在 中文 中使用 卷积网络 的示例及其翻译为 英语
{-}
-
Political
-
Ecclesiastic
-
Programming
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％。
On the basic 5-layer convolutional network, using 16-bit floats for everything, BNNS is about 25% faster than MPSCNN on my iPhone 6s.卷积网络并没有尝试去理解三维物体的结构，而且它们也不能识别不同的光照条件。
Convolutional networks make no attempt to understand three-dimensional object structures, and they can't correct for varying lighting conditions.在这项工作中，我们研究了卷积网络深度在大规模的图像识别环境下对准确性的影响。
In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting.OverFeat：使用卷积网络进行综合识别，定位和检测（2013），P.Sermanet等.[[PDF]]（WEB.
OverFeat: Integrated recognition, localization and detection using convolutional networks(2013), P. Sermanet et al.[pdf].与此同时，谷歌2013年的一篇论文描述了它如何使用深度卷积网络从谷歌街景(GoogleStreetView)的照片中读取地址码。
Meanwhile, a 2013 paper described how Google was using deep convolutional networks to read address numbers from photos in Google Street View images.然而，有一种类型的神经网络可以利用形状信息：卷积网络。
However, there is a type of neural 大多数现代图像分类系统都基于称为卷积网络的模型。
Most modern image classification systems are based on a model called convolutional networks.它讨论了深度学习的动机，深度神经网络，卷积网络以及文本和序列的深层模型。
It talks about the motivation for deep learning, deep neural 然后我将解释一种特殊神经网络--深层卷积网络--为什么它特别擅长理解图像。
And then I will explain why a particular type of neural 幸运的是，我们从MatthewZeiler的“可视化和理解卷积网络”及相关着作中获得了一些见解。
Fortunately, we have some insight from Matthew Zeiler's Visualizing and Understanding Convolutional Networks and related works.Hinton提出的最后也是最近期的根本变化是使用胶囊（请参阅原始论文）替代卷积网络。
A final, and very recent, fundamental change proposed by Hinton is the use of capsules( see original paper) as an alternative to Convolutional Networks.最后，课程涵盖了不同类型的深层架构，如卷积网络，循环网络和自动编码器。
Finally, the course covers different types of Deep Architectures, such as Convolutional Networks, Recurrent 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)。
In convolutional networks, these"stencils" are known as feature detectors, and the area they look at is called the receptive field.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。
We have seen that the feature detectors in 最后一层使用所有生成的特征来进行分类或回归（卷积网络的最后一层，本质上就是多项式逻辑回归）。
The final layer(s) use all these generated features for classification or regression(the last layer in a convolutional net is, essentially, multinomial logistic regression).全卷积网络.
Fully Convolutional Networks.卷积网络结构ConvolutionalArchitecture.
Typical convolutional network architecture.可视理解卷积网络及.
WEB Visualizing and Understanding Convolutional Networks.卷积网络在AlexNet中如何工作?
How convolutional networks worked in AlexNet?计算机视觉navigate_next全卷积网络.
Computer Visionnavigate_next Fully Convolutional Networks.
