The bottleneck in interactive visual classification is the exchange of information between human and machine. We introduce the concept of the visible model, which is an ion of an ...
Share and reuse of learning objects are an important issue, that are not solved by simply adding a metadata description. Their contextualisation as well as their level of granular...
Emmanuel Fernandes, Hend Madhour, Sami Miniaoui, M...
Models of learning and performing by exploration assume that the semantic distance between task descriptions and screen labels controls in part the usersÕ search strategies. Neve...
This paper provides a systematic study of inductive inference of indexable concept classes in learning scenarios in which the learner is successful if its final hypothesis describ...
We present a probabilistic generative model for learning semantic parsers from ambiguous supervision. Our approach learns from natural language sentences paired with world states ...