1) initial value
初值，始值，起始值
2) weights initialization
初始权值
1.
The weights initialization of input floor and output floor are set by applying the loading weights of dependent variable and cause variable,the member of hidden nodes are set by applying factor numbers o.
采用非线性迭代偏最小二乘算法预处理数据,将得到主成分数、自变量和因变量的主成分数的权重以及主成分间的关系矩阵B,以此用来确定BP网络的隐节点数和输入层、输出层的初始权值以及隐节点的关联系数。
2.
The weights initialization and the member of hidden nodes are set by applying theloading weights and factor numbers of O-PLS algorithm.
介绍一种新的多变量数据预处理方法——正交信号修正(OSC)法,提出一种OSC与NIPALS算法结合的O-PLS算法,将该方法用于确定BP网络的基本结构,即确定BP网络的隐层数、节点数及其初始权值,由此建立了O-PLS-BP网络模型。
3) initial value
初始值
1.
A simple solution to initial value of impulse response in dynamic circuit;
动态电路冲激响应初始值的一种简易求法
2.
Teaching discussion about calculating the initial value of current and voltage in the linear dynamic circuit;
线性动态电路电流电压初始值计算的教学研究
3.
The structure principle of GM(1,1) was ananlyzed,the initial value and the background value was pointed out as GM(1,1) model key.
分析了GM(1,1)模型的构造原理,指出初始值和背景值是GM(1,1)模型建模的关键,利用最小二乘法原理和GM(1,1)模型传统预测公式改进了初始值,并利用GM(1,1)模型建模条件建立了新背景值计算公式,从而建立了既适应低增长指数序列,又适应高增长指数序列的集成GM(1,1)模型,实例计算结果表明集成GM(1,1)模型的模拟精度较原始GM(1,1)模型和单方面改进的GM(1,1)模型有较大提高且适应范围更广,为提高模型建模精度和适应范围提供了一个新的途径。
4) initial values
初始值
1.
This paper discusses the relationship of the circuit structure of dynamic circuit and the ordering of differential equation,effect of selection unknown variables on the solution of equation and the calculations of special solution and initial values.
分析了电路结构与微分方程阶次的关系 ,电路未知变量的选择对求解方程的影响 ,特解和初始值的计算方法。
2.
Firstly by making elementary row operations to matrixes, the highest order impuls of variables can be found, secondly , the lower order impulses and 0+ initial values can be determined in backward substitution.
本文提出了一种简单而又精确的CAD方法，该方法采用积分形式的结点方程，经对各系数矩阵进行基本行运算后，首先求出电路中所有量的最高阶冲激量，然后通过回代，能逐步求出其他阶冲激量及电路的0+初始值。
3.
Under the specific regular transformation, their equations in implicit function form and the relations between their non-linearized parameters and the characters of their inflection points are so similar that the initial values of their non-linearized parameters can be searched just the same.
从而可用完全相同的方法对它们的未线性化参数初始值进行搜索 ,以拟合隐函数曲线的 GNL法对它们进行最小二乘拟合 。
5) initial weight
初始权值
1.
Due to remarkable influence of initial weights on networks training speed, great attention is paid to selection of initial weights.
将BP算法和使用复合法修正初始权值的BP算法运用到CSTR模型中进行故障诊断。
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