In spite of the recent improvements in the performance of Answer Set Programming (ASP) solvers, when the search space is sufficiently large, it is still possible for the search al...
Modern Bayesian Network learning algorithms are timeefficient, scalable and produce high-quality models; these algorithms feature prominently in decision support model development...
In robot navigation tasks, the representation of the surrounding world plays an important role, especially in reinforcement learning approaches. This work presents a qualitative r...
We present a simple, easily implemented spectral learning algorithm which applies equally whether we have no supervisory information, pairwise link constraints, or labeled example...
Sepandar D. Kamvar, Dan Klein, Christopher D. Mann...
The absolute loss is the absolute difference between the desired and predicted outcome. I demonstrateworst-case upper bounds on the absolute loss for the perceptron algorithm and ...