This paper develops the concept of usefulness in the context of supervised learning. We argue that usefulness can be used to improve the performance of classification rules (as me...
Gholamreza Nakhaeizadeh, Charles Taylor, Carsten L...
Abstract. One of the main problems associated with arti cial neural networks online learning methods is the estimation of model order. In this paper, we report about a new approach...
A new scheme of data-driven segmentation is proposed, which is based on detection of object boundary, and volumetric pattern reconstruction as implicit function by using the detect...
We examine the relationship between the VCdimension and the number of parameters of a smoothly parametrized function class. We show that the VC-dimension of such a function class ...
Wee Sun Lee, Peter L. Bartlett, Robert C. Williams...
The Brain is a slow computer yet humans can skillfully play games such as tennis where very fast reactions are required. Of particular interest is the evidence for strategic thinki...