VO-supported Active Deep Learning as a New Methodology for the Discovery of Objects of Interest in Big Surveys

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985815%3A_____%2F20%3A00562032" target="_blank" >RIV/67985815:_____/20:00562032 - isvavai.cz</a>

Výsledek na webu

<a href="http://www.aspbooks.org/publications/527/163.pdf" target="_blank" >http://www.aspbooks.org/publications/527/163.pdf</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

VO-supported Active Deep Learning as a New Methodology for the Discovery of Objects of Interest in Big Surveys

Popis výsledku v původním jazyce

Deep neural networks have been proved a very successful method of supervised learning in several research fields. To perform well, they require a massive amount of labelled data, which is challenging to get from most astronomical surveys. To overcome this limitation, we have developed a novel active deep learning method. It is based on an iterative training of a deep network followed by relabelling of a small sample according to a qualified decision of an oracle (usually a human expert). To maximise the scientific return, the oracle brings to the decision the domain knowledge not limited only to the data learned by the network. By combining some external resources to extract the key information by an expert in a field, much more relevant labels are assigned. Setup of an active deep learning platform thus requires incorporation of a Virtual Observatory (VO) client infrastructure as an integral part of a machine learning experiment, which is quite different from current practices. As proof of concept, we demonstrate the efficiency of our method for discovery of new emission-line stars in a multimillion spectra archive of the LAMOST DR2 survey.

Název v anglickém jazyce

VO-supported Active Deep Learning as a New Methodology for the Discovery of Objects of Interest in Big Surveys

Popis výsledku anglicky

Deep neural networks have been proved a very successful method of supervised learning in several research fields. To perform well, they require a massive amount of labelled data, which is challenging to get from most astronomical surveys. To overcome this limitation, we have developed a novel active deep learning method. It is based on an iterative training of a deep network followed by relabelling of a small sample according to a qualified decision of an oracle (usually a human expert). To maximise the scientific return, the oracle brings to the decision the domain knowledge not limited only to the data learned by the network. By combining some external resources to extract the key information by an expert in a field, much more relevant labels are assigned. Setup of an active deep learning platform thus requires incorporation of a Virtual Observatory (VO) client infrastructure as an integral part of a machine learning experiment, which is quite different from current practices. As proof of concept, we demonstrate the efficiency of our method for discovery of new emission-line stars in a multimillion spectra archive of the LAMOST DR2 survey.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10308 - Astronomy (including astrophysics,space science)

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2020

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Astronomical Data Analysis Software and System XXIX

ISBN

978-1-58381-942-5

ISSN

—

e-ISSN

—

Počet stran výsledku

4

Strana od-do

163-166

Název nakladatele

Astronomical Society of the Pacific

Místo vydání

San Francisco

Místo konání akce

Groningen

Datum konání akce

6. 10. 2019

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—