Following results are sketched in this extended abstract: (1) Datalog recursive programs where each rule has at most one subgoal called unit recursions are shown to be bounded, wit...
The asymptotic behavior of stochastic gradient algorithms is studied. Relying on some results of differential geometry (Lojasiewicz gradient inequality), the almost sure pointconve...
In pattern recognition, data integration is a processing method to combine multiple sources so that the combined result can be more accurate than a single source. Evidence theory ...
We formalize a model for supervised learning of action strategies in dynamic stochastic domains and show that PAC-learning results on Occam algorithms hold in this model as well. W...
Abstract. A logic-based language is often adopted in systems for pervasive computing, because it provides a convenient way to define rules that change the behavior of the systems d...