On the basis of both adaptive BP algorithm and Newtons method, Quasi Newton algorithm with adaptive decoupled step and momentum (QNADSM) for feed-forward neural networks is derived.
基于输出层函数为线性函数的三层前馈神经网络，结合自适应步长和动量解耦的伪牛顿算法及迭代最小二乘法导出了一种混合算法。
We update sensitivities matrix by the quasi-Newton method after the first inversion.
在第一次反演之后，采用拟牛顿法更新灵敏度矩阵。
The disadvantages of quasi-Newton algorithm is the great memory, so for large problems, memory difficulties may be encountered.
拟牛顿算法的缺点是所需存储量较大，对于大型问题，可能遇到存储方面的困难。
应用推荐