Learn 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)
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)
We study characteristics of receptive fields of units in deep convolutional networks. The receptive field size is a crucial issue in many visual tasks, as the output must respond to large enough areas in the image to capture information about large objects. We introduce the notion of an effective receptive field, and show that it both has a Gaussian(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)
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)
For the generation of highly natural synthetic speech, the control of prosody is of primary importance. The fundamental frequency (F0) is one of the most important components of speech prosody. This research investigates the variation of F0 in continuous Cantonese speech, with the goal of establishing an effective mechanism of prosody control in Cantonese(More)
Semi-supervised learning, which uses unlabeled data to help learn a discriminative model, is especially important for structured output problems, as considerably more effort is needed to label its multi-dimensional outputs versus standard single output problems. We propose a new max-margin framework for semi-supervised structured output learning, that(More)