gnn

GNN Model of Environment Dynamics in Force Telepresence System

力觉临场感系统中环境动力学的遗传神经网络模型

Neural net constructional method of function approximation of GNN

G神经网络函数映射能力的构造性证明

In addition , a new accelerating genetic operator was introduced to improve the convergence of GNN .

另外，设计了一个新的加速遗传算子，可以提高实数遗传算法的收敛速度。

The results of training and simulation are relatively stable with GNN model and the R2 ranges from 0.6572 to 0.8724 .

GNN模型的训练和模拟结果相对BPNN模型要稳定一些，其R2值在0.6572到0.8724之间。

Group nearest neighbor ( GNN ) query is a novel form of nearest neighbor search in spatial databases .

组最近邻居查询是空间数据库在最近邻居查询上的新问题。

GNN ( Genetic Neural Network , GNN ) is obtained by using genetic algorithm to optimize neural network which is trained by BP algorithm .

GNN（GeneticNeuralNetwork，GNN）是通过将遗传算法与BP网络耦合获得。

This paper explores the application of the genetic neural network ( GNN ) in the link capacity control of the asynchronous transfer mode ( ATM ) .

研究遗传神经网络算法在异步转移模式（ATM）链路容量分配中的应用。

In comparison with conventional BP network , GNN has the following advantages : ( 1 ) Network topology and its learning parameters can be learned by itself ;

同传统的BP网络相比，GNN具有如下优点：（1）网络拓扑结构和学习参数可通过学习获得；

In this paper , the function approximation of Gelenbe Neural Network ( GNN ) is discussed and it is proved that GNN can approximate any G-type polynomial by using constructional method .

该文研究了G神经网络的函数映射能力，给出了前馈G神经网络映射任意G型多项式的构造性证明。

The GNN removed some outliers or noises in the dataset by grid technique and disposed of density threshold of grid by density threshold method . The GNN clustered by the method of shared nearest neighbor and improved the efficiency by the use of the grid center .

该算法主要利用网格技术去除数据集中的部分孤立点或噪声，使用密度阈值处理技术来处理网格的密度阈值，使用中心点技术提高聚类效率。