Despite serious research efforts, automatic ontology matching still suffers from severe problems with respect to the quality of matching results. Existing matching systems trade-of...
Kai Eckert, Christian Meilicke, Heiner Stuckenschm...
— In connectionist learning, one relevant problem is “catastrophic forgetting” that may occur when a network, trained with a large set of patterns, has to learn new input pat...
Dario Albesano, Roberto Gemello, Pietro Laface, Fr...
The human ability to learn difficult object categories from just a few views is often explained by an extensive use of knowledge from related classes. In this work we study the use...
The demand for and expectation of ubiquitous access to multimedia online learning resources are much higher amongst computer science students than other fields of study. Previous ...
We consider a setting for discriminative semisupervised learning where unlabeled data are used with a generative model to learn effective feature representations for discriminativ...