SG separation challenge » History » Version 7

« Previous - Version 7/37 (diff) - Next » - Current version
Eli Rykoff, 11/25/2013 09:29 AM

SG separation challenge

Now that several people are testing their own approaches:

  • Cut-based with DESDM info (Eli, Diego, Nacho, Ryan...).
  • Multi-class (Maayane)
  • Random Forests (Ryan)
  • Boosted Decision Trees (Nacho)
  • Alternative Neural Network with probabilistic output (Chris Bonnett).
  • others...

I think the time is right and the codes are mature to launch a specific SG separation challenge, mimicking the successful photo-z WG exercise.

We have to establish:

  • The training/validation/testing sample (COSMOS, others).
  • Only stars and galaxies? What about QSOs, image artifacts?
  • The metrics (Fixed cut, Fixed purity, Fixed Efficiency, ROC -- see example below).
  • SVA1 systematics: correlations with depth, Galactic latitude, seeing, etc.
  • Who/how to run it.
  • The schedule.