损失函数

  • 网络loss function;Loss-function;cost function
损失函数损失函数
  1. Huber损失函数集的Vγ维

    On the v_ γ dimension of the set of Huber loss function

  2. 相对损失函数下期望向量的线性Minimax估计

    The linear Minimax Estimators of expected vector under relative loss function

  3. 分类中软间隔损失函数的Vγ维

    On the V_ γ dimension of soft margin loss functions in classification

  4. 一种基于损失函数的SVM算法在P2P流量检测中的应用

    Risk Function-based SVM Algorithm and its Application in P2P-traffic Detection

  5. 基于损失函数的SVM算法及其在轻微故障诊断中的应用

    Risk function based SVM algorithm and its application to a slight malfunction diagnosis

  6. 给出了在熵损失函数下,指数分布参数的Bayes估计.在给出先验分布的条件下,得到了Bayes估计的精确形式.证明了此估计是可容许的

    In this paper , Bayes estimation under entropy loss function under

  7. NA样本下非对称损失函数截尾参数的经验Bayes检验

    Empirical Bayes Test for Truncation Parameters with Asymmetric Loss Functions Using NA Samples

  8. Levy分布参数估计的损失函数和风险函数的Bayes推断

    Bayes Inference for the Loss and Risk Function in Levy Distribution Parameter Estimation

  9. ε-不敏感损失函数下的Bayes估计方法

    Bayes Estimation with ε - insensitive Loss

  10. 基于塔古奇损失函数和AHP法的供应商评选机制研究

    Study of mechanism of evaluation and selection system of suppliers based on Taguchi loss functions and analytic hierarchy process

  11. 如果基于VAR损失函数的真实性检验评估,EWMA模型较优。

    If based on the VaR loss function by reality check , the EWMA is better .

  12. 首先介绍了常用的做法,即取共轭分布β(a,b)作为先验分布,给出了在平方损失函数下的经验贝叶斯估计,并用与以往不同的方法研究了其渐近最优性。

    Firstly , we introduce the common method , and give out empirical Bayes estimation under the square loss function when conjugate distribution is the prior distribution , then its asymptotic optimality is discussed with the different method .

  13. 与其他判别训练算法不同,MSR算法直接使用阶梯形函数作为其损失函数。

    Unlike other discriminative methods , MSR directly takes a step function as its loss function .

  14. 为实现对设备轻微故障的正确识别和及时诊断,该文提出了一种基于损失函数的支持向量机(SVM)算法。

    In order to identify the slight mulfunction of facility correctly and timely , a Support Vector Machine ( SVM ) algorithm based on risk function is put forward .

  15. 在进行SVR回归时,使用鲁棒的Huber损失函数。

    In SVR regression , we use the Huber loss function due to its excellent robustness .

  16. 二项分布参数的经验Bayes估计Ⅰ&损失函数为(p-d)~2的情况

    Empirical Bayes Estimates for Binomial Parameters I & the Case of Loss Function ( p-d ) ~ 2

  17. 针对回声状态网络(EchoStateNetwork,ESN)模型易受异常点影响的问题,本文提出一种基于Huber损失函数的鲁棒岭回归方法。

    Focusing on the problem that ESN ( Echo State Network ) is sensitive to outliers , this paper proposes a Robust ridge regression method by using Huber loss function .

  18. 本文研究了方差分量模型中在平方和损失函数和矩阵损失函数下回归系数的线性Bayes估计。

    In this paper , Bayes linear estimates of regression coefficient in a variance component model are studied both under the quadratic loss function and matrix loss function .

  19. 针对伽玛分布族Γ(θ,1/2),在加权平方损失函数下,得到了其参数θ的经验Bayes估计及其收敛速度。

    In this part , we obtain the empirical Bayes estimation for the parameter of the gamma distribution families Y (θ, 1 / 2 ), and obtain convergent rate .

  20. 通过应用递推最小二乘(RLS)技术来最小化损失函数,得到了用于求解最大广义特征值对应的广义特征向量的自适应算法。

    By applying recursive least-squares technique to minimize the cost function , an adaptive algorithm is proposed for finding the most dominant generalized eigenvector .

  21. 基于加权损失函数下的EWMA控制图

    EWMA Chart Based on Weighted-Loss-Function

  22. 结果损失函数中虚警损失和漏检损失的比值不同导致整个系统的性能(虚警率和检测率)不同,与N-P准则相比较,贝叶斯方法能够充分利用先验知识和样本知识。

    Results Different ratios of the loss of false alarm to the loss of non - detection resulting in different system performance . Compared to N - P criterion , Bayesian method can make use of the prior knowledge and the sample knowledge .

  23. 研究了支持向量机(SVM)在二次损失函数下的优化问题解的形式,并与普通的最小二乘(LS)估计问题进行了比较,得到了几乎完全一致的优化问题形式。

    This paper compares the solution of a support vector machine ( SVM ) using a quadratic cost function with the least squares method which has a form similar to the SVM .

  24. 引入一广义损失函数J′,在噪声模型能估计的条件下,应用损失函数最小法能确定模型的阶次。

    By introducing a generalized loss function J ' and using minimal loss function , the order of linear dynamic system can be determined under the condition that the noise model is available .

  25. 最后我们可以看到,指数损失函数下的最优贝叶斯估计在特殊情况下(c→0的极限情况)就是经典的平方损失函数下的最优贝叶斯估计。

    And we can see that in the special case of c → 0 , the best estimator under exponential loss function is also the mean of the posterior structure function , which corresponds to the classical exact credibility result using a quadratic loss function .

  26. 将该模型用于某机组振动烈度的预示,进行了不同核函数和不同C值和ε值的比较,证明采用径向基函数和适当的损失函数,取得了较好的预测效果。

    The SVM model has been applied to the fault trend prediction of the vibration from a machine set . Through comparing different kernel functions and parameters C and ε, good prediction results have been obtained by using radial base functions ( RBF ) and proper loss functions .

  27. 本文将贝叶斯,经验贝叶斯理论应用于双指数分布族的刻度参数估计和Weibull分布的损失函数和风险函数的估计。

    In this thesis . Bayesian and empirical Bayesian theory are used to estimate the scale parameter of the double exponential distribution and the loss function and risk function of the Weibull distribution .

  28. 简要介绍了贝叶斯参数估计的基本原理,并在选择绝对型损失函数的基础上,给出了最小绝对值误差估计器(minimummeanabsoluteerror,简称MMAE)的实现方法。

    The main principle of Bayes parameter estimation is briefly introduced in this paper . Based on choosing absolute error function as the cost function , the realization methods of minimum mean absolute error ( MMAE ) are derived .

  29. 在两种相对损失函数下,我们给出了线性估计在线性估计类中的唯一的线性Minimax估计。

    In this paper , the authors get a unique linear Minimax estimator of linear estimator about β in the class of linear estimator under two relative loss function , respectively .

  30. C-Z型估计量关于损失函数的稳健性

    Robustness of C-Z Type Estimators on the Loss Function