Atat: astronomical transformer for time series and tabular data

HIGHLIGHTS

• What: The authors compare ATAT against the current ALeRCE classifier balanced hierarchical random forest (BHRF) trained on human-engineered features derived from light curves and metadata. For the rest of the paper, the authors call these models ATAT variants since different input combinations can be used.
• Who: Cabrera-Vives G. and collaborators from the Department of Computer Science, Universidad de Concepción, Concepción, European Southern, Karl-Schwarzschild-Strasse, Garching bei München, Germany have published the research work: ATAT: Astronomical Transformer for time series and Tabular data, in the Journal: (JOURNAL) of September/28 . . .
  

   

  

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

  Thanks :)

  Username or E-mail:

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