The momentum and the delayed frequency adjustment were adopted in the learning algorithms to promote the convergence speed.
在学习算法中增加动量项并采用频率延迟调整策略,提高了算法的收敛速度。
参考来源 - 电参量自适应测量技术研究Chapter 4 presents an error back propagation algorithm with quadratic momentum of the multilayer forward neural networks that will speed up the error convergence velocity.
本文提出一种带二次动量项的多层前向网络误差反传算法，提高了神经网络的误差收敛速度。
参考来源 - 车辆悬架振动的神经网络半主动控制·2,447,543篇论文数据，部分数据来源于NoteExpress
附加动量项方法能减少震荡时间，提高网络的收敛速度。
The momentum item addition method reduces vibration time and accelerates the convergence of the neural network.
在BP算法中加入动量项和混沌映射，选择神经网络初值。
The momentum item and chaotic mapping was added into BP algorithm, and the initial value of the network was selected.
神经网络采用一种综合改进的BP网络，并进行了动量项自适应调整的改进。
A comprehensively improved BP neural network is adopted, and an improvement for momentum adaptive adjustment is carried out.
应用推荐