We show that if the closureof a function class F under the metric induced by some probability distribution is not convex, then the sample complexity for agnostically learning F wi...
Wee Sun Lee, Peter L. Bartlett, Robert C. Williams...
Current semi-supervised incremental learning approaches select unlabeled examples with predicted high confidence for model re-training. We show that for many applications this dat...
— We present a topological navigation system that is able to visually recognize the different rooms of an apartment and guide a robot between them. Specifically tailored for sma...
It is possible to model avatars that learn to simulate object manipulations and other complex actions. A number of applications may benefit from this technique including safety, e...
In this paper we present Evaluate, a platform for learning performance monitoring. Evaluate manages a number of artefacts that can be used to monitor learning performance, like met...
Bernd Simon, Kasra Seirafi, Asmund Realfsen, Mark ...