What is the translation of " 的卷积网络 " in English?

• convolutional networks
• convolutional network

Examples of using 的卷积网络 in Chinese and their translations into English

用于大规模图像识别的非常深度的卷积网络.
Very deep convolutional networks for large-scale image recognition.

对抗性的PoseNet:一种对于人类姿态估计的结构感知的卷积网络.
Adversarial PoseNet: a structure-aware convolutional network for human pose estimation.

要完成，这是对我们更大的卷积网络的差异。
To finish, here is the difference dropout makes to our bigger convolutional network.

我们需要三个基本的元素来定义一个基本的卷积网络.
We need three basic components to define a basic convolutional network.

它主要专注于计算机视觉应用的卷积网络。
It focuses primarily on convolutional networks for computer vision applications.

目前主宰机器视觉的深层卷积网络的关键组成部分直接受到大脑的启发。
Critical ingredients underlying deep convolutional networks currently dominating machine vision were directly inspired by the brain.

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。
I created two simple convolutional networks, a“better” one, and a“worse” one.

以上就是所有的过程了：一个常规的卷积网络，以及后续对结果的一些处理。
And that's pretty much all there is to it: a regular convolutional network and a bit of postprocessing of the results afterwards.

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。
CONCLUSION In this work we evaluated very deep convolutional networks(up to 19 weight layers) for largescale image classification.

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

上面这些差不多就是这个意思：一个常规的卷积网络加上对结果的一系列处理。
And that's pretty much all there is to it: a regular convolutional network and a bit of postprocessing of the results afterwards.

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 have been central to the largest advances in image recognition performance in recent years.

首先，找到一种将数据转换成图像的方法；其次，使用一个经过预训练的卷积网络或者从头开始进行训练。
First, find a way to convert your data into images and second, use a pretrained convolutional network or train one from scratch.

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.
Very deep convolutional networks for large-scale image recognition(2014), K. Simonyan and A. Zisserman[pdf].

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。
This approach has proven just as effective and today's convolutional networks use convolutional layers only.

共享权重和偏置的一个很大的优点是，它大大减少了参与的卷积网络的参数。
A big advantage of sharing weights and biases is that it greatly reduces the number of parameters involved in a convolutional network.

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。
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.

就硬件要求而言，Alex在2个NvidiaGTX580GPU（速度超过1000个快速的小内核）上实现了非常高效的卷积网络。
In terms of hardware requirements, Alex used a very efficient convolutional network implementation on two Nvidia GTX 580 GPUs(more than 1000 fast small cores).

有趣的是，我们并没有这种类型的卷积神经网络或者Q网络（Q-Network）（应用于强化学习）或者传统的神经网络的记忆。
It's interesting to note that we don't have this type of memory with CNNs or with Q-networks(for reinforcement learning) or with traditional neural nets.

就硬件要求而言，Alex在2个NvidiaGTX580GPU(速度超过1000个快速的小内核)上实现了非常高效的卷积网络。
In terms of hardware requirement, Alex uses a very efficient implementation of convolutional nets on 2 Nvidia GTX 580 GPUs(over 1000 fast little cores).

图像的每一层在我们的卷积网络中表示为一个层。
Each layer of the image represents a layer in our convolutional network.

在传统的卷积网络中，每一层都会从之前的层提取信息，以便将输入数据转换成更有用的表征。
In a traditional conv net, each layer extracts information from the previous layer in order to transform the input data into a more useful representation.

即使是最简单的卷积神经网络也能更好地识别物体。
Even the simplest convolutional neural network recognizes objects better.

用于语音识别的卷积神经网络结构的研究和优化技术，2014。
Exploring convolutional neural network structures and optimization techniques for speech recognition, 2014.

我们已经讨论了LeNet，它是最早的卷积神经网络之一。
We discussed the LeNet above which was one of the very first convolutional neural networks.

它是一个大型的卷积神经网络，由K.Simonyan和A.
VGG16 is a Convolutional Neural Network model proposed by K. Simonyan and A..

最成功的深度学习网络是由YannLeCun开发的卷积神经网络（CNN）。
The most successful deep learning network is a convolutional neural network(CNN) developed by Yann LeCun.

该团队的卷积神经网络的简单性带来了更好的测试结果。
The team says the simplicity of their convolutional neural network resulted in better testing results.

在我们深入看实际的卷积网络之臆，我们先定义一个图像滤波器，或者称为一个赋有相关权重的方阵。
Before we look at the actual structure of convolutional networks, we first define an image filter, or a square region with associated weights.