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操作称为积。

Moreover, separable deep convolution blocks were employed to enhance object feature information and reduce model computation.

此外，采用了可分离深度积块，以增强对象特征信息并减少模型计算量。

And one thing worth noticing is that as we do this convolution, it's possible to get negative values.

值得注意一件事是， 当我们进行积时，有可能得到负值。

This area is almost but not quite  the value of the convolution at s.

该面积几乎但不完全是 s 处积值。

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、积码和神经元也包括在内，还有扩展矩阵数学操作。

To find anything approaching the violence and convolution of Hardy's plots one must go back to the Elizabethan drama.

要找到任何接近哈代节暴力和错综复杂东西，我们必须回到伊丽莎白时代戏剧。

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，并缠绕着缠绕在心爱绳索。

And we spent a lot of time building up two distinct ways to visualize  what this convolution operation really is.

我们花了很多时建立两种不同方法来可视化这个积运算真正含义。

The  essence of what we want to compute is what the convolution between two  copies of this function looks like.

我们想要计算本质是这个函数两个副本之积是什么样子。

Once our smaller list of values entirely overlaps with the bigger one, think about what each term in this convolution really means.

一旦较小值列表与较大值列表完全重叠，请考虑此积中每一项真正含义。

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

甜美音乐飘进索比耳朵，把他吸引住了，他把身体紧紧地贴在那盘旋形铁栅栏上。

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，而不是一个一维输入列表，它就像一个积。

That second lesson is also meant to be the follow  on to the convolutions video that I promised.

第二课也是我承诺积视频后续课程。

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

第一个积层可能会找到边缘之类东西，因为这是单个积可以识别东西，正如我们已经讨论过那样。

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.

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

Not to mention, solving that system is certainly going to be computationally as difficult as just doing the convolution in the first place.

更不用说，解决该系统在计算上肯定会像最初进行积一样困难。

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神经元层处理，允许在积上进行积。

The architecture of MS-FRCNN is improved to detect lower-level features by incorporating feature maps from shallower convolution feature maps for regions of interest (ROI) pooling.

MS-FRCNN架构经过改进，通过在感兴趣区域（ROI）池化过程中融入更浅积特征图特征图，以实现对低级特征有效检测。

But the prose writer, without these restrictions, accumulated clauses, petered out in interminable catalogues, tripped and stumbled over the convolutions of his own rich draperies.

但是，散作家如果没有这些限制，就会积累大量条款，在无休无止目录中逐渐消失，在自己丰富帷幔盘旋中绊倒和绊倒。