Probability density estimation from data is a widely studied problem. Often, the primary goal is to faithfully mimic the underlying empirical density. Having an interpretable model that allows insight into why certain predictions were made is often of secondary importance. Using logic-based formalisms, such as Markov logic, can help with interpretability, but even in Markov logic it can be diff...

Kernel based neural networks with probabilistic reasoning are suitable for many practical applications. But in uence of data set sizes let the probabilistic approach fail in case of small data amounts. Possibilistic reasoning avoids this drawback because it is independent of class size. The fundamentals of possibilistic reasoning are derived from a probability/possibility consistency principle ...

Logic programs with ordered disjunction have shown to be a flexible specification language able to model common user preferences in a natural way. However, in some realistic scenarios the preferences should be linked to the evidence of the information when trying to reach a single preferred solution. In this paper, we extend the syntax and the semantics of logic programs with ordered disjunctio...

We show a hybrid probabilistic and possibilistic model for assessing the risk of a service level agreement for a computing task in a cluster/grid environment. Using the predictive probabilistic approach we develop a framework for resource management in grid computing, and by introducing an upper limit for the number of failures we approximate the probability that a particular computing task is ...

We introduce the class of possibilistic nested logic programs. These possibilistic logic programs allow us to use nested expressions in the bodies and the heads of their rules. By considering a possibilistic nested logic program as a possibilistic theory, a construction of a possibilistic logic programing semantics based on answer sets for nested logic programs and the proof theory of possibili...

image segmentation is an essential issue in image description and classification. currently, in many real applications, segmentation is still mainly manual or strongly supervised by a human expert, which makes it irreproducible and deteriorating. moreover, there are many uncertainties and vagueness in images, which crisp clustering and even type-1 fuzzy clustering could not handle. hence, type-...

Risk aversion is one of the main themes in risk theory. Risk theory is treated usually by probability theory. The aim of this paper is to propose an approach of the risk aversion by possibility theory initiated by Zadeh in 1978 as an alternative of probability theory in the modeling of uncertain situations. The main notions studied in this paper are the possibilistic risk premium and the possib...

To address the need for efficient and unbiased experimental testing of methods for decision under uncertainty, we devise an approach for probing weaknesses of these methods by running numerical experiments on readily available or easily obtainable databases of real life data. Since the approach uses real life data, it allows us to study the effect of modeling error on the performance of a metho...

Possibilistic logic provides a convenient tool for dealing with inconsistency and handling uncertainty. In this paper, we propose possibilistic description logics as an extension of description logics. We give semantics and syntax of possibilistic description logics. We then define two inference services in possibilistic description logics. Since possibilistic inference suffers from the drownin...