这是一个快速的拟牛顿法程序，非常实用，非常强大-FMINLBFGS is a Memory efficient optimizer for problems such as image registration with large amounts of unknowns, and cpu-expensive gradients. Supported: - Quasi Newton Broyden–Fletcher–Goldfarb–Shanno (BFGS). -

计算梯度下降法计算极值，只能找到局部最小点。可以通过调整步长实现全局最小-Calculation of gradient descent method to calculate extreme value, can only find local minimum point. By adjusting the step size can achieve the global minimum