还指出由于当前的连续小波神经网络主要使用传统BP神经网络的随机初始化方法和基于梯度的训练算法，因此存在收敛性差的缺点。
It is also indicated that current WNN has a poor convergence performance because of adopting the random initialization method and gradient training algorithm of traditional BP NET.
讨论了一类度分布在无标度网络和随机网络之间连续可调的网络模型。
Discusses a class of continuously variable network models which are heterogeneously distributed in between scale-free networks and random networks.
首先应用随机不连续面三维网络模拟技术建立不连续面分布的概率统计模型。
The probability distribution model of discontinuities is established through the three dimensional network modeling.
应用推荐