Les stages
Non linear matter power spectrum and machine learning
Non linear matter power spectrum and machine learning
Candidature avant le
10/04/2020
Durée
6 mois
Poursuite possible en thèse
oui
Contact
Pettorino Valeria
+33 1 69 08 42 75
Autre lien
Résumé/Summary
This internship is meant to use and compare different machine learning methods in order
to check which one better performs in estimating the matter power spectrum in the non-linear regime.
to check which one better performs in estimating the matter power spectrum in the non-linear regime.
This internship is meant to use and compare different machine learning methods in order
to check which one better performs in estimating the matter power spectrum in the non-linear regime.
to check which one better performs in estimating the matter power spectrum in the non-linear regime.
Sujet détaillé/Full description
Work builds on preliminary results
and codes developed within the CosmoStat group.
The internship will take place within the research group CosmoStat, within the Astrophysics
Department (DAp) under the supervision of Valeria Pettorino, Santiago Casas, and Jean-Luc
Starck.
and codes developed within the CosmoStat group.
The internship will take place within the research group CosmoStat, within the Astrophysics
Department (DAp) under the supervision of Valeria Pettorino, Santiago Casas, and Jean-Luc
Starck.
The internship will take place within the research group CosmoStat, within the Astrophysics
Department (DAp) under the supervision of Valeria Pettorino, Santiago Casas, and Jean-Luc
Starck.
Department (DAp) under the supervision of Valeria Pettorino, Santiago Casas, and Jean-Luc
Starck.
Mots clés/Keywords
Machine Learning
