Learn More
When modeling structured outputs such as image segmentations, prediction can be improved by accurately modeling structure present in the labels. A key challenge is developing tractable models that are able to capture complex high level structure like shape. In this work, we study the learning of a general class of pattern-like high order potential, which we(More)
Cantonese is a major Chinese dialect with a complicated tone system. This research focuses on quantitative modeling of Cantonese tones. It uses Stem-ML, a language-independent framework for quantitative intonation modeling and generation. A set of F 0 prediction models are built, and trained on acoustic data. The prediction error is about 11 Hz or 1(More)
We investigate the problem of learning representations that are invariant to certain nuisance or sensitive factors of variation in the data while retaining as much of the remaining information as possible. Our model is based on a variational autoencoding architecture (Kingma & Welling, 2014; Rezende et al., 2014) with priors that encourage independence(More)
Graph-structured data appears frequently in domains including chemistry, natural language semantics, social networks, and knowledge bases. In this work, we study feature learning techniques for graph-structured inputs. Our starting point is previous work on Graph Neural Networks (Scarselli et al., 2009), which we modify to use gated recurrent units and(More)
Titanium dioxide nanomaterials (nano-TiO(2) ) exhibit stronger photochemical oxidation/reduction capacity compared with their bulk counterparts, but the effectiveness of nano-TiO(2) interaction with ultraviolet (UV) light strongly depends on particle size. In this study, the dependence of nano-TiO(2) toxicity on particle size and interaction with UV light(More)
Diseases caused by dengue virus (DV) infection vary in severity, with symptoms ranging from mild fever to life threatening dengue hemorrhage fever (DHF) and dengue shock syndrome (DSS). Clinical studies have shown that significant decrease in the level of lipoproteins is correlated with severe illness in DHF/DSS patients. Available evidence also indicates(More)
Large static magnetic fields may be employed in magnetic resonance imaging (MRI). At high magnetic field strengths (usually from about 3 T and above) it is possible for humans to perceive a number of effects. One such effect is mild vertigo. Recently, Roberts et al (2011 Current Biology 21 1635-40) proposed a Lorentz-force mechanism resulting from the ionic(More)
MADS-box transcription factors play important roles in organ development. In plants, most studies on MADS-box genes have mainly focused on flower development and only a few concerned fruit development and ripening. A new MADS-box gene named MaMADS7 was isolated from banana fruit by rapid amplification of cDNA ends (RACE) based on a MADS-box fragment(More)