Transfer learning allows leveraging the knowledge of source domains, available a priori, to help training a classifier for a target domain, where the available data is scarce. Th...
Development of a research project in Computer Science, integrating a considerable number of research institutions and about 1200 individual researchers all over a country with big...
Current methods for learning visual categories work well when a large amount of labeled data is available, but can run into severe difficulties when the number of labeled examples...
This paper presents the findings from a project investigating management development for SME managers using an action learning programme, combining both face-to-face workshops and ...