Learn More
Predictive analysis using publicly available yeast functional genomics and proteomics data suggests that many more proteins may be involved in biogenesis of ribonucleoproteins than are currently known. Using a microarray that monitors abundance and processing of noncoding RNAs, we analyzed 468 yeast strains carrying mutations in protein-coding genes, most(More)
This report presents the concrete, as implemented, software architecture of the Linux kernel. Linux is a UNIX like operating system written by Linus Torvalds. The C language source code for Linux 2.0.30 contains over 800 KLOC and as such is a good candidate for analysis. The architecture was extracted from the source code through a reverse engineering(More)
Geographic indexing is a powerful and effective way to organize information on the web, but the use of standardized location tags is not widespread. Therefore, there is considerable interest in using machine learning approaches to automatically obtain semantic associations involving geographic locations from processing unstructured natural language text.(More)
The web has the potential to serve as an excellent source of example imagery for visual concepts. Image search engines based on text keywords can fetch thousands of images for a given query; however, their results tend to be visually noisy. We present a technique that allows a user to refine noisy search results and characterize a more precise visual object(More)
Message passing algorithms based on variational methods and belief propagation are widely used for approximate inference in a variety of directed and undi-rected graphical models. However, inference can become extremely slow when the cardinality of the state space of individual variables is high. In this paper we explore sparse message passing to(More)
Image stitching allows users to combine multiple regular-sized photographs into a single wide-angle picture, often referred to as a panoramic picture. During stitching users often discover that the produced panorama contains arti-facts or is incomplete. Fixing these flaws requires retaking individual images, which is often difficult by this time. In this(More)
The task of suggesting recipients for an email has recently received attention as it has potential to enhance the flow of knowledge and information within an organization or social network. We investigate two transfer learning techniques to improve recipient prediction performance through considering predictions for multiple users. We present a novel(More)
ACKNOWLEDGMENTS Writing the acknowledgments is the most enjoyable part of this thesis. Many people helped me during my graduate school career, and it is very exciting to have this opportunity to acknowledge them. Much of the research in this dissertation would not have occurred without the hard work and great insight of my colleagues. My first thanks must(More)