Recurrent neural networks are able to store information about previous as well as current inputs. This "memory" allows them to solve temporal problems such as language r...
Abstract. We analyze the expected cost of a greedy active learning algorithm. Our analysis extends previous work to a more general setting in which different queries have differe...
In examine the tutoring protocols of one expert human tutor tutoring 10 students in solving physics problems, four analyses reveal that he tutored the five good learners in differe...
The fitness landscape of the resource constrained project scheduling problem is investigated by examining the search space position type distribution and the correlation between t...
Abstract -- We experimentally examine the performance of preconditioners based on entries of the symmetric positive definite part and small subspace solvers for linear system of eq...