We extend the classical single-task active learning (AL) approach. In the multi-task active learning (MTAL) paradigm, we select examples for several annotation tasks rather than f...
Roi Reichart, Katrin Tomanek, Udo Hahn, Ari Rappop...
In this paper a new learning scheme for SAT is proposed. The originality of our approach arises from its ability to achieve clause learning even if no conflict occurs. This clear...
Multiple instance learning (MIL) is a branch of machine learning that attempts to learn information from bags of instances. Many real-world applications such as localized content-...
In this paper, we propose a generative model for representing complex motion, such as wavy river, dancing fire and dangling cloth. Our generative method consists of four component...
Given a graph G whose set of vertices is a Polish space X, the weak Borel chromatic number of G is the least size of a family of pairwise disjoint G-independent Borel sets that cov...