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.
仿真结果显示，自然梯度算法比传统梯度算法收敛速度更快，分离效果更好。
Simulation results show that the natural gradient approach has faster convergence speed and better separation performance than the conventional gradient based algorithm.
本文在介绍了盲源分离的基础理论的基础上，对自然梯度算法进行了详细的介绍。
This paper describes the basic theory of blind source separation and natural gradient algorithm in detail.
自然梯度算法有收敛速度和稳定误差两个重要指标，然而这两个指标存在内在的矛盾。
In the natural gradient algorithm, the convergence speed and stability error are two important indicators, but these two indicators are of inherent contradictions.
所以我们又给出一种自适应修正自然梯度算法，用一个合适的距离测度函数来控制步长和动力因子。
So we present an adaptive improved natural gradient algorithm, which use an appropriate estimation function to control the step-size and the momentum factor.
为了解决自然梯度算法的这个缺点，人们提出了变步长自然梯度算法，既可以获得较快的收敛速度，又可以减小稳定误差。
Variable step-size natural gradient algorithm which enjoys faster convergence speed and smaller stability error is proposed to solve the shortcoming of natural gradient algorithm.
新算法具有与自然梯度算法相同的收敛速度，而且克服了已有算法不能稳定收敛的缺点。仿真验证了新算法的分离性能和收敛稳定性。
Finally, simulation proves the capacity to perform the blind source separation with an unknown number of sources and the convergent stability of the new algorithm.
基于自然梯度原则并利用信号的时间相关属性对一类代价函数进行推导，获得一种新的非平稳信号自适应盲分离算法。
A new adaptive blind source separation algorithm of non-stationary signals was presented by using natural gradient rule and time-correlation property of the source signals acting on a cost function.
给出了一个基于自然梯度的后非线性多信道盲解卷算法。
A natural gradient based algorithm for multichannel blind deconvolution of post-nonlinear mixtures is proposed.
丈中利用双梯度算法对自然图像的基向量进行迭代学习。
The basis vectors of the natural images were obtained by using fast conjugate gradient algorithm.
丈中利用双梯度算法对自然图像的基向量进行迭代学习。
The basis vectors of the natural images were obtained by using fast conjugate gradient algorithm.
应用推荐