We study the regret of an online learner playing a multi-round game in a Banach space B against an adversary that plays a convex function at each round. We characterize the minima...
A significant advance in inductive modelling are systems that retain learned knowledge and selectively transfer portions of that knowledge as a source of inductive bias. We defi...
This paper presents an interactive framework for pupils to learn the basic concepts of programming by means of the functional programming language Erlang. Beside the idea of the f...
Abstract. In their search through a huge space of possible hypotheses, rule induction algorithms compare estimations of qualities of a large number of rules to find the one that ap...
Martin Mozina, Janez Demsar, Jure Zabkar, Ivan Bra...
A large number of learning algorithms, for example, spectral clustering, kernel Principal Components Analysis and many manifold methods are based on estimating eigenvalues and eig...