We present and relate recent results in prediction based on countable classes of either probability (semi-)distributions or base predictors. Learning by Bayes, MDL, and stochastic ...
A blind classification algorithm is presented that uses hyperdimensional geometric algorithms to locate a hypothesis, in the form of a convex polytope or hyper-sphere. The convex ...
Engineering natural and appropriate interactive behaviour in ubiquitous computing systems presents new challenges to their developers. This paper explores formal models of interac...
Abstract: This paper presents a unified and simple treatment of basic questions concerning two computational models: multiparty communication complexity and polynomials over GF(2)....
We address the problem of analyzing multiple related opinions in a text. For instance, in a restaurant review such opinions may include food, ambience and service. We formulate th...