在神经网络自学习过程中,引入了自适应学习速率和误差批处理法,加快了学习速度。
In the training process, the adaptive learning rate and error batch-mode process are introduced to accelerate the training rate.
与标准BP算法比较,该系统通过结合附加动量法和自适应学习速率形成新的BP改进算法。
Compared to the standard BP, this algorithm integrated the additional momentum method with the adaptive learning rate method.
对小波神经网络采用最速梯度下降法优化网络参数,并对学习率采用自适应学习速率方法自动调节。
In WNN the most fast grads descent methodology was adopted to adjust the network parameters and the learning rate by self adapting learning rate method.
应用推荐