深度网络 in English translation

• deep network
• deep networks
• deep nets
• deep web
• deep net

Examples of using 深度网络 in Chinese and their translations into English

批量标准化：通过减少内部协变量转换加速深度网络培训（2015），S.Loffe和C.Szegedy[[pdf]]（WEB.
Batch normalization: Accelerating deep network training by reducing internal covariate shift(2015), S. Loffe and C. Szegedy[pdf].

神经网络(包括深度网络)通常需要仔细调整权重初始化和学习参数。
Neural networks including deep networks require careful tuning of weight initialization and learning parameters.

但辛顿并没有放弃，他在1986年证明了反向传播（backpropagation）这个概念可以训练这些深度网络。
Hinton didn't give up and in 1986 showed that the idea of backpropagation could train these deep nets.

大多数最好的深度神经网络拥有深度网络架构（很多非线性处理单元的图层）以实现更高的精确度。
Most of the best DNNs have deep network structures(many layers of nonlinear processing units) to achieve higher accuracy.

反过来，这将导致更快的卷积模型的训练，并最终，将有助于我们使用卷积层建立深度网络。
That, in flip, will lead to faster coaching for the convolutional mannequin, and, in the end, will assist us build deep networks using convolutional layers.

这些问题减少了，但仍然存在，尽管使用了大数据集和深度网络。
These problems are reduced, but still remain, despite the use of big datasets and Deep Nets.

在此研究中，我们调查了如何构建单个、可延展深度网络，能够贪婪的捕捉不同派别的艺术风格。
In this work we investigate the construction of a single, scalable deep network that can parsimoniously capture the artistic style of a diversity of paintings.

在过去十年里，新技术和对激活功能的一个简单调整使训练深度网络成为可能。
In the past decade new techniques and a simple tweak to the activation function has made training deep networks feasible.

YannLeCun大胆地预言，在不久的将来，每个人都将使用深度网络。
Yann LeCun boldly predicted that everyone would soon use Deep Nets.

事实上，导致目前深度学习成功的许多论文都是仔细的实证研究，其描述了深度网络训练的基本原则。
In fact, many of the papers leading to the current success of deep learning were careful empirical investigations characterizing principles for training deep networks.

他的研究兴趣包括非凸优化，稀疏/结构化的评估，深度生成模型，深度网络压缩。
His research interests include non-convex optimization, sparse/structured estimation, deep generative models, and deep network compression.

比如Yosinski就表示他正尝试「像理解动物甚至理解人类那样」去理解深度网络。
Yosinski, for example, says he is trying to understand deep networks“in the way we understand animals, or maybe even humans.”.

传统神经网络只包含2到3个隐藏层，而深度网络可能包含多达150个隐藏层。
A neural network may contain only 2- 3 hidden layers, whereas a deep network can have as many as 150 layers.

传统神经网络只包含2到3个隐藏层，而深度网络可能包含多达150个隐藏层。
There are 2- 3 hidden layers in the traditional neural networks, whereas the deep networks may have as many as 150.

在此论文中，我们考虑了使用成千上万个CPU核训练一个带有数十亿参数的深度网络的问题。
In this paper, we consider the problem of training a deep network with billions of parameters using tens of thousands of CPU cores.

传统神经网络只包含2到3个隐藏层，而深度网络可能包含多达150个隐藏层。
According to a Mathwork blog, traditional neural networks only contain 2-3 hidden layers, while deep networks can have as many as 150.

人类的能力并不只是将即时刺激映射成即时反应，就像深度网络或者昆虫那样。
Humans are capable of far more than mapping immediate stimuli to immediate responses, as a deep network, or maybe an insect, would.

传统神经网络只包含2到3个隐藏层，而深度网络可能包含多达150个隐藏层。
A traditional neural network contains only 2-3 hidden layers while deep networks can contain as much as 150 hidden layers.

DownpourSGC和SandblasterL-BFGS都增加了深度网络训练的规模和速度。
Downpour SGD and Sandblaster L-BFGS both increase the scale and speed of deep network training.

在过去的十几年中，新技术的出现和对激活函数的一种简单调整使得训练深度网络变得可行。
In the past decade new techniques and a simple tweak to the activation function have made training deep networks feasible.