Geodesic Distance Kernels

Article Sidebar

PDF
Published: Jan 5, 2018
Keywords:
Finsler metrics, Hilbert spaces, non-symmetric kernels, weighted quasi-metric spaces

Main Article Content

Uraiwan Somboon*
Department of Mathematics, Faculty of Science, King Mongkut’s Institute of Technology Ladkrabang, Bangkok, Thailand
Praiboon Pantaragphong
Department of Mathematics, Faculty of Science, King Mongkut’s Institute of Technology Ladkrabang, Bangkok, Thailand
Sorin V. Sabau
School of Biological Science, Department of Biology, Tokai University, Sapporo Campus, Sapporo, Japan

Abstract

In this paper, the authors deals with non-symmetric kernels induced by weighted quasi-metrics on Hilbert spaces and they study their fundamental properties. These are new and original. Such kind of metrics is obtained from Finsler metrics for example. We show that the use of such kernels may provide a solution to the conflict between positive definiteness of the kernel and the curvature of the underlying space.


 Keywords:Finsler metrics, Hilbert spaces, non-symmetric kernels, weighted quasi-metric spaces


*Corresponding author:       Tel.: +66 91 7300313


E-mail: uraiwan.somboon@gmail.com

Article Details

How to Cite
Somboon*, U., Pantaragphong, P., & Sabau, S. V. (2018). Geodesic Distance Kernels. CURRENT APPLIED SCIENCE AND TECHNOLOGY, 17(1), 29–41. retrieved from https://li01.tci-thaijo.org/index.php/cast/article/view/128696
Issue
Vol. 17 No. 1 (2017)
Section
Original Research Articles

Copyright Agreement Statement

The corresponding author has to submit Copyright Agreement form after the article is accepted for publication in order to warrant that this contribution is original and that he/she has full power to make this grant. The author signs for and accepts responsibility for releasing this material on behalf of any and all co-authors.

 

The author(s) grant Current Applied Science and Technology a non-exclusive, irrevocable, royalty-free license to publish, reproduce, distribute, and archive the article in print and electronic form with effect if and when the article is accepted for publication. In the event that the article is withdrawn prior to acceptance or is declined, this agreement shall have no effect, and no party shall be bound by it.

 

The author(s) retain copyright of this article, including but not limited to the right to reproduce and distribute the article, to include it in a thesis or book, and to post it on an institutional or personal repository, provided that the original publication in Current Applied Science and Technology is properly cited.

 

 

 

References

[1] Feragen, A., Lauze, F. and Hauberg, S., 2015. Geodesic Exponential Kernels: When Curvature and linearity Conflict. Proceedings of Computer Vision and Pattern Recognition 2015, Boston, June 7-12, 3032-3042.
[2] Jayasumana, S., Hartley, R., Salzmann, M., Li, H. and Harandi, M., 2015. Kernel Methods on Riemannian Manifold with Gaussian RBF Kernels. IEEE Transaction on Pattern Analysis and Machine Intelligence, 37(12), 2464-2477.
[3] Sabau, S.V., Shibuya, K. and Shimada, H., 2014. Metric structures associated to Finsler metrics. Publicationes Mathematicae Debrecen, 84(1-2), 89-103.
[4] Vitolo, P., 1999. The Representation of Weighted Quasi-Metric Spaces. Rendiconti dell'Istituto di Matematica dell'Università di Trieste, XXXI, 95-100.
[5] Valette, A., Bekka, B. and Harpe, P.D., 2008. Kazhdan’s Property (T). New Mathematical Monographs.
[6] Burago, D., Burago, Y. and Ivanov, S., 2001. A course on Metric Geometry. American Mathematical Society.