A comparison of evidential networks and compositional models

Title:

A comparison of evidential networks and compositional models

Creator:

Vejnarová, Jiřina

Identifier:

https://cdk.lib.cas.cz/client/handle/uuid:98db0c3e-9834-4853-bbf6-0faf0583adc5
uuid:98db0c3e-9834-4853-bbf6-0faf0583adc5

Subject:

evidence theory, conditioning, independence, and directed graphs

Type:

model:article and TEXT

Format:

bez média and svazek

Description:

Several counterparts of Bayesian networks based on different paradigms have been proposed in evidence theory. Nevertheless, none of them is completely satisfactory. In this paper we will present a new one, based on a recently introduced concept of conditional independence. We define a conditioning rule for variables, and the relationship between conditional independence and irrelevance is studied with the aim of constructing a Bayesian-network-like model. Then, through a simple example, we will show a problem appearing in this model caused by the use of a conditioning rule. We will also show that this problem can be avoided if undirected or compositional models are used instead.

Language:

English

Rights:

http://creativecommons.org/publicdomain/mark/1.0/
policy:public

Coverage:

[246]-267

Source:

Kybernetika | 2014 Volume:50 | Number:2

Harvested from:

CDK

Metadata only:

false