THE LOSS FUNCTION - 翻译成中文

• 损失函数
• loss function

在 英语 中使用 The loss function 的示例及其翻译为 中文

We need a way to calculate just“how much” wrong it is, and that is done by the loss function.
我们需要一种方法以计算其错误的“具体程度”，而这一目标需要通过loss函数实现。

Evaluation is essentially the loss function.
评估基本上就是损失函数。

The gain function is different from the loss function.
本质上是其lossfunction不同。

The loss function is the negative log likelihood.
损失函数还是选择negativelog-likelihoodfunction：.

Then the loss function can be rewritten as.
则损失函数可重写为：.

The picture below represents the loss function f(w).
下图描述了损失函数f（w）。

And we also use a binary cross entropy as the loss function.
因此，我们使用交叉熵作为损失函数。

The optimizer's goal is to minimize the output value of the loss function.
优化器的目标是最小化损失函数的输出值。

Second-order methods use the second derivative(Hessian) to minimize or maximize the loss function.
二阶优化算法使用了二阶导数(也叫做Hessian方法)来最小化或最大化损失函数。

Next we calculate the slope of the loss function with respect to our weights and biases.
接着我们计算损失函数相对于权重和偏置的坡度。

Optimizer species how the model is updated based on the input data and the loss function.
优化器-这就是模型根据它看到的数据及其损失函数进行更新的方式。

An optimizer applies the computed gradients to the model's variables to minimize the loss function.
优化器将计算出的梯度应用于模型的变量以最小化loss函数。

We use categorical cross entropy as the loss function, which is widely used in classification problems.
交叉熵作为损失函数，在分类问题中被广泛应用。

Although the loss function depends on many parameters, one-dimensional optimization methods are of great importance here.
一维优化方法虽然损失函数取决于许多参数，一维优化方法在这里非常重要。

Although the loss function depends on many parameters, one-dimensional optimization methods are of great importance here.
尽管损失函数的值需要由多个参数决定，但是一维优化方法在这里也非常重要。

But if you really wanted to, the hard part is calculating the gradient of the loss function.
但是，如果你真的想这么做的话，最困难的部分就是计算损失函数的梯度。

When entering the optimal learning rate zone, you will observe a quick drop in the loss function.
当进入了最优学习率区域，你将会观察到在损失函数上一次非常大的下降。

Once we have the loss function, we can use an optimization algorithm in attempt to minimize the loss..
有了损失函数以后，我们就可以使用优化算法试图使其最小化。

At any point A, we can be calculate the first and second derivatives of the loss function.
在任何点A，我们可以计算损失函数的一阶和二阶导数。

We are seeking to minimize the error, which is also known as the loss function or the objective function..
我们正在寻求最小化的误差，这也被称为损失函数或目标函数。