In the context of learning paradigms of identification in the limit, we address the question: why is uncertainty sometimes desirable? We use mind change bounds on the output hypotheses as a measure of uncertainty and interpret ‘desirable’ as reduction in data memorization, also defined in terms of mind change bounds. The resulting model is closely related to iterative learning with bounded mind...

We propose a rigorous definition of the notion of typicality, making use of the strict partial order naturally induced among the objects at hand by a given concept. This perspective enables us to transpose in the framework of object determination logic some well-known problems like contextual typicality or contextual inference. Then these problems can be treated with the help of the tools devel...

This extended abstract provides an overview of my research towards a dissertation thesis in the context of programming cognitive agents with non-monotonic reasoning capabilities.

of Nonmonotonic Fuzzy Inference

Airline markets are characterized by the existence of substantial price dispersion. In this paper we investigate the relationship between daily price dispersion and competition using data related to products offered to business travelers in the Italian airline market. We find that the effect of competition on price dispersion is non-monotonic.

The non-overlapping sets of pictures are sets such that no two pictures in the set (properly) overlap. They are the generalization to two dimensions of the cross-bifix-free sets of strings. Non-overlapping sets of pictures are non-expandable when no other picture can be added without violating the property. We present a construction of non-expandable non-overlapping (NENO) sets of pictures and ...

This note is concerned with a formal analysis of the problem of non-monotonic reasoning in intelligent systems, especially when the uncertainty is taken into account in a quantitative way. A firm connection between logic and probability is established by introducing conditioning notions by means of formal structures that do not rely on quantitative measures. The associated conditional logic, co...