Reasoning over Bayesian Networks using Semantic Artificial Neural Networks

Sotirios Batsakis, Grigoris Antoniou

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)

Abstract

Representation of application domains, related concepts and their dependencies is often achieved using Bayesian Networks. In Bayesian Networks nodes represent random variables and arcs represent their dependencies. Since inference over Bayesian Networks is a complex task in this work a novel approach for representing and reasoning over Bayesian Networks using Semantically labeled Neural Networks is proposed and evaluated. Using Semantic Neural Networks combines advantages of Neural Networks such as wide adoption and highly optimized implementations while preserving the interpretability of Bayesian Networks which is an important requirement, especially in medical applications. In addition the proposed approach is evaluated over medical datasets with positive results.

Original languageEnglish
Title of host publication12th International Conference on Information, Intelligence, Systems and Applications
Subtitle of host publicationIISA 2021
PublisherIEEE
Number of pages4
ISBN (Electronic)9781665400329
ISBN (Print)9781665400336
DOIs
Publication statusPublished - 8 Oct 2021
Event12th International Conference on Information, Intelligence, Systems and Applications - Virtual, Chania Crete, Greece
Duration: 12 Jul 202114 Jul 2021
Conference number: 12

Conference

Conference12th International Conference on Information, Intelligence, Systems and Applications
Abbreviated titleIISA 2021
Country/TerritoryGreece
CityVirtual, Chania Crete
Period12/07/2114/07/21

Fingerprint

Dive into the research topics of 'Reasoning over Bayesian Networks using Semantic Artificial Neural Networks'. Together they form a unique fingerprint.

Cite this