File(s) not publicly available
A geometric method to improve the performance of the support vector machine
journal contribution
posted on 2023-06-08, 09:20 authored by Peter Williams, Sheng Li, Jianfeng Feng, Si WuThe performance of a support vector machine (SVM) largely depends on the kernel function used. This letter investigates a geometrical method to optimize the kernel function. The method is a modification of the one proposed by S. Amari and S. Wu. Its concern is the use of the prior knowledge obtained in a primary step training to conformally rescale the kernel function, so that the separation between the two classes of data is enlarged. The result is that the new algorithm works efficiently and overcomes the susceptibility of the original method
History
Publication status
- Published
Journal
IEEE Transactions on Neural NetworksISSN
1045-9227Publisher
Institute of Electrical and Electronics Engineers (IEEE)External DOI
Issue
3Volume
18Page range
942-947Department affiliated with
- Informatics Publications
Notes
Originality: Significantly improved a well-known method in machine learning for optimizing the kernel function of support vector machines, the current state-of-art pattern recognition method. Rigor: Applied the Information Geometry method to analyze the behaviours of kernel mapping. The new method was tested by real-world problem. Significance: this new method significantly improves the performance of the previous one, and makes this type of geometry-based method more robust and easier to use. Outlet/Citation: Top Engineering/Machine Learning journal. In press.Full text available
- No
Peer reviewed?
- Yes
Legacy Posted Date
2013-02-20Usage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC