Physical Sciences and Mathematics Commons^™

Active Learning With Generalized Queries, Jun Du

Electronic Thesis and Dissertation Repository

We study active learning with generalized queries in the thesis.

In contrast to supervised learning, active learning can usually achieve the same predictive accuracy with much fewer labeled training examples, thus significantly reducing the labeling cost. However, previous studies of active learning mostly assume that the learner can only ask specific queries (i.e., require labels for specific examples by providing all feature values). For instance, if the task is to predict osteoarthritis based on a patient data set with 30 features, the previous active learners could only ask the specific queries as: does this patient have osteoarthritis, if ID is …