We consider the problem of boosting the accuracy of weak learning algorithms in the agnostic learning framework of Haussler (1992) and Kearns et al. (1992). Known algorithms for t...
We consider the supervised learning of a binary classifier from noisy observations. We use smooth boosting to linearly combine abstaining hypotheses, each of which maps a subcube...
Abstract. Comparison between different formalisms and models is often by flattening structure and reducing them to behaviorally equivalent models e.g., automaton and Turing machine...
Weak Observational Congruence (woc) defined on CCS agents is not a bisimulation since it does not require two states reached by bisimilar computations of woc agents to be still w...