Abstract. The use of sparse invariant features to recognise classes of actions or objects has become common in the literature. However, features are often "engineered" to...
Machine learning often relies on costly labeled data, and this impedes its application to new classification and information extraction problems. This has motivated the developme...
We describe a single convolutional neural network architecture that, given a sentence, outputs a host of language processing predictions: part-of-speech tags, chunks, named entity...
In this paper, we present a regularization approach on discrete graph spaces for perceptual image segmentation via semisupervised learning. In this approach, first, a spectral cl...
Finding good representations of text documents is crucial in information retrieval and classification systems. Today the most popular document representation is based on a vector ...