...LM学习算法; 权重初始化 [gap=934]r perceptron; fuzzy linear discriminant function; nonlinear activation function; LM learning algorithm; weightinitialization hypersphere ..
基于6个网页-相关网页
LM learning algorithm is adopted in BP network learning.
BP网络的学习采用了LM学习算法。
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。
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。
应用推荐