The application of Scaled Conjugate Gradient Algorithm makes the neural networks converge more quickly and accurately.
神经网络预测技术中，选择共轭梯度法作为训练算法，在很大程度上提高了神经网络的收敛速度和精度。
参考来源 - 基于神经网络的短期负荷预测A boundary identification problem, i. e. , inverse geometry problem of two-dimensional heat conduction was solved by using boundary element method (BEM) and conjugate gradient method (CGM)-based inverse algorithm.
采用基于边界元法和共轭梯度法的反演算法求解二维导热边界识别问题,即几何反问题。
参考来源 - 一种基于边界元离散的导热问题几何边界识别算法·2,447,543篇论文数据，部分数据来源于NoteExpress
Conjugate Gradient; Sufficient Descent Property; Convergence.
共轭梯度，充分下降，收敛性。
For this theory, it is better than the traditional fixed damping conjugate gradient method.
从理论上讲，它要优于传统的固定阻尼共轭梯度法。
The numerical results show that, the conjugate gradient method can solve the absorption coefficient well in one dimensional system.
数值计算的结果表明，共轭梯度法可以比较好的反演辐射系统的吸收系数。
应用推荐