Manuel Gómez-Olmedo

Learn More
This paper proposes some possible modifications on the PC basic learning algorithm and makes some experiments to study their behaviour. The variations are: to determine minimum size cut sets between two nodes to study the deletion of a link, to make statistical decisions taking into account a Bayesian score instead of a classical Chi-square test, to study(More)
This paper proposes two new algorithms for inference in credal networks. These algorithms enable probability intervals to be obtained for the states of a given query variable. The first algorithm is approximate and uses the hill-climbing technique in the Shenoy–Shafer architecture to propagate in join trees; the second is exact and is a modification of(More)
The propagation of probabilities in credal networks when probabilities are estimated with a global imprecise Dirichlet model is an important open problem. Only Zaffalon [21] has proposed an algorithm for the Naive classifier. The main difficulty is that, in general, computing upper and lower probability intervals implies the resolution of an optimization of(More)
The present paper introduces a new kind of representation for the potentials in a Bayesian network: binary probability trees. They enable the representation of context-specific independences in more detail than probability trees. This enhanced capability leads to more efficient inference algorithms for some types of Bayesian networks. This paper explains(More)
When there is uncertainty about the values of a variable, it is possible to have different pieces of information about it. This can be due to the fact that they represent the points of view of different agents and these agents have followed different criteria when codify the pieces of information by means of numbers. The aim of this paper is to provide(More)
Although influence diagrams are powerful tools for representing and solving complex decisionmaking problems, their evaluation may require an enormous computational effort and this is a primary issue when processing real-world models. We shall propose an approximate inference algorithm to deal with very large models. For such models, it may be unfeasible to(More)
Recommendation Systems are tools designed to help users to find items within a given domain, according to their own preferences expressed by means of a user profile. A general model for recommendation systems based on probabilistic graphical models is proposed in this paper. It is designed to deal with hierarchical domains, where the items can be grouped in(More)