During the last decade, several quantum information protocols, such as quantum key distribution, teleportation or quantum computation, have attracted a lot of interest. Despite th...
While the SoftAssign algorithm imposes a two-way constraint embedded into the deterministic annealing scheme and the EMICP algorithm imposes a one-way constraint, they represent t...
Log-linear and maximum-margin models are two commonly-used methods in supervised machine learning, and are frequently used in structured prediction problems. Efficient learning of...
Michael Collins, Amir Globerson, Terry Koo, Xavier...
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...
A number of today's state-of-the-art planners are based on forward state-space search. The impressive performance can be attributed to progress in computing domain independen...