.png){kind=icon}
.png){kind=icon}
Return
Strong CWoLa: binary classification without background simulation
.png){kind=icon}
OA
AI
DOI：10.1088/2632-2153/ae47b7.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Supervised deep learning methods have been successful in the field of high energy physics, the trend within the field being to move away from high level reconstructed variables to lower level, higher dimensional features. Supervised methods require labeled data, which is typically provided by a simulator. As the number of features increases, simulation accuracy decreases, leading to greater domain shift between training and testing data when using lower-level features. This work demonstrates that the classification without labels paradigm can be used to remove the need for background simulation when training supervised classifiers. This can result in classifiers with higher performance on real data than those trained on simulated data.
Keywords:
deep learning
high energy physics
unsupervised learning
domain shift
classification without labels
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
M
IF:
0
Papers:
116
Citations:
0