—Biasing properly the hypothesis space of a learner has been shown to improve generalization performance. Methods for achieving this goal have been proposed, that range from desi...
We introduce the problem of zero-data learning, where a model must generalize to classes or tasks for which no training data are available and only a description of the classes or...
The experience of preparing interface design knowledge to be reusable allows reflection on the process, potential, and general challenges of effectively and efficiently using this...
Catherine Payne, C. F. Allgood, Christa M. Chewar,...
Learners and knowledge workers are increasingly facing environments where frequent interruptions, multi-tasking, information overload, and insufficient community awareness are the ...
Visual attributes expose human-defined semantics to object recognition models, but existing work largely restricts their influence to mid-level cues during classifier training....