在这个工作,有为 BP 神经网络的动量的一个坡度方法被考虑。动量系数以一种适应方式被选择加速并且稳定网络重量的学习过程。相应集中结果被证明。
In this work, a gradient method with momentum for BP neural networks is considered. The momentum coefficient is chosen in an adaptive manner to accelerate and stabilize the learning procedure of the network weights. Corresponding convergence results are proved.