UNIGE document Doctoral Thesis
previous document  unige:24004  next document
add to browser collection
Title

A unified framework for Support Vector Machines, Multiple Kernel Learning and metric learning

Author
Directors
Defense Thèse de doctorat : Univ. Genève, 2012 - Sc. 4478 - 2012/10/22
Abstract In this work we studied several families of learning algorithms, including Support Vector Machines, Multiple Kernel Learning and metric learning. We focused on two fundamental tasks in Machine Learning which are classification and feature selection. We derived novel learning algorithms for classification and for feature selection, which outperformed the state-of-the-art in several experiments. Moreover, we discovered the relationship among algorithms and built a unified framework of various learning algorithms, more precisely, a unified framework of Support Vector Machines, Multiple Kernel Learning and metric learning.
Keywords Machine LearningArtificial IntelligenceComputer ScienceSupport Vector MachinesMultiple Kernel LearningMetric LearningUnified frameworkLearning algorithmsOptimization
Identifiers
URN: urn:nbn:ch:unige-240049
Full text
Thesis (1.7 MB) - public document Free access
Structures
Research group Geneva Artificial Intelligence Laboratory
Projects DROPTOP
FP7: DebugIT
FP7: e-LICO
Citation
(ISO format)
DO, Thi Thanh Huyen. A unified framework for Support Vector Machines, Multiple Kernel Learning and metric learning. Université de Genève. Thèse, 2012. https://archive-ouverte.unige.ch/unige:24004

328 hits

516 downloads

Update

Deposited on : 2012-11-14

Export document
Format :
Citation style :