In this chapter, we describe how the p-values derived from the conformal predictions framework can be used for active learning; that is, to select the informative examples from a data collection that can be used to train a classifier for best performance. We show the connection of this approach to information-theoretic methods, as well as show how the methodology can be generalized to multiple classifier models and information fusion settings. © 2014 Elsevier Inc. All rights reserved.