Artificial intelligence: Concept overview, methodological approaches and choice metrics

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

Abstract

During the last couple of years there has been a renaissance in the field of artificial intelligence, also called AI. A wide diversity of possible concepts to this topic leads to the compulsion to be properly informed about a variety of approaches. This paper focuses on explaining the primary and most relevant theoretical concepts in regard to artificial intelligence and to rate them based on derived criteria. To achieve this, the most significant manifestations of these learning concepts are analyzed to identify their core characteristics. Choice metrics are derived based on this knowledge and selected with regard to an industrial environment. Additionally, a methodical approach is developed to ease the user's choice of an appropriate concept according to the given criteria. The final result of this paper is a set of diagrams that illustrate the different artificial intelligence concepts based on the found criteria.

Original languageEnglish
Title of host publication31st European Modeling and Simulation Symposium, EMSS 2019
EditorsMichael Affenzeller, Agostino G. Bruzzone, Francesco Longo, Guilherme Pereira
PublisherDIME UNIVERSITY OF GENOA
Pages103-110
Number of pages8
ISBN (Electronic)9788885741263
Publication statusPublished - 2019
Event31st European Modeling and Simulation Symposium, EMSS 2019 - Lisbon, Portugal
Duration: 18 Sep 201920 Sep 2019

Publication series

Name31st European Modeling and Simulation Symposium, EMSS 2019

Conference

Conference31st European Modeling and Simulation Symposium, EMSS 2019
CountryPortugal
CityLisbon
Period18.09.201920.09.2019

Keywords

  • Artificial intelligence
  • Decision support system
  • Deep learning
  • Independent metrics

Fingerprint Dive into the research topics of 'Artificial intelligence: Concept overview, methodological approaches and choice metrics'. Together they form a unique fingerprint.

Cite this