QML-Morven: A Novel Framework for Learning Qualitative Models

Research output: Book/ReportOther Report

8 Downloads (Pure)

Abstract

In this report, a novel qualitative model learning (QML) framework named
QML-Morven is presented. QML-Morven is an extensible framework and currently includes three QML subsystems, which employ either symbolic or evolutionary approaches
as their learning strategies. QML-Morven uses the formalism of Morven, a fuzzy qualitative simulator, to represent and reason about qualitative models, and it also utilises
Morven to verify candidate models. Based on this framework, a series of experiments were
designed and carried out to: (1) verify the results obtained by the previous QML system
ILP-QSI; (2) investigate factors that in¿uence the learning precision and minimum data
requirement for successful learning; (3) address the scalability issue of QML systems.
Original languageEnglish
Place of PublicationAberdeen
PublisherDepartment of Computing Science, University of Aberdeen
Number of pages37
Publication statusPublished - Jun 2012

Publication series

NameTechnical Report ABDN–CS–12–03

Keywords

  • qualitative reasoning
  • qualitative model learning
  • artificial immune systems
  • backtracking with forward checking

Fingerprint Dive into the research topics of 'QML-Morven: A Novel Framework for Learning Qualitative Models'. Together they form a unique fingerprint.

  • Cite this

    Pang, W., & Coghill, G. M. (2012). QML-Morven: A Novel Framework for Learning Qualitative Models. (Technical Report ABDN–CS–12–03). Department of Computing Science, University of Aberdeen. http://homepages.abdn.ac.uk/pang.wei/pages/TechReport/abdntechrep12-03.pdf