What is the translation of " OUTPUT LAYER " in Chinese?

• 输出层
• 一个输出层

Examples of using Output layer in English and their translations into Chinese

There are 4 hidden layers and 1 output layer.
有4个隐藏层和1个输出层。

Once the operation is complete, the output layer will contain the prediction of the model.
一旦操作完成，输出层将包含模型的预测。

In this case, we will use a linear activation function at the output layer.
在这种情况下，我们将在输出层使用线性激活函数。

In between the input and the output layer, there are one or more hidden layers(Figure 5).
在输入和输出层之间,有一个或多个隐藏层(图5)。

Consider an I layer neural network, which has L-1 hidden layers and 1 output layer.
考虑一个L层神经网络，它具有L-1个隐藏层和1个输出层。

In the output layer, we use the sigmoid function, which maps the values between 0 and 1.
在输出层，我们使用sigmoid函数，它将0和1之间的值进行映射。

Later, in Chapter 6, we will sometimes use a softmax output layer, with log-likelihood cost.
后续在第6章中，我们有时会使用softmax输出层搭配log-likelihood代价函数。

When the output layer is a continuous variable, then the network can be used to do regression.
当输出层是一个连续变量时，那么该网络可被用于执行回归。

Likewise, we can use a similar operation to derive the yi node value from the output layer using the hj value.
同样，我们可以使用类似的操作，使用hj值从输出层派生yi节点值。

We can see that the fully connected output layer has 5 inputs and is expected to output 5 values.
我们可以看到，完全连接的输出层有5个输入，预期输出5个值。

In the simplest network, we would have an input layer, a hidden layer, and an output layer.
在最简单的网络中，我们将有一个输入层、一个隐藏层和一个输出层。

Output Layer: The output layer is the predicted feature, it basically depends in the type of model you're building.
输出层：输出层具有预测性，其主要取决于你所构建的模型类型。

In a feedforward network, information moves in only one direction from input layer to output layer.
在前馈神经网络中，信息只从一个方向移动，从输入层，通过隐藏层到输出层。

The rightmost or output layer contains the output neurons, or, as in this case, a single output neuron.
最右或者输出层包含了输出神经元，该例中只有一个输出神经元。

Finally, we can stack multiple deconvolutional layers to gradually grow our output layer to the desired size.
最后，我们可以堆叠多个解卷积层，逐渐将我们的输出层增长到所需的大小。

This can be done by placing the output layer of one task at a lower level(Søgaard& Goldberg, 2016)[29].
这可通过把一项任务的输出层放置在较低级别来完成(Søgaard&Goldberg,2016)[47]。

The model has 10 inputs, 3 hidden layers with 10, 20, and 10 neurons, and an output layer with 1 output..
该模型有10个输入，3个隐藏层，10个神经元，输出层有1个输出。

The last layer is the output layer, and the neurons in this layer output the final prediction or decision.
最后一层是输出层，这一层中神经元输出最终的预测或结果。

After the learning is done we can feed new objects to the network and see scores for each category in the output layer.
在学习过程结束之后，新的物体就能够送入这个网络，并且能够在输出层看到每个种类的分数。

The output layer contains a probability of life, which is based on a measurement of the input's similarity of the five solar system.
输出层包含一个“生命的概率”，它是基于输入与五个太阳系统目标相似度的测量。

In the image below, the simple neural net has four inputs, a single hidden layer with five parameters, and an output layer.
下图中，简单神经网络有四个输入，一个带有五个参数的隐藏层和一个输出层。

Like other neural networks, a CNN is composed of an input layer, an output layer, and many hidden layers in between.
像其他神经网络一样，CNN由一个输入层、一个输出层和中间的多个隐藏层组成。

Output layer F7 is composed of Euclidean Radial Basis Function units(RBF), one for each class, with 84 inputs each.
Output层由欧式径向基函数（EuclideanRadialBasisFunction）单元组成，每类一个单元，每个有84个输入。

Training begins by clamping an input sample to the input layer of t=1, which is propagated forward to the output layer of t=2.
整个训练开始于将输入样本数据赋到t=1的输入层，通过前向传播至t=2的输出层。

We also can use the TimeDistributed on the output layer to wrap a fully connected Dense layer with a single output..
我们也可以在输出层上使用TimeDistributed来装饰一个完全连接的Dense层，并且只带有一个输出。

The first, middle, and last layers of a neural network are called the input layer, hidden layer, and output layer respectively.
神经网络的第一层、中间层和最后一层分别称为输入层、隐藏层和输出层。

In a Feed-Forward neural network, the information only moves in one direction, from the input layer, through the hidden layers, to the output layer.
在前馈神经网络中，信息只从一个方向移动，从输入层，通过隐藏层到输出层。

The key differentiator is feedback within the network, which could manifest itself from a hidden layer, the output layer, or some combination thereof.
关键的区别在于网络内反馈，其表现形式可以是隐藏层、输出层或一些组合。

Image of a larger neural network, composed of many individual neurons and layers: an input layer, 2 hidden layers and an output layer.
大的神经网络的图像，由许多单独的神经元和层组成：一个输入层，两个隐藏层和一个输出层.