1) weight optimal initialization
![点击朗读](/dictall/images/read.gif)
初始权值优化
1.
Furthermore, a weight optimal initialization method is introduced for improving performance of the soft-sensing model.
针对回归神经网络训练效率低,泛化能力差等问题,尝试引入一种初始权值优化方法加以改进。
2) optimization of initial weights and threshold values
![点击朗读](/dictall/images/read.gif)
初始权值和阈值优化
3) optimal weights initialization technology
![点击朗读](/dictall/images/read.gif)
初始权值优化技术
1.
Also a novel optimal weights initialization technology is proposed so that the sample sets and initial weights can match perfectly.
针对移动机器人建立了基于BP神经网络的智能避障控制模型,提出了初始权值优化技术,使得样本组与初始权值相匹配,显著地提高了网络的收敛速度。
2.
Based on multiplayer feed-forward neural networks using BP algorithm, considering the fluctuation of initial weights and sample sets, a novel optimal weights initialization technology is proposed for the sake of matching between initial weights and sample sets.
本文在采用BP学习算法的多层感知器的基础上,考虑初始权值的波动和样本组的因素,提出了初始权值优化技术,以提高初始权值与样本组的匹配能力。
4) optimized initial value
![点击朗读](/dictall/images/read.gif)
优化初始值
1.
Modeling variance is used to find the optimized initial values with the method of minimum modeling variation in GM(1,1) model.
依据建模方差2δ最小的原则,对传统GM(1,1)模型的初始值进行改进,提出基于优化初始值的GM(1,1)模型。
5) weight initialization
![点击朗读](/dictall/images/read.gif)
权值初始化
1.
A novel learning algorithm is proposed that is based on the combination of independent component analysis(ICA)based weight initialization and automatically adjusting the gain parameter of sigmoid activation function.
提出了一种基于独立元分析(ICA)方法的权值初始化方法和动态调整S型激励函数的斜率相结合的神经网络学习算法。
补充资料:因侵害姓名权、肖像权、名誉权、荣誉权产生的索赔权
因侵害姓名权、肖像权、名誉权、荣誉权产生的索赔权:公民、法人的姓名权、名称权,名誉权、荣誉权、受到侵害的有权要求停止侵害,恢复名誉,消除影响,赔礼道歉,并可以要求赔偿损失。
说明:补充资料仅用于学习参考,请勿用于其它任何用途。
参考词条