Semi-supervised learning (SSL), is classification where additional unlabeled data can be used to improve accuracy. Generative approaches are appealing in this situation, as a mode...
Meta-Learning has been used to relate the performance of algorithms and the features of the problems being tackled. The knowledge in Meta-Learning is acquired from a set of meta-e...
We present a new grammatical formalism called Constraint Dependency Grammar (CDG) in which every grammatical rule is given as a constraint on wordto-word modifications. CDG parsin...
The problem of predicting a sequence x ; x ; . . . generated by a discrete source with unknown statistics is considered. Each letter x is predicted using the information on the wor...
Despite significant progress in deformable model fitting over the last decade, the problem of efficient and accurate person-independentface fitting remains a challenging probl...