Deep learning from the crowd. Fundamentals of morphological galaxy classification
A deep neural network model to perform galaxy morphological classification trained from crowd annotations is adapted, considering the training scheme, the agreement between the annotators, and the hierarchy, to derive useful results for upper levels in the hierarchy.
L. E. Sucar, C. del Burgo, Jonathan Serrano-Pérez
· Astronomy & Astrophysics · 0 citations