摘要
采用一种改进的人工神经网络反向传播算法(BP算法),将动量方法和可变学习速度的BP算法(VLBP算法)结合,并且在每个样本点更新权值和偏置值,这种算法称为动量VLBP算法。用C语言实现该算法,并将其运用到对一种新型组合式非周期性缺陷接地结构(CNPDGS)低通滤波器的神经网络建模之中。以CNPDGS的结构尺寸和频率为输入样本,传输系数参数为输出样本,建模成功后,在样本范围内输入结构尺寸和频率能够很快得出准确的传输系数。结果表明应用动量VLBP算法的神经网络相对于FDTD分析方法可以节省大量的时间,并且与基本的BP算法相比,可以加速算法收敛、减少训练时间。
An improved artificial neural network (ANN) model of lowpass filter with combinatorial nonperiodic defected ground structures (CNPDGS) is developed in this paper. The momentum VLBP algorithm used in the model integrates the momentum with the variable learning rate backpropagation (VLBP), updates the weight and the bias at each sample point, and is accomplished by C language. The structure size of CNPDGS and the frequency are defined as the input samples of the ANN model, the parameters of transmission coefficient are defined as the output samples. Within the range of training, the parameters of transmission coefficient can be obtained correctly and quickly from the model which has been trained successfully. The result indicates that the momentum VLBP algorithm is more timesaving than FDTD and more efficient than the basic BP algorithm.
出处
《微波学报》
CSCD
北大核心
2007年第6期36-39,共4页
Journal of Microwaves
基金
国家自然科学基金资助项目(编号:60371029)
关键词
神经网络
反向传播算法
组合式非周期性缺陷接地结构
动量VLBP
Artificial neural network, Backpropagation algorithm, Combinatorial nonperiodic defected ground structures, Momentum variable learning rate backpropagation