An anytime algorithm is capable of returning a response to the given task at essentially any time; typically the quality of the response improves as the time increases. Here, we c...
Uncertainty is a popular phenomenon in machine learning and a variety of methods to model uncertainty at different levels has been developed. The aim of this paper is to motivate ...
Model learning combined with dynamic programming has been shown to be e ective for learning control of continuous state dynamic systems. The simplest method assumes the learned mod...
In this paper we discuss the need for learning in multi-agent design systems, and the variety of forms it might take. We propose a particular method of guiding learning in these s...
We propose a new local learning scheme that is based on the principle of decisiveness: the learned classifier is expected to exhibit large variability in the direction of the test ...