Probabilistic learning for pulsar classification

  title={Probabilistic learning for pulsar classification},
  author={Sambatra Hagatiana Andrianomena},
  journal={Journal of Cosmology and Astroparticle Physics},
  • S. Andrianomena
  • Published 11 May 2022
  • Computer Science
  • Journal of Cosmology and Astroparticle Physics
In this work, we explore the possibility of using probabilistic learning to identify pulsar candidates. We make use of Deep Gaussian Process (DGP) and Deep Kernel Learning (DKL). Trained on a balanced training set in order to avoid the effect of class imbalance, the performance of the models, achieving relatively high probability of differentiating the positive class from the negative one (roc-auc ∼ 0.98), is very promising overall. We estimate the predictive entropy of each model predictions…