Multi-Community Detection Algorithm Based on Network Weight(NW) 基于网络权重(NW)的多社团网络结构划分算法
This paper improves the algorithm of B P neural network. After finding out the relation between the single layer neural network weight matrix and the fuzzy comprehensive decision relation matrix, a fuzzy neural network system is constructed. 改进了B-P神经网络的算法结构,找到了单层神经网络权值矩阵与模糊综合评判关系矩阵之间的对应关系,由此构造了模糊神经网络系统。
The influence of primary network weight on final assessment result could be eliminated by symbolic statistics. 应用数理统计方法消除了网络学习初始权重对评价结果的影响。
Firstly, the BP neural network topology and learning algorithm were studied. For the defects of easily trapping into local minima, genetic algorithm was adopted to optimize the neural network weight and thresholds, and their work flow chart was given. 首先分析了BP神经网络的拓扑结构和学习算法,针对其学习速度慢、易陷入局部极小等缺陷,采用了遗传算法优化神经网络的权值和阈值,并给出其工作流程图。
Based on the combination of genetic algorithm and BP neural network, this paper establishes the genetic neural network for predicting milling forces by using the method of genetic algorithm training the neural network weight. 论文在遗传算法与BP网络模型相结合的基础上,利用遗传算法训练神经网络权重(NW)的方法,建立了铣削力预测的遗传神经网络模型。