Only institutional emails for accounts, please. Pour demander un compte, indiquez une adresse mail institutionnelle.
Bienvenue sur le catalogue des événements organisés par le LAL
Pour accéder aux catégories Direction et CHS, consulter les news.

RAMP 03 Astrophyiscs

présidé par Balázs Kégl (LAL), Akin Kazakci (MINES ParisTech), Alexandre Gramfort (Telecom ParisTech, CNRS), Djalel Benbouzid (LAL, Université Paris-Sud), Loïc Estève (INRIA)
vendredi 10 avril 2015 de à (Europe/Paris)
à Proto204
200 rue André Ampère 91 440 Bures-sur-Yvette
Description

This RAMP will be on Astrophysics, more precisely, on classification of variable stars from their light curves (luminosity vs time profiles), brought to you by Marc Monier (LAL), Gilles Faÿ (Centrale-Supelec), and your regular coaches.

The event will take place at Proto204, a 10 minute walk from either the Orsay-Ville or the Bur-sur-Yvette RER B stations.

Supporting material:

Some general guidelines. 

Your primary goal is to have a high score in the "contributivity" column. One way to achieve it is to submit a strong model, high in the "score" column, but we appreciate especially those models which do not have top scores but are sufficiently different from the rest of the models to achieve high score in the "contributivity" column.

Our best feature extractor is based on Gaussian Process. It smoothes the light curves, aligns them so the period starts at the minimum luminosity, normalizes the amplitude so the response is bounded between 0 and 1, and bins the smooth curve into ten bins. It also adds the amplitude and the lenght scale (smoothness) as feature. Here are some plots that show how it works.

The performance gain is significant, so you might want to work on this model if you decide to improve the feature extractor. The bad news is that it is quite slow: it takes eight minutes to train. So, if you submit anything based on this feature extractor, please do extensive preliminary tests on your computer or on your private VM, and do not submit more than once per 30 minutes to an hour. A general rule is that you should not resubmit until your previous model has not yet been trained (it shows up in the "New models" table.)

Some strategies you can employ:

  1. Take a good classifier and work on the feature extractor or vice verse.
  2. Take a good classifier or feature extractor and optimize its hyperparameters using smac or hyperopt. See the course material for help.
  3. Take two good submissions and combine the feature extractor and the classifier.
Participants Naveen Kumar Aranganathan; Christian Arnault; asma atamna; Rémi Bardenet; Alexandre Beelen; Giannis Bekoulis; nacim belkhir; Hervé Bertin; michael blot; Alexandre Boucaud; DIEM BUI; Antoine Bureau; Anastase Charantonis; mehdi cherti; Bogdan-Ionut Cirstea; François-David Collin; Isabelle Guyon; Farhang Habibi; Jean Lafond; Delphine Le; Lionel LIMERY; Kevin Lourd; Odalric-Ambrym Maillard; Gaetan Marceau Caron; Pierre-Yves Massé; Basile mayeur; Sourava Prasad Mishra; Rafael Morales; Aurelie MUTSCHLER; Anais Möller; anaelle pain; Adrien PAIN; Tien PHAN; Antoine Pérus; Maria Rossi; Amir Sani; Thomas Schmitt; mehdi sebbar; Sana Tfaili; Eric TUON; liying wei; Izzet Burak Yildiz
Go to day
  • vendredi 10 avril 2015
    • 09:00 - 09:30 Welcome of participants & Coffee
    • 09:30 - 10:00 Introduction talk
    • 10:00 - 12:00 Data munging and machine learning session 1
    • 12:00 - 13:30 Buffet & presentation of the first results
    • 13:30 - 15:00 Data munging and machine learning session 2
    • 15:00 - 15:30 Café
    • 15:30 - 17:00 Data munging and machine learning session 3
    • 17:00 - 18:00 Debriefing and closing