Parametric kernels for structured data analysis

dc.contributor.advisorFussell, Donald S., 1951-
dc.creatorShin, Young-inen
dc.date.accessioned2015-05-04T17:36:14Zen
dc.date.available2015-05-04T17:36:14Zen
dc.date.issued2008-05en
dc.descriptiontexten
dc.description.abstractStructured representation of input physical patterns as a set of local features has been useful for a veriety of robotics and human computer interaction (HCI) applications. It enables a stable understanding of the variable inputs. However, this representation does not fit the conventional machine learning algorithms and distance metrics because they assume vector inputs. To learn from input patterns with variable structure is thus challenging. To address this problem, I propose a general and systematic method to design distance metrics between structured inputs that can be used in conventional learning algorithms. Based on the observation of the stability in the geometric distributions of local features over the physical patterns across similar inputs, this is done combining the local similarities and the conformity of the geometric relationship between local features. The produced distance metrics, called “parametric kernels”, are positive semi-definite and require almost linear time to compute. To demonstrate the general applicability and the efficacy of this approach, I designed and applied parametric kernels to handwritten character recognition, on-line face recognition, and object detection from laser range finder sensor data. Parametric kernels achieve recognition rates competitive to state-of-the-art approaches in these tasks.en
dc.description.departmentComputer Sciencesen
dc.format.mediumelectronicen
dc.identifier.urihttp://hdl.handle.net/2152/29669en
dc.language.isoengen
dc.rightsCopyright is held by the author. Presentation of this material on the Libraries' web site by University Libraries, The University of Texas at Austin was made possible under a limited license grant from the author who has retained all copyrights in the works.en
dc.subjectParametric kernelsen
dc.subjectStructured dataen
dc.subjectDistance metricsen
dc.subjectConventional learning algorithmsen
dc.subjectHandwritten character recognitionen
dc.subjectOn-line face recognitionen
dc.subjectObject detectionen
dc.titleParametric kernels for structured data analysisen
dc.typeThesisen
thesis.degree.departmentComputer Sciencesen
thesis.degree.disciplineComputer Sciencesen
thesis.degree.grantorThe University of Texas at Austinen
thesis.degree.levelDoctoralen
thesis.degree.nameDoctor of Philosophyen

Access full-text files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
shiny63148.pdf
Size:
1.38 MB
Format:
Adobe Portable Document Format

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.66 KB
Format:
Item-specific license agreed upon to submission
Description: