Credit assignment is a fundamental issue for the Learning Classifier Systems literature. We engage in a detailed investigation of credit assignment in one recent system called UC...
Labeling objects in images is an essential prerequisite for many visual learning and recognition applications that depend on training data, such as image retrieval, object detecti...
Large scale learning is often realistic only in a semi-supervised setting where a small set of labeled examples is available together with a large collection of unlabeled data. In...
Acquiring knowledge has long been the major bottleneck preventing the rapid spread of AI systems. Manual approaches are slow and costly. Machine-learning approaches have limitatio...
Topic models could have a huge impact on improving the ways users find and discover content in digital libraries and search interfaces, through their ability to automatically lea...
David Newman, Youn Noh, Edmund M. Talley, Sarvnaz ...