说明：  计学习理论采用结构风险最小化（Structural Risk Minimization，SRM）准则，在最小化样本点误差的同时，最小化结构风险，提高了模型的泛化能力，且没有数据维数的限制。在进行线性分类时，将分类面取在离两类样本距离较大的地方；进行非线性分类时通过高维空间变换，将非线性分类变成高维空间的线性分类问题
(The Structural Risk Minimization (SRM) criterion is adopted in the calculation learning theory, which minimizes the sample point error while minimizes the structural risk, and improves the generalization ability of the model without the limitation of data dimension. When linear classification is carried out, the classification plane is taken at a place with a large distance from the two types of samples. When nonlinear classification is carried out, the nonlinear classification is transformed into a linear classification problem of high dimensional space through the transformation of high dimensional space)