Title :
Error analysis of classifiers in machine learning
Author :
Ding, Lei ; Sheng, Bao-Huai
Author_Institution :
Dept. of Math., Shaoxing Univ., Shaoxing, China
Abstract :
The paper is related to the error analysis of Support Vector Machine (SVM) classifiers based on reproducing kernel Hilbert spaces. We choose the polynomial kernels as the Mercer kernel and give the error estimate with De La Vallée Poussin means which improve the approximation error. On the other hand, the distortion is replaced by the uniformly boundedness of the Cesàro means. We also introduce the standard estimation of the sample error, and derive the explicit learning rate.
Keywords :
Hilbert spaces; error analysis; learning (artificial intelligence); pattern classification; support vector machines; Hilbert spaces; Mercer kernel; SVM; approximation error; classifier; error analysis; machine learning; polynomial kernels; support vector machine; Approximation error; Error analysis; Estimation; Kernel; Polynomials; Support vector machines;
Conference_Titel :
Image and Signal Processing (CISP), 2010 3rd International Congress on
Conference_Location :
Yantai
Print_ISBN :
978-1-4244-6513-2
DOI :
10.1109/CISP.2010.5646324
