We address the problem of learning classifiers for several related tasks that may differ in their joint distribution of input and output variables. For each task, small
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...
Many university classes and commercial training courses rely on classroom lecture and practice exercises to help students learn new skills. The thesis work described in this paper...
A long-lived agent continually faces new tasks in its environment. Such an agent may be able to use knowledge learned in solving earlier tasks to produce candidate policies for it...
We study the problem of object classification when training
and test classes are disjoint, i.e. no training examples of
the target classes are available. This setup has hardly be...
Christoph H. Lampert, Hannes Nickisch, Stefan Harm...