Learning temporal graph structures from time series data reveals important dependency relationships between current observations and histories. Most previous work focuses on learn...
Recent approaches to learning structured predictors often require approximate inference for tractability; yet its effects on the learned model are unclear. Meanwhile, most learnin...
We present exact algorithms for identifying deterministic-actions' effects and preconditions in dynamic partially observable domains. They apply when one does not know the ac...
It has been widely observed that different NLP applications require different sense granularities in order to best exploit word sense distinctions, and that for many applications ...
Rion Snow, Sushant Prakash, Daniel Jurafsky, Andre...
Abstract. Most of the processing in vision today uses spatially invariant operations. This gives efficient and compact computing structures, with the conventional convenient separa...