ASPCS
 
Back to Volume
Paper: Novel Approaches to Semi-supervised and Unsupervised Learning
Volume: 295, Astronomical Data Analysis Software and Systems XII
Page: 427
Authors: Bazell, D.; Miller, D. J.; Borne, K.
Abstract: We discuss a novel approach to the exploration, understanding, and classification of astronomical data. We are exploring the use of unlabeled data for supervised classification and for semi-supervised clustering. Current automated classification methods rely heavily on supervised learning algorithms that require training data sets containing large amounts of previously classified, or labeled, data. While unlabeled data are often cheap and plentiful, using a human to classify the data is tedious, time consuming, and expensive. We are examining methods whereby supervised classification techniques can use cheaply available, large volumes of unlabeled data to substantially improve their ability to classify objects.
Back to Volume