Often when modeling structured domains, it is desirable to leverage information that is not naturally expressed as simply a label. Examples include knowledge about the evaluation ...
While determining model complexity is an important problem in machine learning, many feature learning algorithms rely on cross-validation to choose an optimal number of features, ...
Abstract. A variant of iterative learning in the limit (cf. [LZ96]) is studied when a learner gets negative examples refuting conjectures containing data in excess of the target la...
The paper presents an approach to using structural descriptions, obtained through a human-robot tutoring dialogue, as labels for the visual object models a robot learns. The paper...
Geert-Jan M. Kruijff, John D. Kelleher, Gregor Ber...
This demonstration presents an integrated web-based synchronized scenario for many-to-one cross-media correlations between speech (an EFL, English as Foreign Language, lecture wit...