Hostname: page-component-7b7567c8c-8p88z Total loading time: 0 Render date: 2026-11-19T09:40:36.539Z Has data issue: false hasContentIssue false

Deep-Learning the Time Domain

Published online by Cambridge University Press:  29 August 2019

A. Mahabal
Affiliation:
Department of Astronomy, California Institute of Technology, Pasadena, CA, USA email: aam@astro.caltech.eduCenter for Data Driven Discovery, California Institute of Technology, Pasadena, CA, USA
K. Sheth
Affiliation:
Indian Institute of Technology Gandhinagar, India,
F. Gieseke
Affiliation:
Department of Computer Science, University of Copenhagen, Denmark
A. Drake
Affiliation:
Center for Data Driven Discovery, California Institute of Technology, Pasadena, CA, USA
G. Djorgovski
Affiliation:
Department of Astronomy, California Institute of Technology, Pasadena, CA, USA email: aam@astro.caltech.eduCenter for Data Driven Discovery, California Institute of Technology, Pasadena, CA, USA
M. J. Graham
Affiliation:
Department of Astronomy, California Institute of Technology, Pasadena, CA, USA email: aam@astro.caltech.eduCenter for Data Driven Discovery, California Institute of Technology, Pasadena, CA, USA
Rights & Permissions [Opens in a new window]

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the 'Save PDF' action button.

“Deep learning” is finding more and more applications everywhere, and astronomy is not an exception. This talk described the application of convolutional neural networks to time-domain astronomy, specifically to light-curves of sources. The work that is discussed is based on a published paper to which reference can be made for more detail. The talk finished with a note cautioning new practitioners about the pitfalls lurking in out-of-the-box use of deep-learning techniques.