Tuning the SVM Parameters to Class Variability
The aim of the research reported in this paper was to investigate the performance of new variants of gradient ascent type using kernels algorithms in learning SVMs. The results of the comparative analysis based on a long series of tests point out that the new proposed variants are quite promising in improving both the learning rate and generalization capacities. Following, a brief presentation of the kernel-based SVMs in solving classification tasks presented in the second section, a new heuristic method for adaptive learning of SVM parameters together with the resulted algorithm are supplied in the third section of the paper. The performance of the proposed methods has been experimentally evaluated using a long series of tests, the derived conclusions being summarized in the final section of the paper.
No Reference information available - sign in for access.
No Citation information available - sign in for access.
No Supplementary Data.
No Article Media
Document Type: Research Article
Publication date: December 1, 2013
More about this publication?
- ADVANCED SCIENCE LETTERS is an international peer-reviewed journal with a very wide-ranging coverage, consolidates research activities in all areas of (1) Physical Sciences, (2) Biological Sciences, (3) Mathematical Sciences, (4) Engineering, (5) Computer and Information Sciences, and (6) Geosciences to publish original short communications, full research papers and timely brief (mini) reviews with authors photo and biography encompassing the basic and applied research and current developments in educational aspects of these scientific areas.
- Editorial Board
- Information for Authors
- Subscribe to this Title
- Ingenta Connect is not responsible for the content or availability of external websites