后验

The uncertainties of the parameter estimation are analysed in terms of the posterior probability distributions of inversion results.

最后利用参数的后验概率分析反演结果的不确定性。

When it comes to the non-parameter density estimation technique for characterizing the region feature distribution, it also takes the collective distribution into consideration because of inaccurate segmentation.

此外，在应用非参数密度估计技术来构造语义类的特征分布时，针对区域分割的不精确性，该文还考虑了区域特征空间的总体分布因素，进而对区域的后验分布进行更可靠地估计。

Two different global localization methods based on Bayesian estimation theory are mainly investigated in the paper.

文中侧重研究了两种以贝叶斯概率后验估计理论为基础的全局定位方法。

Provided that the initial prior intensity of the states is Gaussian or can be identified as a Gaus- sian sum, the analytical results of the algorithm show that the posterior intensity at any subsequent time step remains a Gaussian sum under the assumption that the state noise, the measurement noise, target spawn intensity, new target birth intensity, target survival prob- ability, and detection probability are all Gaussian sums.

分析的结果表明，当初始的先验强度满足高斯或者可以表示成高斯和的形式时，通过将状态噪声、观测噪声、目标的繁衍、新目标的产生、目标的存活概率和检测概率表示成高斯和的形式，之后每个时刻的后验强度均能表示成高斯和形式。

So people are more interested in the researches of observation model and the impoverishment problem.

在实际的视觉跟踪过程中，后验概率的分布往往是非线性、非高斯、多模态的。

The main contents include: Some preliminary theory (introduction to Sobolev spaces and variational formulations for differential equations); finite element methods for one-dimensional elliptic problems; the construction methods for general finite elements; error estimates for interpolation operators and inverse inequalities for finite element spaces; a priori and a posteriori error estimates for the finite element method for high-dimensional elliptic problems; some typical spectral methods for partial differential equations; error analysis for the spectral approximation for some linear and nonlinear partial differential equations.

主要内容有：准备知识（Sobolev空间的基本概念和主要结果，微分方程的变分描述）；一维椭圆型方程有限元方法；一般有限元的构造；插值算子误差估计和逆不等式；高维椭圆型方程的先验、后验误差估计；求解偏微分方程的几类谱方法；线性与非线性问题谱逼近的误差分析等。

The inverse of condition number is recommended as a good prior criterion for choosing response positions in least squares approach.

条件数的倒数在最小二乘法响应点的选取时可作为优选的先验判据，归一化残差可作为估算质量的后验判据。

The inverse of condition number is recommended as a good a priori criterion for choosing response positions in least squares approach.

条件数的倒数在最小二乘法响应点的选取时可作为优选的先验判据，归一化残差可作为估算质量的后验判据。

Dempster et al (1983) assumed that logit of the historical rates is normally distributed. Bayesian methods are applied to obtain a P-value of the posterior probability of a positive dose-response slope. The authors indicated that their Bayesian approach is asymptotically equiva- lent to the large sample test of Tarone.

Dempster et a1（1983）假设历史对照患癌率的Logit服从正态分布，应用Bayesian方法给出了递增剂量反应斜率后验概率的P-值，并且指出，这种Bayesian方法与Tarone（1982）的检验在大样本时是渐近等价的。

The probabilistic methodology of inversion consists of evaluation of likelihood function and calculation of posterior probability.

根据贝叶斯理论给出了对含噪声地球物理数据处理的具体流程和方法，主要包括似然函数估计和后验概率计算。

With Death guitarist Schuldiner adopting vocal duties, the band made a major impact on the scene.

随着死亡的吉他手Schuldiner接受主唱的职务，乐队在现实中树立了重要的影响。

But he could still end up breakfasting on Swiss-government issue muesli because all six are accused of nicking around 45 million pounds they should have paid to FIFA.

不过他最后仍有可能沦为瑞士政府&议事餐桌&上的一道早餐，因为这所有六个人都被指控把本应支付给国际足联的大约4500万英镑骗了个精光。