权值 英语是什么意思 - 英语翻译

• weight
• weights
• weighted

在 中文 中使用 权值 的示例及其翻译为 英语

AKA权值和偏置。
Aka weights and biases.

看是否也能得到同样的权值。
See if they are of equal value.

那些这些权值就需要保存下来。
These values have to be preserved.

更新每个样本的权值.
Measuring the weight of each sample.

如果权值被初始化为0，则W矩阵将是：.
If the weights are initialized to 0, the W matrix will be:.

一个MLN只是一组逻辑公式及其权值。
An MIN is just a set of logical formulas and their weights.

Rhino也有检查和改变控制点权值的工具。
Rhino provides tools for examining and changing control point weights.

所有其他的例子都不相关，而且它们的权值都是零。
All other examples are irrelevant, and their weight is zero.

因此，对于每个权值做如下调整（来自公式（5）和（8））：.
So the adjustment to each weight will be(from Equations 5 and 8):.

此外，为了更新未展开网络的权值，我们必须再次传播误差。
Moreover, to update the weight of unfolded network, we have to propagate error once again.

如果想在网络中包括权值．单击Yes，否则跳到第13步。
Click Yes if you want to include weights in the network; otherwise, skip to step 13.

元学习算法本身可以是任意学习算法，从决策树到简单的权值投票。
The metalearner can itself be any learner, from a decision tree to a simple weighted vote.

在这种情况下，优化例子权值可以再次通过梯度降低的形式来确定。
In this case the optimal example weights can again be learned by a form of gradient descent.

也就是说，权值衰减在模型中不单单起到正则化作用；它还协助降低模型的训练错误率。
In other words, weight decay here is not merely a regularizer: it reduces the model's training error.

我们可以看到，CNN神经网络的隐层节点的连接权值参数可以共享。
We can see that the connection weight parameters of nodes on the hidden layer of a CNN neural network can be shared.

反向传播是梯度下降的一种形式，炼金术用它来优化马尔科夫逻辑网络权值。
Backpropagation is a form of gradient descent, which Alchemy uses to optimize the weights of a Markov logic network.

权值现在对我们来说意义不大，但我们将在下一节中使用这些数字来测试感知器。
The weights don't mean much to us right now, but we will use those numbers in the next section to test our perceptron.

同理，当计算机为两张图像建立相似度联系时，它将为这些相似度分配权值。
In a similar vein, when computers establish similarities between two images it assigns a weight to those similarities.

现在这些权值对我们来说并不重要，但是我们将在后面使用这些数字来测试我们的感知器。
The weights don't mean much to us right now, but we will use those numbers in the next section to test our perceptron.

增长核算的原理是，投入要素增长率的加权值是否大于产出的增长率。
The principle of growth accounting is to ascertain whether the weighted sum of factor growths is larger than the growth rate of total output.

如果我们引入权值上的高斯先验，那么我们就得到了第4章讨论过的模型。
If we introduce a Gaussian prior over the weight vector w, then we obtain the model that has been considered already in Chapter 4.

如果权值是常数,那么混合模型的参数可以由第9章讨论的EM算法确定。
If the weights were constant, then the parameters of the mixture model could be determined by using the EM algorithm discussed in Chapter 9.

他们将一种形式的权值共享应用在了一段电影评论的情感分析和与贫血症有关的生物医学搜索中。
They applied a form of weight sharing to a sentiment analysis of movie reviews and to a biomedical search related to anemia.

相反，联结学派更喜欢用一个简单、手工编写的结构，加上许多连接行为，然后让权值学习来完成所有工作。
In contrast, connectionists prefer to take a simple, hand-coded structure with lots of connections and let weight learning do all the work.

神经网络经常需要处理不同大小的输入矩阵和权值矩阵，它们的维度常常不满足矩阵相乘的规则。
Neural networks frequently process weights and inputs of different sizes where the dimensions do not meet the requirements of matrix multiplication.

在第二阶段，算法计算一个错误，然后将此错误从最后一层反向传播（调节权值）到第一层。
In the second phase, the algorithm computes an error, and then backpropagates this error(adjusting the weights) from the final layer to the first.

不幸的是，这样做只会让权值不受限制地增长，因为从数学的角度讲，权值越大，边际越大。
Unfortunately, this would just make the weights grow without limit, because mathematically, the larger the weights, the larger the margin.

终极算法既不是遗传编程，也不是反向传播，但它得包含这两者的重要部分：结构学习和权值学习。
The Master Algorithm is neither genetic programming nor backprop, but it has to include the key elements of both: structure learning and weight learning.

大多数人工神经网络有两个共同点:大量的权值，本质上是网络在训练中学习的可调参数;
Most artificial neural networks have two things in common: a huge number of weights, which are essentially the tunable parameters that networks learn during training;

量化过程基本上是将机器学习模型中权值的大小从32位浮点权值减少到16位或8位的精度。
What quantization basically does is reducing the size of the weights in a machine learning model, from 32-bit floating point weights to 16 or 8-bit precision.