Compiling Possibilistic Networks: Alternative Approaches to Possibilistic Inference
نویسندگان
چکیده
Qualitative possibilistic networks, also known as min-based possibilistic networks, are important tools for handling uncertain information in the possibility theory framework. Despite their importance, only the junction tree adaptation has been proposed for exact reasoning with such networks. This paper explores alternative algorithms using compilation techniques. We first propose possibilistic adaptations of standard compilation-based probabilistic methods. Then, we develop a new, purely possibilistic, method based on the transformation of the initial network into a possibilistic base. A comparative study shows that this latter performs better than the possibilistic adaptations of probabilistic methods. This result is also confirmed by experimental results.
منابع مشابه
On the Compilation of Stratified Belief Bases under Linear and Possibilistic Logic Policies
Developing efficient approaches for reasoning under inconsistency is an important issue in many applications. Several methods have been proposed to compile, possibly inconsistent, weighted or stratified bases. This paper focuses on the well-known linear order and possibilistic logic strategies. It provides a way for compiling a stratified belief base in order to be able to process inference fro...
متن کاملHybrid Possibilistic Networks
Possibilistic networks are important tools for dealing with uncertain pieces of information. For multiplyconnected networks, it is well known that the inference process is a hard problem. This paper studies a new representation of possibilistic networks, called hybrid possibilistic networks. The uncertainty is no longer represented by local conditional possibility distributions, but by their co...
متن کاملProduct-based Causal Networks and Quantitative Possibilistic Bases
In possibility theory, there are two kinds of possibilistic causal networks depending if possibilistic conditioning is based on the minimum or on the product operator. Similarly there are also two kinds of possibilistic logic: standard (min-based) possibilistic logic and quantitative (product-based) possibilistic logic. Recently, several equivalent transformations between standard possibilistic...
متن کاملLearning Possibilistic Networks with a Global Evaluation Method
Inference networks, probabilistic as well as possibilistic, are popular techniques to make reasoning in multi-dimensional domains feasible. Since constructing them by hand can be tedious and time consuming, a large part of recent research has been devoted to learning inference networks from data. Most of the proposed methods are based on local, i.e. single hyperedge evaluation. In this paper we...
متن کاملEvaluation Measures for Learning Probabilistic and Possibilistic Networks
Evidence propagation in inference networks, probabilistic or possibilistic, can be done in two different ways — using a product/sum scheme or using a minimum/maximum scheme — depending on the type of answers one expects from the network. Usually the first is seen in connection with probabilistic, the second in connection with possibilistic reasoning, although we argue that both schemes are appl...
متن کامل