Machine learning methods have become crucial to many aspects of astrophysics and cosmology. We focus on the evaluation of photometric redshifts as a template case of classification/regression problem in astronomical data mining. We discuss the general aspects of the problem and some recent work which tries to solve the issues posed by optimal feature selection, missing data and by the evaluation of probability distribution functions.
The astronomical data deluge: The template case of photometric redshifts / Longo, G.; Brescia, M.; Cavuoti, S.. - 2022:(2018), pp. 27-29. (Intervento presentato al convegno 19th International Conference on Data Analytics and Management in Data Intensive Domains, DAMDID/RCDL 2017 tenutosi a Lomonosov Moscow State University at the Department of Computational Mathematics and Cybernetics, Russia nel 2017).
The astronomical data deluge: The template case of photometric redshifts
Longo, G.
;Brescia, M.
;
2018
Abstract
Machine learning methods have become crucial to many aspects of astrophysics and cosmology. We focus on the evaluation of photometric redshifts as a template case of classification/regression problem in astronomical data mining. We discuss the general aspects of the problem and some recent work which tries to solve the issues posed by optimal feature selection, missing data and by the evaluation of probability distribution functions.| File | Dimensione | Formato | |
|---|---|---|---|
|
xx1-Longo-CEUR.pdf
solo utenti autorizzati
Tipologia:
Versione Editoriale (PDF)
Licenza:
Copyright dell'editore
Dimensione
480.95 kB
Formato
Adobe PDF
|
480.95 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
