Probabilistic multiple kernel learning

Damoulas, Theodoros (2009) Probabilistic multiple kernel learning. PhD thesis, University of Glasgow.

Abstract

The integration of multiple and possibly heterogeneous information sources for an overall decision-making process has been an open and unresolved research direction in computing science since its very beginning. This thesis attempts to address parts of that direction by proposing probabilistic data integration algorithms for multiclass decisions where an observation of interest is assigned to one of many categories based on a plurality of information channels.

• Item Type: Thesis (PhD)
• Qualification Level: Doctoral
• Keywords: pattern recognition, data integration, information fusion, classification, bayesian inference
• Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science; Q Science > QA Mathematics > QA76 Computer software; Q Science > Q Science (General)
• Colleges/Schools: College of Science and Engineering > School of Computing Science
• Supervisor's Name: Girolami, Prof. Mark and van Rijsbergen, Prof. Keith
• Date of Award: 2009
• Depositing User: Mr Theodoros Damoulas
• Unique ID: glathesis:2009-1266
• Copyright: Copyright of this thesis is held by the author.
• Date Deposited: 10 Nov 2009
• Last Modified: 28 Feb 2020 09:26
• URI: https://theses.gla.ac.uk/id/eprint/1266