Towards an automated data cleaning with deep learning in cresst

HIGHLIGHTS

• who: G. Angloher et al. from the Max-Planck-Institut fu00fcr, Mu00fcnchen, Germany Faculty of Mathematics, Physics and Informatics, Comenius University, Bratislava, Slovakia have published the paper: Towards an automated data cleaning with deep learning in CRESST, in the Journal: Eur. Phys. J. Plus
• what: The authors show on an exemplary detector that about half of the wrongly predicted events are in fact wrongly labeled events and a large share of the remaining ones have a context-dependent ground truth. The authors explore the synergies with the PCA method from Ref in Sect 4.3 . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or Email

  Password

  Remember me

  Lost your password?

  If you don't have an account, you can create one here.