在神经网络自学习过程中,引入了自适应学习速率和动量法,加快了网络的收敛速度,提高了网络的辨识精度。
During the self learning process, the adaptive learning rate and momentum gene are introduced to accelerate the rate of convergence and advance the identify accuracy.
针对BP算法收敛速度慢的特点,在隐含层上加入了关联节点,改善了网络的学习速率和适应能力。
Aiming at the slow convergence rate of BP neural network, append a correlative node on hidden layer, improve the adaptive ability and rate of studying of neural network.
传统的强化学习模型在整个学习过程中使用恒定学习速率,导致在未知环境下收敛速度慢且适应性差。
The learning process use the constant learning rate in the traditional reinforce learning model, because of that robot learn in a low convergence speed and with the poor adaptation.
使用常规pid控制很难满足手指精确位置控制的要求,而采用依据BPNN原理设计成的常规单神经元pid控制器又因学习速率低,收敛速度慢,控制效果不能令人满意。
But if single neuron PID controller designed in terms of BPNN Theory is adopted, the control effect is not satisfactory because the learning rate and speed of convergence are slow.
详细地讨论了增益、学习速率、动量等网络参数对神经网络收敛速度和导数脉冲伏安法计算结果的影响。
The effects of neural network parameters including gain, learning rate, and momentum on network convergence and DPV computation results have been investigated.
本文讨论了非线性多组分液相色谱速率模型求解过程中两种不同的插值方式即线性插值和拉格朗日插值对模型计算结果收敛速度的影响。
Two interpolation methods, which are linear interpolation method and the Lagrange interpolation method, are compared for calculating the rate model of multi-component nonlinear liquid chromatography.
本文讨论了非线性多组分液相色谱速率模型求解过程中两种不同的插值方式即线性插值和拉格朗日插值对模型计算结果收敛速度的影响。
Two interpolation methods, which are linear interpolation method and the Lagrange interpolation method, are compared for calculating the rate model of multi-component nonlinear liquid chromatography.
应用推荐