说明：  简单的讲，所谓拟合是指已知某函数的若干离散函数值{f1,f2,…,fn}，通过调整该函数中若干待定系数f(λ1, λ2,…,λ3), 使得该函数与已知点集的差别(最小二乘意义)最小。如果待定函数是线性，就叫线性拟合或者线性回归(主要在统计中)，否则叫作非线性拟合或者非线性回归。表达式也可以是分段函数，这种情况下叫作样条拟合。
(Simply speaking, the so-called fitting refers to a function known to a number of discrete function values (f1, f2, ..., fn), by adjusting the number of undetermined coefficient function f (λ1, λ2, ..., λ3), makes the function and known points of difference (least squares significance) the smallest. To be determined if the function is linear, is called linear regression or linear regression (mainly in the statistics), otherwise known as non-linear fitting, or nonlinear regression. Expressions can also be a sub-function, this case is called spline fitting.)