We present a faster method of solving optimal planning problems and show that our solution performs up to an order of magnitude faster than Satplan on a variety of problems from t...
This work characterizes the generalization ability of algorithms whose predictions are linear in the input vector. To this end, we provide sharp bounds for Rademacher and Gaussian...
Serious games that should adapt training to the individual might benefit from methods that are developed for intelligent tutoring systems. One method, model tracing, might be used...
The selection of an optical flow method is mostly a choice from among accuracy, efficiency and ease of implementation. While variational approaches tend to be more accurate than lo...
Claudia Nieuwenhuis, Daniel Kondermann, Christoph ...
We present a simple, agnostic active learning algorithm that works for any hypothesis class of bounded VC dimension, and any data distribution. Our algorithm extends a scheme of C...