Learn More
Convolutional neural network (CNN) has been widely employed for image recognition because it can achieve high accuracy by emulating behavior of optic nerves in living creatures. Recently, rapid growth of modern applications based on deep learning algorithms has further improved research and implementations. Especially, various accelerators for deep CNN have(More)
Many face recognition algorithms use “distance-based” methods: Feature vectors are extracted from each face and distances in feature space are compared to determine matches. In this paper, we argue for a fundamentally different approach. We consider each image as having been generated from several underlying causes, some of which are due to(More)
Lipid droplets (LDs) are emerging cellular organelles that are of crucial importance in cell biology and human diseases. In this study, we present our screen of approximately 4,700 Saccharomyces cerevisiae mutants for abnormalities in the number and morphology of LDs; we identify 17 fld (few LDs) and 116 mld (many LDs) mutants. One of the fld mutants (fld1)(More)
Lipid droplets (LDs) are important cellular organelles that govern the storage and turnover of lipids. Little is known about how the size of LDs is controlled, although LDs of diverse sizes have been observed in different tissues and under different (patho)physiological conditions. Recent studies have indicated that the size of LDs may influence(More)
The main theme of this paper is to develop a novel eigenvalue optimization framework for learning a Mahalanobis metric. Within this context, we introduce a novel metric learning approach called DML-eig which is shown to be equivalent to a well-known eigenvalue optimization problem called minimizing the maximal eigenvalue of a symmetric matrix (Overton,(More)
Integer overflow bugs in C and C++ programs are difficult to track down and may lead to fatal errors or exploitable vulnerabilities. Although a number of tools for finding these bugs exist, the situation is complicated because not all overflows are bugs. Better tools need to be constructed, but a thorough understanding of the issues behind these errors does(More)
A deficiency of dietary protein or amino acids has long been known to impair immune function and increase the susceptibility of animals and humans to infectious disease. However, only in the past 15 years have the underlying cellular and molecular mechanisms begun to unfold. Protein malnutrition reduces concentrations of most amino acids in plasma. Findings(More)
Arabidopsis thaliana Protein Interactome Database (AtPID) is an object database that integrates data from several bioinformatics prediction methods and manually collected information from the literature. It contains data relevant to protein-protein interaction, protein subcellular location, ortholog maps, domain attributes and gene regulation. The predicted(More)
Keyphrases are widely used as a brief summary of documents. Since manual assignment is time-consuming, various unsupervised ranking methods based on importance scores are proposed for keyphrase extraction. In practice, the keyphrases of a document should not only be statistically important in the document , but also have a good coverage of the document.(More)
Neural machine translation (NMT) aims at solving machine translation (MT) problems using neural networks and has exhibited promising results in recent years. However, most of the existing NMT models are shallow and there is still a performance gap between a single NMT model and the best conventional MT system. In this work, we introduce a new type of linear(More)