本文提出了类条件概率密度随机变量（特征）空间离散化及类条件概率分布估计方法。
A discrete method for stochastic variable (features) space of class-conditional-probability density and estimation method for class-conditional -probability distribution is proposed.
这意味着，在虚假设条件下，观察到X平方分布极限值 9.80的概率是 2％（这是一个相当低的概率）。
This means that the probability of observing a Chi Square value as extreme as 9.80 under the null hypothesis is 2 percent (which is quite a low probability).
利用拟生灭过程与矩阵几何解的方法求出了系统的稳态平衡条件和稳态概率分布。
By using the Quasi-Birth-Death process and the matrix geometric solution, we obtain the equilibrium conditions of the system and the steady-state probability distribution.
给出了排队平稳条件以及用矩阵迭代法得到了平稳队长分布和受阻概率分布。
The stationary condition and stationary queue length distribution are given in terms of matrix iterative solution. Block probability and block time probability distribution are given.
在得出港口货物吞吐量概率分布的基础上，利用条件数学期望提出了港口货物吞吐量的双层预测模型。
A double forecasting model is proposed by using conditional mathematical expectation, based on probability distribution of port cargo throughput.
条件受险价值是一种能够反映损失分布尾部信息，从而有利于防范小概率极端金融风险的风险度量和优化工具。
CVaR is a new tool for credit risk measurement and optimization, which provides the tail information of loss and is favorable to keeping away the extreme finance risk with very little probability.
利用在理想条件下的概率分布，计算了同步变长码的抗误码扩散概率。
By using the probability distribution in perfect condition, the error resiliency of synchronized variable length codes (SVLC) is counted.
请注意，明显兼容性条件，即这一边缘概率分布是在同一个班的一名来自全套随机过程，不是一个要求。
Note that the obvious compatibility condition, namely, that this marginal probability distribution be in the same class as the one derived from the full-blown stochastic process, is not a requirement.
从概率基本公式出发，在偏态分布的约束条件下，经数学推导；建立概率积分式。
From a probability basic equation through mathematical deduction, a probability integral equation is set up in constraint condition of non-normal distribution.
本文建立了不需要求边缘概率分布而直接从联合分布判别独立性的一个充要条件。
A necessary and sufficient condition for discriminating the independence of random variables directly from joint distribution instead of marginal probability distribution has been established.
推导了基于零件条件失效概率分布的共因失效概率模型；
A model for common cause failure probability was derived based on the distribution of the conditional failure probability of components.
研究了次级电子倍增条件以及次级电子出射角度和出射速度概率密度分布的特点。
The qualification of multipactor and the characteristic of the angle and velocity of secondary electron were study.
在保险风险和金融风险为重尾分布的条件下，得到了二维风险模型两种破产概率的精确估计以及另外一个破产概率的上下界。
Some precise estimates were made of two kinds of ruin probabilities of finite time with heavy- tailed insurance risk and financial risk.
其中有一个基本的假设条件：训练数据与测试数据来自相同的特征空间而且服从相同的概率分布。
There exists a basic assumption: the training data and test data are drawn from the same distribution and the same feature space.
其中有一个基本的假设条件：训练数据与测试数据来自相同的特征空间而且服从相同的概率分布。
There exists a basic assumption: the training data and test data are drawn from the same distribution and the same feature space.
应用推荐