What is the translation of " 循环神经网络 " in English?

• recurrent neural networks
• recurrent neural network

Examples of using 循环神经网络 in Chinese and their translations into English

但是，循环神经网络有一个问题。
Recurrent Neural Networks have one problem though.

循环神经网络.
The Recurrent Neural Network.

循环神经网络（RNN）可以解决这类问题。
Recurrent Neural Networks(RNNs) can solve this kind of problems.

用于语音识别循环神经网络(RobinsonandFallside,1991)。
Recurrent neural network for speech recognition(Robinson and Fallside, 1991).

它融入了变分推理，并将超网络用作循环神经网络细胞。
It incorporates variational inference and utilizes hypernetworks as recurrent neural network cells.

循环神经网络的不可思议的效用，2015.
The Unreasonable Effectiveness of Recurrent Neural Networks, 2015.

循环神经网络实现”.
The“ Implementation of the Recurrent Neural Network.

理解如何构建并训练循环神经网络（RNN），以及一些广泛应用的变体，例如GRU和LSTM.
Understand how to build and train Recurrent Neural Networks(RNNs), and commonly-used variants such as GRUs and LSTMs.

在本课程的下一部分中，您需要重新审视循环神经网络最流行的应用之一--语言建模。
In the next section of the book, we are going to revisit one of the most popular applications of recurrent neural networks- language modeling.

这场革命的领导者是循环神经网络，特别是其LSTM模型的表现。
The leader of this revolution has been the recurrent neural network and particularly its manifestation as an LSTM.

现在，我们来解释循环神经网络是如何应用到与金融相关的任务上的。
Now, let's explain how recurrent neural networks can be applied to a finance-related task.

对于循环神经网络，信号可能会多次经过同一层，CAP的深度可能是无限的。!
For a recurrent neural network, a signal might propagate through a layer more than once, so the CAP depth is potentially unlimited!

这需要将许多不同的技术组合在一起，包括循环神经网络、web应用程序、模板、HTML、CSS，当然还有Python。
This requires bringing together a number of different technologies including recurrent neural networks, web applications, templating, HTML, CSS, and of course Python.

未来研究的一个方向是要在管理器层引入循环神经网络架构。
One future direction is to introduce a recurrent neural network architecture at the Manager level.

卷积神经网络通常用于处理图像，而循环神经网络（RNN）用于处理语言。
While convolutional neural networks are typically used for processing images, recurrent neural networks(RNNs) are used for processing language.

虽然结果并不总是完全正确，但它们确实表明循环神经网络已经掌握了英语基础。
While the results are not always entirely on-point, they do show the recurrent neural network has learned the basics of English.

循环神经网络（RNN）能够从序列和时序数据中学习特征和长期依赖关系。
Recurrent neural networks(RNNs) are capable of learning features and long term dependencies from sequential and time-series data.

我们正在探索这个方向非常具体，主要与与深层神经网络和循环神经网络以及其他类型的机器学习有关。
We're exploring this very specific direction having to do with deep neural networks and recurrent neural networks and other kinds of machine learning.

简介：我将讲解深度学习用于自然语言处理时的基础知识：词向量、循环神经网络、受语言学影响的任务和模型。
I will describe the foundations of deep learning for natural language processing: word vectors, recurrent neural networks, tasks and models influenced by linguistics.

受到机器学习集成技术（machinelearningensembletechniques）的启发，该系统使用了一系列卷积和循环神经网络。
Inspired by machine learning ensemble techniques, the system uses a range of convolutional and recurrent neural networks.

我们请数据科学家NeelabhPant向大家来讲述他使用循环神经网络预测汇率变化的经验。
We asked a data scientist, Neelabh Pant, to tell you about his experience of forecasting exchange rates using recurrent neural networks.

现在，让我们来看看几种不同的循环神经网络，首先从非常简单的概念开始.
Let's now take a tour of the different types of recurrent neural networks, starting with very simple conceptions.

此外，其它不同类型的深度学习模型，比如循环神经网络也许能在这个任务中达到更好的结果。
Furthermore, different types of deep learning models, such as recurrent neural networks might achieve better performance on this task.

序列模型：隐藏马尔可夫模型、循环神经网络（RNN）、长短期记忆神经网络（LSTMs）.
Sequence models: Hidden Markov models, recursive neural networks(RNNs), Long short term memory neural networks(LSTMs).

然而对于音乐，我们需要对时间序列做分析，所以我们使用了循环神经网络。
But for music, we need the time sequence, and thus we should use RNN.

在完全连接和卷积网络之后，您应该看看循环神经网络。
After fully-connected and convolutional networks, you should have a look at recurrent neural networks.

循环神经网络建模能力：循环神经网络（RNNs）被用于语音识别，时间序列预测，图像描述和其他需要处理时序信息的任务。
RNN Modeling Capability: Recurrent neural networks(RNNs) are used for speech recognition, time series prediction, image captioning, and other tasks that require processing sequential information.

在循环神经网络中，训练过程中在更少的先前时间步上进行更新（沿时间的截断反向传播，truncatedBackpropagationthroughtime）可以缓解梯度爆炸问题。
In recurrent neural networks, updating across fewer prior time steps during training, called truncated Backpropagation through time, may reduce the exploding gradient problem.