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

这堆海量的信息需要卷积神网络来处理。

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

作者引用了典的学习算法，使用个卷积神网络。

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

研究中使用了三维卷积神网络。

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

这通常是用典的名为卷积神网络的机器学习术完成的。

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

如今，最火的新算法是卷积神网络。

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

这应该听起来有点熟悉，因为它很像次卷积。

It's similar to the story of RNNs and CNNs, of RNNs and CovNets.

这RNN（循环神网络）和CNN（卷积神网络）的故事类，RNNCovNets的对比。

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、卷积码和神元也包括在内，还有扩展的矩阵数学操作。

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

然而，这并不是传统的卷积神网络算法，因为正如我们曾提到的，它的输入是2D，输出是3D。

For example, convolutional neural networks have been used to extract features and classify drone images, achieving good recognition results.

例如，卷积神网络已被用于对无人机图像进行特征提取和分类，取得了良好的识别效果。

Deep learning models, such as convolutional neural networks (CNN), have shown great capabilities in processing image data.

深度学习模型， 例如卷积神网络（CNN），在处理图像数据方面表现出了强大的能力。

The results show that ResNet101 performed better than VGG16 (Visual Geometry Group 16) convolutional neural network.

结果表明，ResNet101的表现优于VGG16（视觉几何组16层）卷积神网络。

Sometimes when  students see the definition of a convolution out of context, it can seem a little intimidating.

有时当学生在没有上下文的情况下看到卷积的定义时，可能会觉得有点吓人。

In image data, long-distance dependencies are typically modeled by the large receptive fields formed through deep stacks of convolutional operations.

在图像数据中， 长距离依赖性通常由通过深度卷积运算堆栈形成的大感受野建模。

There's some added steps with carries and the like but the core step is a convolution.

有些额外的进位步骤之类的，但核心步骤是卷积。

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

这些输出随后由后续的神元层处理，从而实现卷积的卷积的卷积。

The loss function and the anchors in the RPN of the convolutional neural network were optimized.

卷积神网络中的区域提议网络（RPN）内的损失函数和锚点得到了优化。

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

但是这次不样了，因为通过学习算法、卷积神网络和 siamese 网络，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.

他们使用叫做深度卷积神网络的东西来做到这点，并用个包含大约130,000张图像的数据集来训练它。

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

此外，采用了可分离深度卷积块，以增强对象特征信息并减少模型计算量。