model, it is possible to change one element (&) and then to compensate others to reestablish a good fit. However, the fact that an improved fit is achieved when the first slice is allowed to differ suggests that there are significant differences in the field structure in the gate feed region. In particular, the source resistance is large in the first slice and negligible in the remainder. This ...

Discriminative methods for learning structured output classifiers have been gaining popularity in recent years due to their successful applications in fields like computer vision, natural language processing or bio-informatics. Learning of the structured output classifiers leads to solving a convex minimization problem which is not tractable by standard algorithms. A significant effort has been...