Probabilistic learning for pulsar classification

Simple item page
dc.contributor.authorAndrianomena, Sambatra
dc.date.accessioned2022-10-18T08:02:11Z
dc.date.available2022-10-18T08:02:11Z
dc.date.issued2022
dc.description.abstractIn 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 and find that DKL is more confident than DGP in its predictions and provides better uncertainty calibration. Upon investigating the effect of training with imbalanced dataset on the models, results show that each model performance decreases with an increasing number of the majority class in the training set. Interestingly, with a number of negative class 10× that of positive class, the models still provide reasonably well calibrated uncertainty, i.e. an expected Uncertainty Calibration Error (UCE) less than 6%.en_US
dc.identifier.citationAndrianomena, S. (2022). Probabilistic learning for pulsar classification. Journal of Cosmology and Astroparticle Physics, (10), 016. https://doi.org/10.1088/1475-7516/2022/10/016en_US
dc.identifier.issn1475-7516
dc.identifier.urihttps://doi.org/10.1088/1475-7516/2022/10/016
dc.identifier.urihttp://hdl.handle.net/10566/8061
dc.language.isoenen_US
dc.publisherIOP Publishingen_US
dc.subjectAstrophysicsen_US
dc.subjectAstronomyen_US
dc.subjectCosmologyen_US
dc.subjectRadio pulsarsen_US
dc.titleProbabilistic learning for pulsar classificationen_US
dc.typeArticleen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
andrianomena_probabilistic learning for pulsar classification_2022.pdf
Size:
805.74 KB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Research Articles (Physics)