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。
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.
针对直接矢量控制感应电机感应电机调速系统 ，设计和训练一个三层前馈神经网络以估计系统的实际转子磁链和单位矢量 ，并由此构成系统的闭环控制。
This paper designed and trained a three-layer fee dforward neural network to estimate the actual rotor flux and unit vector ford irect vector controlled induction motor speed drive.
讨论了利用仅含一个隐层的前馈多层神经网络来辨识离散时间非线性动态系统时的模型检验问题。
This paper investigates the problem of the model validation in identifying discrete-time-nonlinear dynamic systems by using neural networks with a single hidden layer.
非毗邻层连接的前馈神经网络结构有极快的收敛速度。
The front feedback nerve network structure of not-adjacent layer conjunction has splitting velocity on convergence.
结果表明，非毗邻层连接的前馈神经网络结构有优越的识别性能和极快的收敛速度。
The result indicates that the front feedback nerve network structure of not-adjacent layer conjunction has predominant function on identify and splitting velocity on convergence.
从网络结构上看，它是一种混合型的神经网络，由下面三层的前馈网络和上层的反馈网络组成。
The network structure of PBCA is a mixed structure composed of feed-forward network and feedback network.
从网络结构上看，它是一种混合型的神经网络，由下面三层的前馈网络和上层的反馈网络组成。
The network structure of PBCA is a mixed structure composed of feed-forward network and feedback network.
应用推荐