图 G 的合适的全部的着色以便与 G 的一个周期那些顶点和边事件上有至少 4 种颜色，被称为非循环的全部的着色。G 的非循环的全部的色彩的数字是在 G 的非循环的全部的着色的颜色的最少的数字。在这份报纸，这被证明最大的度的平面图 G 的非循环的全部的色彩的数字至少 k 并且没有 l 周期，是至多(G)+ 2 如果( k ， l ){( 6 ， 3 )，( 7 ， 4 )，( 6 ， 5 )，( 7 ， 6 )}。
This paper is concerned with the theoretical foundation of support vector machines (SVMs). The purpose is to develop further an exact relationship between SVMs and the statistical learning theory (SLT). As a representative, the standard C-support vector classification (C-SVC) is considered here. More precisely, we show that the decision function obtained by C-SVC is just one of the decision functions obtained by solving the optimization problem derived directly from the structural risk minimization principle. In addition, an interesting meaning of the parameter C in C-SVC is given by showing that C corresponds to the size of the decision function candidate set in the structural risk minimization principle.
ZHANG ChunHua 1 , TIAN YingJie 2 & DENG NaiYang 3,1 School of Information, Renmin University of China, Beijing 100872, China
