After a classifier is trained using a machine learning algorithm and put to use in a real world system, it often faces noise which did not appear in the training data. Particularl...
Abstract. Many classes of images exhibit sparse structuring of statistical dependency. Each variable has strong statistical dependency with a small number of other variables and ne...
We present a system that learns to follow navigational natural language directions. Where traditional models learn from linguistic annotation or word distributions, our approach i...
Inpainting is the problem of filling-in holes in images. Considerable progress has been made by techniques that use the immediate boundary of the hole and some prior information o...
Most previous work on trainable language generation has focused on two paradigms: (a) using a statistical model to rank a set of generated utterances, or (b) using statistics to i...