Deep-Learning the Time Domain

A. Mahabal, Kinal Sheth, Fabian Gieseke, A. J. Drake, G. Djorgovski, M. J. GrahamProceedings of the International Astronomical Union 2017 · DOI

Abstract

Abstract “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.
BibTeX
@inproceedings{mahabal2017deep,
  author = {A. Mahabal and Kinal Sheth and Fabian Gieseke and A. J. Drake and G. Djorgovski and M. J. Graham},
  title = {{Deep-Learning the Time Domain}},
  booktitle = {Proceedings of the International Astronomical Union},
  year = {2017},
  doi = {10.1017/s1743921318002491},
}
Figure