Strong CWoLa: binary classification without background simulation

Today's article comes from the journal of Machine Learning Science and Technology. The authors are Klein et al., from the University of Geneva, in Switzerland. In this paper, they explore a new approach to CWoLa: Classification Without Labels. Instead of relying on two unlabeled mixtures with different proportions, they anchor one side of the problem with labeled signal from simulation, and the other with real experimental data.

DOI: 10.1088/2632-2153/ae47b7

Book
Book

Members Only

You must be an active Journal Club member to access this content. If you're already a member, click the blue button to login. If you're not a member yet, click the sign-up button to get started.

Login to My Account Sign Up