Active learning (AL) is an increasingly popular strategy for mitigating the amount of labeled data required to train classifiers, thereby reducing annotator effort. We describe ...
Byron C. Wallace, Kevin Small, Carla E. Brodley, T...
We propose an approach for learning visual models of object categories in an unsupervised manner in which we first build a large-scale complex network which captures the interacti...
Abstract. In this paper we describe a virtual laboratory that is designed to accelerate scientific exploration and discovery by minimizing the time between the generation of a scie...
Judith Ellen Devaney, Steven G. Satterfield, John ...
Concept drifting is an important and challenging research issue in the field of machine learning. This paper mainly addresses the issue of semantic concept drifting in time series...
We consider geometric conditions on a labeled data set which guarantee that boosting algorithms work well when linear classifiers are used as weak learners. We start by providing ...