CONVOLUTIONAL NETWORKS in Chinese translation

• 卷积网络
• convolutional networks
• 神经网络

Examples of using Convolutional networks in English and their translations into Chinese

I created two simple convolutional networks, a“better” one, and a“worse” one.
我创建了两个简单的卷积网络，一个是“更好”的网络，另一个是“更差”的网络。

The first successful applications of Convolutional Networks were developed by Yann LeCun in 1990s.
LeNet：第一个成功的卷积神经网络应用，是YannLeCun在上世纪90年代实现的。

CONCLUSION In this work we evaluated very deep convolutional networks(up to 19 weight layers) for largescale image classification.
在这项工作中，我们评估了非常深的卷积网络（最多19个权重层）用于大规模图像分类。

This approach has proven just as effective and today's convolutional networks use convolutional layers only.
这种方法就是有效的，今天的卷积网络仅仅使用了卷积层。

Very deep convolutional networks have been central to the largest advances in image recognition performance in recent years.
摘要非常深的卷积网络已成为近年来图像识别性能最大进展的核心。

Very deep convolutional networks for large-scale image recognition(2014), K. Simonyan and A. Zisserman[pdf].
用于大规模图像识别的非常深的卷积网络（2014），K.Simonyan和A.Zisserman[[pdf]]（WEB.

Convolutional networks were inspired by biological processes in that the connectivity pattern between neurons resembles the organization of the animal visual cortex.
卷积神经网络受到生物过程的启发，因为神经元之间的连接模式类似于动物视觉皮层的组织。

This approach has proven just as effective and today's convolutional networks use convolutional layers only.
这种方法已被证明是同样有效的，而今天的卷积网络仅使用卷积层。

This approach has proven just as effective and today's convolutional networks use convolutional layers only.
这种方法被证明是有效的，当今的卷积网络仅仅使用了卷积层。

Last year Apple announced the Metal CNN and BNNS frameworks for creating basic convolutional networks.
去年，苹果发布了MetalCNN和BNNS框架，用于创建基本的卷积神经网络。

In convolutional networks, these"stencils" are known as feature detectors, and the area they look at is called the receptive field.
在卷积网络中，这些“模板”被称为特征检测器(featuredetector)，它们所观察的区域被称为接受域(receptivefield)。

This paper, titled“ImageNet Classification with Deep Convolutional Networks”, has been cited a total of 6,184 times and is widely regarded….
这篇论文，题目叫做“ImageNetClassificationwithDeepConvolutionalNetworks”，迄今被引用6184次，被业内普遍视为行业最重要的论文之一。

We have seen that the feature detectors in convolutional layers perform impressive pattern recognition, but so far I haven't explained how convolutional networks actually work.
我们已经看到卷积层中的特征检测器执行了牛逼的模式识别，但是到目前为止，我还没有解释卷积网络实际上是如何工作的。

Specifically, our experiments establish that state-of-the-art convolutional networks for image classification trained with stochastic gradient methods easily fit a random labeling of the training data.
具体来说，我们的实验证明了用随机梯度方法训练的、用于图像分类的最先进的卷积网络很容易拟合训练数据的随机标记。

A convolutional network is a specific kind of neural network well suited to identifying images and sensing patterns in them.
卷积网络是一种特殊的神经网络，非常适合于识别图像和感知其中的模式。

In this section I will explain what a convolutional network does and why the technique has become crucial to modern image recognition algorithms.
在本节中，我将解释卷积网络的作用，以及为什么这项技术对现代图像识别算法至关重要。

In particular, the continuous-filter convolutional network SchNet accurately predicts chemical properties across compositional and configurational space on a variety of datasets.
特别是，连续滤波器卷积网络SchNet准确地预测了各种数据集上的组成和配置空间的化学特性。

RPN is a fully convolutional network, trained end-to-end, that simultaneously predicts object boundaries and object scores at each detection.
RPN是一个全卷积网络，在每个位置同时预测目标边界和objectness得分。

In 2017, government and academic researchers used a standard convolutional network to detect cyclones in the data with 74% accuracy;
年，政府和学术研究人员使用标准卷积网络以74％的准确性检测数据中的气旋特征；.

On the basic 5-layer convolutional network, using 16-bit floats for everything, BNNS is about 25% faster than MPSCNN on my iPhone 6s.
对于基本的5层卷积网络，在我的iPhone6s上，使用16位浮点数，BNNS比MPSCNN快大约25％。