Synthetic vs Real: Deep Learning on Controlled Noise

Huang Di
Huang Di
Yang Weilong
Yang Weilong
Cited by: 0|Bibtex|Views17
Other Links: arxiv.org

Abstract:

Performing controlled experiments on noisy data is essential in thoroughly understanding deep learning across a spectrum of noise levels. Due to the lack of suitable datasets, previous research have only examined deep learning on controlled synthetic noise, and real-world noise has never been systematically studied in a controlled setti...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments