0

 

Tags
Comments