自然梯度算法是其中非常重要的算法之一。
Natural gradient algorithm is one of the most important algorithms.
然而，变步长自然梯度算法性能仍然不够理想。
However, the performance of variable step-size natural gradient algorithm is still less than ideal.
分离系统的线性部分和非线性部分参数学习都采用自然梯度算法。
The natural gradient method is applied for parameter learning of the linear and nonlinear parts of the separating system.
应用推荐