Current re-ranking algorithms for machine translation rely on log-linear models, which have the potential problem of underfitting the training data. We present BoostedMERT, a nove...
In this paper, we describe an algorithm and implementation of locality optimizations for architectures with instruction sets such as Intel’s SSE and Motorola’s AltiVec that su...
We consider the Bounded Diameter Minimum Spanning Tree problem and describe four neighbourhood searches for it. They are used as local improvement strategies within a variable nei...
We present a shape representation and a matching method for nonrigid shapes with closed contours. The representation utilizes the areas of the triangles formed by the boundary poi...
Naif Alajlan, Ibrahim El Rube, Mohamed S. Kamel, G...
Reinforcement learning algorithms that employ neural networks as function approximators have proven to be powerful tools for solving optimal control problems. However, their traini...