In 1995 V.N.Vapnik and his colleagues first present support vector machine, it is a new generation of machine learning algorithm based on statistical learning theory, also is a great achievement of machine learning in recent years. The advantage of support vector machine (SVM) is mainly embodied in solving linear inseparable problem, by introducing nonlinear feature mapping which kernel function defines, SVM first maps the samples into a high-dimensional feature space, thereby nonlinear problem can be solved very well. According to the statistical learning theory, this nonlinear transform is through the proper kernel function k(x,x i ) realized in the algorithm, as long as the kernel functions can satisfy the Mercer conditions and without knowing its specific forms. © 2012 Springer-Verlag London Limited.
CITATION STYLE
Wu, X., Tang, W., & Wu, X. (2012). Support vector machine based on hybrid kernel function. In Lecture Notes in Electrical Engineering (Vol. 154 LNEE, pp. 127–133). https://doi.org/10.1007/978-1-4471-2386-6_17
Mendeley helps you to discover research relevant for your work.