VO-Neural is the natural evolution of the Astroneural project which was started in 1994 with the aim to implement a suite of neural tools for data mining in astronomical massive data sets. At a difference with its ancestor, which was implemented under Matlab, VO-Neural is written in C++, object oriented, and it is specifically tailored to work in distributed computing architectures. We discuss the current status of implementation of VO-Neural, present an application to the classification of Active Galactic Nuclei, and outline the ongoing work to improve the functionalities of the package.
The VO-Neural project:. recent developments and some applications / Brescia, M.; Cavuoti, S.; D'Angelo, G.; D'Abrusco, R.; Deniskina, N.; Garofalo, M.; Laurino, O.; Longo, G.; Nocella, A.; Skordovski, B.. - In: MEMORIE DELLA SOCIETÀ ASTRONOMICA ITALIANA. - ISSN 1824-016X. - 80:(2009), pp. 565-571. (Intervento presentato al convegno EURO-VO DATA CENTRE ALLIANCE WORKSHOP: THEORY IN THE VIRTUAL OBSERVATORY - GRID AND VIRTUAL OBSERVATORY tenutosi a Garching, Germania nel Aprile 2008).
The VO-Neural project:. recent developments and some applications
Brescia, M.
Conceptualization
;Longo, G.;
2009
Abstract
VO-Neural is the natural evolution of the Astroneural project which was started in 1994 with the aim to implement a suite of neural tools for data mining in astronomical massive data sets. At a difference with its ancestor, which was implemented under Matlab, VO-Neural is written in C++, object oriented, and it is specifically tailored to work in distributed computing architectures. We discuss the current status of implementation of VO-Neural, present an application to the classification of Active Galactic Nuclei, and outline the ongoing work to improve the functionalities of the package.| File | Dimensione | Formato | |
|---|---|---|---|
|
41-Brescia-565.pdf
accesso aperto
Tipologia:
Versione Editoriale (PDF)
Licenza:
Dominio pubblico
Dimensione
463.59 kB
Formato
Adobe PDF
|
463.59 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
