The pipeline of most Phrase-Based Statistical Machine Translation (PB-SMT) systems starts from automatically word aligned parallel corpus. But word appears to be too fine-grained ...
—Current leadership-class machines suffer from a significant imbalance between their computational power and their I/O bandwidth. While Moore’s law ensures that the computatio...
Nawab Ali, Philip H. Carns, Kamil Iskra, Dries Kim...
We have developed a new Linear Support Vector Machine (SVM) training algorithm called OCAS. Its computational effort scales linearly with the sample size. In an extensive empirica...
The assumptions behind linear classifiers for categorical data are examined and reformulated in the context of the multinomial manifold, the simplex of multinomial models furnishe...
We introduce flexible algorithms that can automatically learn mappings from images to actions by interacting with their environment. They work by introducing an image classifier i...