We show that it is possible to use data compression on independently obtained hypotheses from various tasks to algorithmically provide guarantees that the tasks are sufficiently r...
We consider reinforcement learning in systems with unknown dynamics. Algorithms such as E3 (Kearns and Singh, 2002) learn near-optimal policies by using "exploration policies...
This paper is concerned with affective issues in learning technologies in a collaborative context. Traditionally in learning there has been a division between cognition and affect...
In this paper we address the problem of predicting when the available data is incomplete. We show that changing the generally accepted table-wise view of the sample items into a g...
In this paper we propose a new distributed learning method called distributed network boosting (DNB) algorithm for distributed applications. The learned hypotheses are exchanged b...