共轭梯度法（Conjugate Gradient）是介于最速下降法与牛顿法之间的一个方法，它仅需利用一阶导数信息，但克服了最速下降法收敛慢的缺点，又避免了牛顿法需要存储和计算Hesse矩阵并求逆的缺点，共轭梯度法不仅是解决大型线性方程组最有用的方法之一，也是解大型非线性最优化最有效的算法之一。 在各种优化算法中，共轭梯度法是非常重要的一种。其优点是所需存储量小，具有步收敛性，稳定性高，而且不需要任何外来参数-Conjugate Gradient method (Conjugate Gradient) is between the steepest descent method between Newton method and a method, it only USES a derivative information, but overcome the steepest descent method slow convergence of weakness, but also avoid the Newton law needs to storage and computing Hesse inverse matrix and shortcomings, Conjugate Gradient method is not only solve linear equations with most of the large method, and also one of the most effective solution large nonlinear optimization of one of the algorithm. In all kinds of optimization algorithm, the conjugate gradient method is very important. Its advantage is the storage capacity needed, it has small step convergence, high stability, and doesn t require any exotic parameters numerical experiment, this is the modern scientific computing of the answer above problem sets