We show that the automatically induced latent variable grammars of Petrov et al. (2006) vary widely in their underlying representations, depending on their EM initialization point...
The problem of automatic feature selection/weighting in kernel methods is examined. We work on a formulation that optimizes both the weights of features and the parameters of the ...
Super-resolution is the task of creating an high resolution image from a low resolution input sequence. To overcome the difficulties of fine image registration, several methods ...
In supervised learning, a training set consisting of labeled instances is used by a learning algorithm for generating a model (classifier) that is subsequently employed for decidi...
We consider di usion processes on a class of R trees. The processes are de ned in a manner similar to that of Le Gall's Brownian snake. Each point in the tree has a real value...