Multi-instance (MI) learning is a variant of supervised learning where labeled examples consist of bags (i.e. multi-sets) of feature vectors instead of just a single feature vecto...
The goal of robot learning from demonstration is to have a robot learn from watching a demonstration of the task to be performed. In our approach to learning from demonstration th...
We describe a novel simple and highly scalable semi-supervised method called Word-Class Distribution Learning (WCDL), and apply it the task of information extraction (IE) by utili...
Yanjun Qi, Ronan Collobert, Pavel Kuksa, Koray Kav...
It is generally assumed in the traditional formulation of supervised learning that only the outputs data are uncertain. However, this assumption might be too strong for some learni...
Patrick Dallaire, Camille Besse, Brahim Chaib-draa
This paper describes an approach to robotic control that is patterned after models of human skill acquisition. The intent is to develop robots capable of learning how to accomplis...