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

这听起来应该有点耳熟，因为它很像卷积。

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卷积。

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、卷积码和神经元也包括在内，还有扩展的矩阵数学操作。

Humanity thus rises naturally out of humility, and twists the cords of love that in various convolutions entangle the heart.

人性因此从谦卑中自然而然地升起，并缠绕着缠绕在心间的爱的绳索。

For there drifted out to Soapy's ears sweet music that caught and held him transfixed against the convolutions of the iron fence.

甜美的音乐飘进索比的耳朵，把他吸引住了，他把身体紧紧地贴在那盘旋形的铁栅栏上。

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，而不是一个一维的输入列表，它就像一个卷积。

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

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

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.

这项技术用了卷积神经网络以完成类似的东西，但最终它并没有给出一副画面，而是一系列的卷积核心程序。

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，允许在卷积上进行卷积。

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卷积阈值的东西为代价。