交叉熵 英语是什么意思 - 英语翻译

• cross-entropy
• cross entropy

在 中文 中使用 交叉熵 的示例及其翻译为 英语

交叉熵损失函数使用梯度下降进行优化。
Cross-Entropy Loss functions are optimized using Gradient Descent.

在分类树中我们使用交叉熵和基尼指数。
In classification trees, we use cross-entropy and Gini index.

这里采用了交叉熵(cross-entropy)来作为costfunction。
Use Cross entropy as the cost function.

Logistic回归：模型，交叉熵损失，类概率估计。
Logistic regression: model, cross-entropy loss, class probability estimation.

在分类树中，我们使用交叉熵和Gini指数。
In classification trees, we use cross-entropy and Gini index.

然后我们实现交叉熵功能：.
Then we can implement the cross-entropy function:.

也称为交叉熵损失。
Also called the cross entropy loss.

如果我们处理分类结果，我们可能会使用交叉熵。
If we were dealing with a classification outcome, we might use cross-entropy.

对于分类任务，通常使用交叉熵损失函数。
In the classification task, the cross entropy loss function is commonly used.

现在，您可以以安全的方式计算交叉熵：.
And now you can compute your cross-entropy in a safe way:.

交叉熵的公式定义.
Formal definition of the cross-entropy.

交叉熵定义为.
The cross entropy is defined as.

为什么交叉熵是在分类问题中合适的定义距离？?
Why is the cross-entropy the right distance to use for classification problems?

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

大致说来，想法就是：交叉熵是对惊讶的测度。
Roughly speaking, the idea is that the cross-entropy is a measure of surprise.

我们引入了交叉熵基准测试来获得复杂多比特动力学的实验保真度。
We introduce cross-entropy benchmarking to obtain the experimental fidelity of complex multiqubit dynamics.

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

熵，交叉熵和KL-散度经常用于机器学习，特别是用于训练分类器。
Entropy, cross-entropy and KL-divergence are often used in machine learning, in particular for training classifiers.

交叉熵是一个用来比较两个概率分布p和q的数学工具。
Cross entropy is a mathematical tool for comparing two probability distributions p and q.

交叉熵是用来衡量我们的预测用于描述真相的低效性。
The cross-entropy is measuring how inefficient our predictions are for describing the truth.

我们也选择二进制--交叉熵作为损失（因为我们处理二进制分类）和准确性作为我们的评估指标。
We also choose binary- cross entropy as the loss(because we deal with binary classification) and accuracy as our evaluation index.

在本章中我们主要使用交叉熵代价函数来解决学习速度衰退的问题。
In this chapter we will mostly use the cross-entropy cost to address the problem of learning slowdown.

在训练循环中使用该代码训练数据计算精度和交叉熵（例如每10次迭代）：.
The accuracy and cross entropy are computed on training data using this code in the training loop(every 10 iterations for example):.

为了实现交叉熵，我们需要先添加一个新的占位符来输入正确答案：.
To implement cross-entropy we need to first add a new placeholder to input the correct answers:.

二分类问题：对数损失（也称为交叉熵）“_binarycrossentropy”。
Binary Classification(2 class): Logarithmic Loss, also called cross entropy or‘binary_crossentropy‘.

在这副图片当中，交叉熵被表示为一个具有两个权重的函数。
In this picture, cross-entropy is represented as a function of 2 weights.

损失函数（lossfunction，此处为「交叉熵」）的选择稍后会做出解释。
The choice of a loss function(here,"cross-entropy") is explained later.

由于真实分布是未知的，我们不能直接计算交叉熵。
Since the true distribution is unknown, cross-entropy cannot be directly calculated.