Feature kernel functions: Improving SVMs using high-level knowledge

Qiang Sun, Gerald DeJong

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Kernel functions are often cited as a mechanism to encode prior knowledge of a learning task. But it can be difficult to capture prior knowledge effectively. For example, we know that image pixels of a handwritten character result from a few strokes from a single writing implement; it is not clear how to express this in a kernel function. We investigate an Explanation Based Learning (EBL) paradigm to generate specialized kernel junctions. These embody novel high-level features that are automatically constructed from the interaction of prior knowledge and training examples. Our empirical results showed that the performance of the resulting SVM surpasses that of a conventional SVM on the challenging task of classifying handwritten Chinese characters.

Original languageEnglish (US)
Title of host publicationProceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005
PublisherIEEE Computer Society
Pages177-183
Number of pages7
ISBN (Print)0769523722, 9780769523729
DOIs
StatePublished - 2005
Event2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005 - San Diego, CA, United States
Duration: Jun 20 2005Jun 25 2005

Publication series

NameProceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005
VolumeII

Other

Other2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005
CountryUnited States
CitySan Diego, CA
Period6/20/056/25/05

ASJC Scopus subject areas

  • Engineering(all)

Fingerprint Dive into the research topics of 'Feature kernel functions: Improving SVMs using high-level knowledge'. Together they form a unique fingerprint.

  • Cite this

    Sun, Q., & DeJong, G. (2005). Feature kernel functions: Improving SVMs using high-level knowledge. In Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005 (pp. 177-183). [1467439] (Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005; Vol. II). IEEE Computer Society. https://doi.org/10.1109/cvpr.2005.157