English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Gamma hadron classification, a central machine learning task in gamma rayastronomy, is conventionally tackled with supervised learning. However, thesupervised approach requires annotated training data to be produced insophisticated and costly simulations. We propose to instead solve gamma hadronclassification with a noisy label approach that only uses unlabeled datarecorded by the real telescope. To this end, we employ the significance ofdetection as a learning criterion which addresses this form of weaksupervision. We show that models which are based on the significance ofdetection deliver state-of-the-art results, despite being exclusively trainedwith noisy labels; put differently, our models do not require the costlysimulated ground-truth labels that astronomers otherwise employ for classifiertraining. Our weakly supervised models exhibit competitive performances also onimbalanced data sets that stem from a variety of other application domains. Incontrast to existing work on class-conditional label noise, we assume that onlyone of the class-wise noise rates is known.

Noisy Labels for Weakly Supervised Gamma Hadron Classification