Supervised learning uses a training set of labeled examples to compute a classifier which is a mapping from feature vectors to class labels. The success of a learning algorithm i...
We study and compare two combinatorial lowness notions: strong jump-traceability and well-approximability of the jump, by strengthening the notion of jump-traceability and super-l...
It was proved few years ago that classes of Boolean functions definable by means of functional equations [9], or equivalently, by means of relational constraints [16], coincide wit...
The visual appearance of an image is closely associated with its low-level features. Identifying the set of features that best characterizes the image is useful for tasks such as ...
We studied a number of measures that characterize the difficulty of a classification problem. We compared a set of real world problems to random combinations of points in this mea...