误差 函数 英语是什么意思 - 英语翻译

• error function

在 中文 中使用 误差 函数 的示例及其翻译为 英语

误差函数的一个自然选择是误分类的模式的总数。
A natural choice of error function would be the total number of misclassified patterns.

它通过变分方法，使得误差函数达到最小值并产生稳定解。
Calculus of variations to minimize an error function and produce a stable solution.

交叉熵误差函数，其定义如下：.
The cross-entropy error function is defined as follows:.

Erf(x)代表的是误差函数.
Where erf(x) is the error function.

当我们队其进行最小化时，我们也把他称为代价函数，损失函数或误差函数。
When we are minimizing it, we may also call it the cost function, loss function, or error function.

级别1(默认值)，错误位置是误差函数被调用。
Level 1(the default), the error position is where the error function was called.

在很多情况下，选取合适的模型取决于散度测量、重构误差函数和施加先验的设计选型。
In a lot of cases, choosing the appropriate model comes down to the design choices of divergence measurement, reconstruction error function, and imposed priors.

当然，这不表示其他的误分类模式对误差函数的贡献也在减少。
Of course, this does not imply that the contribution to the error function from the other misclassified patterns will have been reduced.

这也促使各种形式的误差函数的使用，并回顾了主要算法的误差函数最小化。
It also motivates the use of various forms of error functions, and reviews the principal algorithms for error function minimization.

但是，网络误差依赖于每一个网络权重，误差函数非常、非常复杂。
However, network error depends on every network weight and the error function is much, much more complex.

本文描述了这些问题的结构，提出了g2o框架，一个开源C++框架，用于优化基于图像非线性误差函数。
This paper describes the general structure of such problems and presents gopt, an open-source C++ framework for optimizing graph-based nonlinear error functions.

这种方法的问题是，我们可能到达误差函数的一个局部最小值，而不是全局最小值。
The problem with this approach is that this way, we can hit a local minimum of the error function, but not the global one.

(2003)发现，对于分类问题，使用交叉熵误差函数的训练速度会比平方和误差函数更快，同时也提升了泛化能力。
(2003) found that using the cross-entropy error function instead of the sum-of-squares for a classification problem leads to faster training as well as improved generalization.

使用的目标误差函数为.
The objective function for the concentration error is given by.

Erfc(x)为互补误差函数.
Where erfc(x) is the complementary error function.

从而，总的误差函数为.
The total error function is then given by.

因此我们将选择另一种误差函数，被称为感知器准则（perceptroncriterion）。
We therefore consider an alternative error function known as the perceptron criterion.

因此感知器学习规则并不保证在每个阶段都会减⼩整体的误差函数。
Thus the perceptron learning rule is not guaranteed to reduce the total error function at each stage.

注意，这种情况下的误差函数是二次的，所以Newton-Raphson公式一步就能给出精确解。
Note that the error function in this case is quadratic and hence the Newton-Raphson formula gives the exact solution in one step.

在数学中，误差函数是S形的特殊函数（非基本），它出现在概率，统计和偏微分方程中。
Error Function In mathematics, the error function is a special function(non-elementary) of sigmoid shape which occurs in probability, statistics and partial differential equations.

这个被称为erf函数或error函数（不要与机器学习模型中的误差函数相混淆）紧密相关的计算。
And known as the erf function or error function(not to be confused with the error function of a machine learning model).

正如我们将在5.3节看到的那样，误差函数的梯度可以通过误差反向传播的方法高效地计算出来。
As we shall see in Section 5.3, it is possible to evaluate the gradient of an error function efficiently by means of the backpropagation procedure.

注意这仅仅把误差函数乘以了一个因子，因此等价于使用原始的误差函数。
Note that this simply multiplies the error function by a factor of 2 and so is equivalent to using the original error function.

当我们对其进行最小化时，我们也把它称为代价函数(costfunction)、损失函数(lossfunction)或误差函数(errorfunction).
When we are minimizing it, we may also call it the cost function, loss function, or error function..

在这章的后面环节我们将讨论选择这个误差函数的动机。
We shall discuss the motivation for this choice of error function later in this chapter.

这个函数之所以被称为“铰链”误差函数，是因为它的形状，如图7.5所示。
The hinge error function, so-called because of its shape, is plotted in Figure 7.5.

所以该平方误差函数的和可以作为基于假设高斯噪音分布的最大似然的结果。
Thus the sum-of-squares error function has arisen as a consequence of maximizing likelihood under the assumption of a Gaussian noise distribution.

Logistic误差函数与铰链损失都可以看成对误分类误差函数的连续近似。
Both the logistic error and the hinge loss can be viewed as continuous approximations to the misclassification error.

这是一个值得担心的问题，再后面我们将看到我们将重新审视误差函数，并做些修改。
This is a valid concern, and later we will revisit the cost function, and make some modifications.