Corpus ID: 203593479

Active Anomaly Detection for time-domain discoveries

@article{Ishida2019ActiveAD,
  title={Active Anomaly Detection for time-domain discoveries},
  author={E. Ishida and M. V. Kornilov and K. Malanchev and M. Pruzhinskaya and A. Volnova and V. S. Korolev and F. Mondon and S. Sreejith and Anastasia Malancheva and S. Das},
  journal={ArXiv},
  year={2019},
  volume={abs/1909.13260}
}

E. Ishida, M. V. Kornilov, +7 authors S. Das

Published 2019

Physics, Computer Science, Mathematics

ArXiv

We present the first application of adaptive machine learning to the identification of anomalies in a data set of non-periodic astronomical light curves. The method follows an active learning strategy where highly informative objects are selected to be labelled. This new information is subsequently used to improve the machine learning model, allowing its accuracy to evolve with the addition of every new classification. For the case of anomaly detection, the algorithm aims to maximize the number… CONTINUE READING

View PDF on arXiv

Save to Library

Create Alert

Cite

Launch Research Feed