Complex questions that require inferencing and synthesizing information from multiple documents can be seen as a kind of topicoriented, informative multi-document summarization. I...
Dynamic program optimization allows programs to be generated that are highly tuned for a given environment and input data set. Optimization techniques can be applied and re-applie...
Abstract. Approximations based on random Fourier features have recently emerged as an efficient and elegant methodology for designing large-scale kernel machines [4]. By expressing...
We introduce a novel active learning algorithm for classification of network data. In this setting, training instances are connected by a set of links to form a network, the label...
Many modern visual recognition algorithms incorporate a step of spatial `pooling', where the outputs of several nearby feature detectors are combined into a local or global `...