该算法将实际问题通过非线性变换到高维的特征空间，在高维空间中构造线性判别函数，以替换原空间中的非线性判别函数，这样能保证机器有较好的推广能力，同时它巧妙地解决了维数问题，其算法复杂度与样本维数无关-The algorithm will be practical problems through the nonlinear transformation to high-dimensional feature space, in high-dimensional space in the structure of linear discriminant function to replace the original space of nonlinear discriminant function, it can guarantee the machine has better generalization ability At the same time, it is cleverly solved the problem dimension, the algorithm complexity has nothing to do with the sample dimension