Abstract-- Methods that faithfully and robustly capture the geometry of complex material interfaces in labeled volume data are important for generating realistic and accurate visua...
Miriah Meyer, Ross Whitaker, Robert M. Kirby, C...
We investigate a number of approaches to generating Stanford Dependencies, a widely used semantically-oriented dependency representation. We examine algorithms specifically design...
Daniel Cer, Marie-Catherine de Marneffe, Daniel Ju...
Background: High-throughput molecular biology provides new data at an incredible rate, so that the increase in the size of biological databanks is enormous and very rapid. This sc...
We introduce a general-purpose learning machine that we call the Guaranteed Error Machine, or GEM, and two learning algorithms, a real GEM algorithm and an ideal GEM algorithm. Th...
Abstract--We investigate parameter-based and distributionbased approaches to regularizing the generative, similarity-based classifier called local similarity discriminant analysis ...