| Literature DB >> 15787157 |
Wei Chu, Chong Jin Ong, S Sathiya Keerthi.
Abstract
The least square support vector machines (LS-SVM) formulation corresponds to the solution of a linear system of equations. Several approaches to its numerical solutions have been proposed in the literature. In this letter, we propose an improved method to the numerical solution of LS-SVM and show that the problem can be solved using one reduced system of linear equations. Compared with the existing algorithm for LS-SVM, the approach used in this letter is about twice as efficient. Numerical results using the proposed method are provided for comparisons with other existing algorithms.Mesh:
Year: 2005 PMID: 15787157 DOI: 10.1109/TNN.2004.841785
Source DB: PubMed Journal: IEEE Trans Neural Netw ISSN: 1045-9227