分析了动态递归神经网络系统辨识的参数学习算法。
The parameter learning algorithm of dynamic recurrent neural network based on system identification is analyzed. D.
分析了动态递归神经网络系统辨识的参数学习算法。
The parameter learning algorithm of dynamic recurrent neural network based on system identification is analyzed.
提出了部分层学习算法，并推导出隶属度函数的参数学习算法，改善了诊断规则和学习性能。
Meanwhile, parameter learning algorithm of the membership function is developed. Both of them improve diagnostic rules as well as learning properties.
理论分析说明这种模糊规则后件参数学习算法是收敛的、所建模糊模型能够以要求的精度逼近已知的实验数据。
The learning algorithm and the characteristics of the fuzzy rules model which can approximate the experiment data are shown to converge to any arbitrary accuracy by the theoretical analysis.
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.
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