We propose statistical predicate invention as a key problem for statistical relational learning. SPI is the problem of discovering new concepts, properties and relations in struct...
We propose to model relative attributes1 that capture the relationships between images and objects in terms of human-nameable visual properties. For example, the models can captur...
In this paper, we describe two di erent learning tasks for relational structures. When learning a classi er for structures, the relational structures in the training sets are clas...
Abstract. In the past years Software Engineering has experienced several difficulties in modularising crosscutting aspects, like shared, dynamic or scattered behavior of object-ori...
We introduce a generic family of behavioral relations for which the problem of comparing an arbitrary transition system to some finite-state specification can be reduced to a model...