PTNT algorithm converges like LM algorithm, with a storage complexity far less than half of the latter.
PTNT算法具有类似于LM算法的收敛性，但存储复杂度远远少于LM的一半。
Based on LM algorithm of an artificial neural network, a model for fault warning diagnosis of wind power units has been established.
基于人工神经网络LM算法，建立了风力发电机组故障预警诊断模型。
The output feedback pole assignment problem is transformed to a least square problem. The feedback matrix can be obtained by using LM algorithm.
将输出反馈极点配置问题转化为非线性最小二乘问题，用LM方法解出具有最小范数的反馈矩阵。
Simulation results illustrate that LM algorithm speed up learning process and reduce training time greatly. The identification effect is very good.
仿真结果表明LM算法可大大地提高学习速度，缩短训练时间，且辨识效果很好。
The way double polarity s function and LM algorithm combine with BP neural network is analyzed in the paper. The steps of new algorithm were given.
分析了双极性S型函数及LM算法与BP神经网络具体结合实现的方法，并给出了算法步骤。
According to the practical superelevation data measured with single-axis gyroscope platform, the designed non-linear neural network is trained with LM algorithm.
根据陀螺平台实测超高数据，采用LM算法对所设计的非线性神经网络进行训练。
Concerned with the training process and accuracy, the LM algorithm is superior to conjugate gradient algorithm and a variable learning rate back propagation (BP) algorithm.
就训练次数与精确度而言，它明显优于共轭梯度法及变学习率的BP算法，适用于系统辨识。
To achieve a higher convergent speed, the forecasting model adopts Levenberg-Marquardt(LM) algorithm, and the model adopts early stop method to improve extended capacity of the model.
在预测模型中采用LM算法提高网络的收敛速度，并采用提前停止法提高网络的推广能力。
To achieve a higher convergent speed, the forecasting model adopts Levenberg-Marquardt(LM) algorithm, and the model adopts early stop method to improve extended capacity of the model.
在预测模型中采用LM算法提高网络的收敛速度，并采用提前停止法提高网络的推广能力。
应用推荐