This work uses a 3D convolutional neural network to accomplish this task.

研究中使用了神经网。

This is typically achieved by a classical machine learning technique that we call a convolutional neural network.

这通常是用一种经典的名为神经网的机器学习技术完成的。

The authors of the paper invoke a classical learning algorithm, a convolutional neural network to accomplish that.

作者引用了一种经典的学习算法，即使用一个神经网。

This operation, of applying a kernel to a patch of pixels, is call a convolution.

这种将内核应用于像素块的操作称为。

Today, the hot new algorithms on the block are Convolutional Neural Networks.

今天，最热门的新算法是神经网。

There is a huge amount of information that the convolutional neural network has to make sense of.

这一堆海量的信息需要神经网来处理。

Machine learning kernels such as LSTMs, convolutions, and neuron layers are included as well as an expanded set of matrix math operations.

机器学习内核，比如 LSTMs、码和神经元也包括在内，还有扩展的矩阵数学操作。

This should sound vaguely familiar, because it's a lot like a convolution.

这听起来应该有点耳熟，因为它很像。

These outputs are then processed by subsequent layers of neurons, allowing for convolutions on convolutions on convolutions.

然后这些输出由后续的神经元层处理，允许在上进行。

This controller operates on a coarse time scale, only twice each second and is trained via a deep convolutional neural network.

它在粗略时间刻度上运作，每秒运作次，经由一个深神经网来训练。

But not this time, because here, super effective descriptors are proposed automatically via a learning algorithm, a convolutional neural network and siamese networks.

但是这次不一样了，因为通过一种学习算法、神经网和 siamese 网，而自动生成了超级有效的描述符。

They did this using something called a deep convolutional neural network and trained it with a dataset containing about 130,000 images.

他们使用一种叫做深度神经网的东西来做到这一点，并用一个包含大约130,000张图像的数据集来训练它。

Convolutional neural networks aren't required to be many layers deep, but they usually are, in order to recognize complex objects and scenes.

神经网不需要有很多层，但通常是这样，以便识别复杂的对象和场景。

However, this is not your classical Convolutional Neural Network, because as we mentioned, the input is 2D and the output is 3D.

然而，这并不是传统的神经网算法，因为正如我们曾提到的，它的输入是2D，输出是3D。

This technique uses a convolutional neural network to accomplish something similar, but in the end, it doesn't give us an image, but a set of convolution kernels.

这项技术用了神经网以完成类似的东西，但最终它并没有给出一副画面，而是一系列的核心程序。

In fact, if we pass a neuron 2D pixel data, rather than a one-dimensional list of inputs, it's exactly like a convolution.

事实上，如果我们传递一个神经元 2D 像素数据，而不是一个一的输入列表，它就像一个。

The very first convolutional layer might find things like edges, as that's what a single convolution can recognize, as we've already discussed.

第一个层可能会找到边缘之类的东西，因为这是单个可以识别的东西，正如我们已经讨论过的那样。

The next layer might have neurons that convolve on those edge features to recognize simple shapes, comprised of edges, like corners.

下一层可能有神经元在这些边缘特征上进行以识别由边缘组成的简单形状，比如角。

It may give them a permanent taste for what is abstruse and infinitely subtle — at the expense of anything that doesn't pass an exaggerated threshold of convolution.

这可能会让他们对深奥和无限微妙的东西产生永久的兴趣——以牺牲所有没有通过夸大的阈值的东西为代价。

Convolutional Neural Networks use banks of these neurons to process image data, each outputting a new image, essentially digested by different learned kernels.

神经网使用这些神经元库来处理图像数据，每个神经元输出一个新图像，基本上由不同的学习内核消化。