local learning rate adaptation 局部学习速率自适应
It is confirmed that PSO could overcome intrinsic shortcomings of BP neural network, including low learning efficiency, slow convergence rate, being easy to fall into local minima, etc.
经验证(PSO)优化算法可以有效地克服BP神经网络存在的学习效率低,收敛速度慢以及容易陷入局部极小点等固有缺点。
The method makes the neural network be self adaptive and difficult to become the local minimum, so that the convergence rate can be greatly speeded and the learning time shortened.
该方法使网络具有自适应能力,从而不易陷入局部最小,导致收敛速度大大加快,训练时间大大缩短。
The self-adaptive learning rate and momentum coefficient are used to avoid the local minimum point in the training process of wavelet neural network.
小波神经网络的训练采用自适应调整学习率及动量系数的方法,以避免陷入局部极小值。
应用推荐