Abstract. We are interested in the relationship between learning efficiency and representation in the case of supervised neural networks for pattern classification trained by conti...
In multi-task learning several related tasks are considered simultaneously, with the hope that by an appropriate sharing of information across tasks, each task may benefit from th...
This paper proposes a multiple instance learning (MIL) algorithm for Gaussian processes (GP). The GP-MIL model inherits two crucial benefits from GP: (i) a principle manner of lea...
We address the problem of multiclass object detection. Our aims are to enable models for new categories to benefit from the detectors built previously for other categories, and fo...
In a ten-session experiment, six participants practiced typing with an expanding rehearsal method on an optimized virtual keyboard. Based on a large amount of in-situ performance ...