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.
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.
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。
应用推荐