【论文翻译】Deep Learning

【论文翻译】Deep Learning

Yann LeCun∗ Yoshua Bengio∗ Geoffrey Hinton

深度学习

Abstract

Deep learning allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. These methods have dramatically improved the in speech recognition, visual object recognition, object detection and many other domains such as drug discovery and genomics. Deep learning discovers intricate structure in large data sets by using the backpropagation algorithm to indicate how a machine should change its internal parameters that are used to compute the representation in each layer from the representation in the previous layer. Deep convolutional nets have brought about breakthroughs in processing images, video, speech and audio, whereas recurrent nets have shone light on sequential data such as text and speech.

摘要

机器学习允许多个处理层组成的计算模型去学习具有多级抽象的数据表示。这些方法极大地提高了语音识别、视觉对象识别、目标检测和很多其他领域的技术水平，例如，药物发现和基因组学。深度学习通过使用反向传播算法来指出机器应该如何改变其用于从前一层的表示中计算每一层表示的内部参数，从而发现大数据集中的复杂结构。深度卷积网络在处理图像、视频、语音和音频方面取得了突破性的进展，而循环网络则对连续数据(如文本和语音)有所帮助。

正文

Machine-learning technology powers many aspects of modern society: from web searches to content filtering on social networks to recommendations on e-commerce websites, and it is increasingly present in consumer products such as cameras and smartphones. Machine-learning systems are used to identify objects in images, transcribe speech into text, match news items, posts or products with users’ interests, and select relevant results of search. Increasingly, these applications make use of a class of techniques called deep learning.
机器学习技术为现代社会很多方面提供动力：从网络搜索到社交网络的内容过滤，再到电子商务网站的推荐，它越来越多地出现在相机和智能手机等消费产品中。机器学习系统用于识别图像中的目标，将语音转录成文本，将新闻、帖子或产品与用户的兴趣匹配，以及选择相关的搜索结果。这些应用程序越来越多地使用一种被称为深度学习的技术。

Conventional machine-learning techniques were limited in their ability to process natural data in their raw form. For decades, con-structing a pattern-recognition or machine-learning system required careful engineering and considerable domain expertise to design a fea-ture extractor that transformed the raw data (such as the pixel values of an image) into a suitable internal representation or feature vector from which the learning subsystem, often a classifier, could detect or classify patterns in the input.
传统的机器学习技术在处理原始形式的自然数据方面受到限制。几十年来，构建一个模式识别或机器学习系统需要仔细的工程设计和相当多的领域专业知识来设计一个特征提取器，将原始数据（如图像的像素值）转换成合适的内部表示或特征向量，学习子系统，通常一个分类器，可以检测或分类输入中的模式。

Representation learning is a set of methods that allows a machine to be fed with raw data and to automatically discover the representations needed for detection or classification. Deep-learning methods are representation-learning methods with multiple levels of representa-tion,obtainedby composing simple but non-linear modules that each transform the representation at one level (starting with the raw input) into a representation at a higher, slightly more abstract level. With the composition of enough such transformations, very complex functions can be learned. For classification tasks, higher layers of representation amplify aspects of the input that are important for discrimination and suppress irrelevant variations. An image, for example, comes in the form of an array of pixel values, and the learned features in the first layer of representation typically represent the presence or absence of edges at particular orientations and locations in the image. The second layer typically detects motifs by spotting particular arrangements of edges, regardless of small variations in the edge positions. The third layer may assemble motifs into larger combinations that correspond to parts of familiar objects, and subsequent layers would detect objects as combinations of these parts. The key aspect of deep learning is that these layers of features are not designed by human engineers: they are learned from data using a general-purpose learning procedure.

表示学习是一组方法，它允许机器接收原始数据并自动发现检测或分类所需的表示。深度学习方法是具有多层表示的表示-学习方法，通过组合简单但非线性的模块来获得，每个模块将一个层次的表示(从原始输入开始)转换为一个更高、稍微抽象的层次的表示。有了足够的这种变换组合，就可以学习非常复杂的函数。对于分类任务，更高层次的表征放大了输入中对辨别很重要的方面，并抑制了不相关的变化。例如，图像以像素值数组的形式出现，在第一层表示中学习到的特征通常表示图像中特定方向和位置上的边缘的存在或不存在。第二层通常通过发现边缘的特殊安排来检测图案，而不考虑边缘位置的微小变化。第三层可以将图案组合成更大的组合，对应于熟悉对象的部分，随后的层将检测作为这些部分组合的对象。深度学习的关键在于，这些功能层不是由人类工程师设计的:它们是通过一种通用的学习过程从数据中学习的。
Deep learning is making major advances in solving problems that have resisted the best attempts of the artificial intelligence community for many years. It has turned out to be very good at discovering intricate structures in high-dimensional data and is therefore applicable to many domains of science, business and government. In addition to beating records in image recognition1–4 and speech recognition5–7, it has beaten other machine-learning techniques at predicting the activity of potential drug molecules8, analysing particle accelerator data9,10, reconstructing brain circuits11, and predicting the effects of mutations in non-coding DNA on gene expression and disease12,13. Perhaps more surprisingly, deep learning has produced extremely promising results for various tasks in natural language understanding14, particularly topic classification, sentiment analysis, question answering15 and language translation16,17.

多年来，人工智能界一直在努力解决一些问题，但深度学习在解决这些问题方面取得了重大进展。它已经被证明非常善于发现高维数据中的复杂结构，因此适用于科学、商业和政府的许多领域。除了打破图像识别和语音识别中的记录，它在预测潜在药物分子的活性、分析粒子加速器数据、重建脑回路、预测非编码DNA突变对基因表达和疾病的影响等方面胜过其他机器学习技术。或许更令人惊讶的是，深度学习已经在自然语言理解的各种任务中产生了非常有希望的结果，尤其是主题分类、情绪分析、问题回答和语言翻译。

We think that deep learning will have many more successes in the near future because it requires very little engineering by hand, so it can easily take advantage of increases in the amount of available computation and data. New learning algorithms and architectures that are currently being developed for deep neural networks will only accelerate this progress.

我们认为，在不久的将来，深度学习将取得更多的成功，因为它只需要很少的手工工程，因此它可以很容易地利用可用计算量和数据量的增加。目前正在为深层神经网络开发的新的学习算法和结构只会加速这一进展。

Supervised learning

监督学习

The most common form of machine learning, deep or not, is super-vised learning. Imagine that we want to build a system that can classify images as containing, say, a house, a car, a person or a pet. We first collect a large data set of images of houses, cars, people and pets, each labelled with its category. During training, the machine is shown an image and produces an output in the form of a vector of scores, one for each category. We want the desired category to have the highest score of all categories, but this is unlikely to happen before training. We compute an objective function that measures the error (or distance) between the output scores and the desired pattern of scores. The machine then modifies its internal adjustable parameters to reduce this error. These adjustable parameters, often called weights, are real numbers that can be seen as ‘knobs’ that define the input–output function of the machine. In a typical deep-learning system, there may be hundreds of millions of these adjustable weights, and hundreds of millions of labelled examples with which to train the machine.
机器学习最常见的形式是监督学习，无论是否深度。想象一下，我们想要建立一个系统，可以将图像分类为包含，房子、汽车、人或宠物的图像。我们首先收集房屋、汽车、人和宠物图像的大数据集，每一个都有其分类的标签。在训练过程中，机器会显示一个图像，并以分数向量的形式输出结果，每个类别对应一个分数。我们希望期望的类别在所有类别中得分最高，但这不可能在训练前发生。我们计算一个目标函数来度量输出分数和期望的分数模式之间的误差（或距离）。然后，机器修改其内部可调参数以减少此误差。这些可调参数，通常称为权重，是一个实数，可以看作是定义机器输入输出功能的“旋钮”。在一个典型的深度学习系统中，可能有数以亿计的可调权重，以及数以亿计的用于训练机器的标签示例。

To properly adjust the weight vector, the learning algorithm com-
putes a gradient vector that, for each weight, indicates by what amount the error would increase or decrease if the weight were increased by a tiny amount. The weight vector is then adjusted in the opposite direction to the gradient vector.
为了适当地调整权重向量，学习算法为每个权重计算一个梯度向量，该梯度向量表示如果权重稍有增加，误差会增加或减少多少。然后权沿与梯度向量相反的方向调整权重向量。

The objective function, averaged over all the training examp les,can be seen as a kind of hilly landscape in the high-dimensional space of weight values. The negative gradient vector indicates the direction of steepest descent in this landscape, taking it closer to a minimum, where the output error is low on average.

所有训练示例中的平均的目标函数可以被看作是丘陵景观在高维空间中的权重值。负梯度向量表示该景观中最陡下降的方向，使其更接近最小值，输出误差平均较低。负梯度向量表示了该景观中最陡下降的方向，使其更接近最小值，即输出误差平均较低的地方。

In practice, most practitioners use a procedure called stochastic gradient descent (SGD). This consists of showing the input vector for a few examples, computing the outputs and the errors, computing the average gradient for those examples, and adjusting the weights accordingly. The process is repeated for many small sets of examples from the training set until the average of the objective function stops decreasing. It is called stochastic because each small set of examples gives a noisy estimate of the average gradient over all examples. This simple procedure usually finds a good set of weights surprisingly quickly when compared with far more elaborate optimization techniques18. After training, the performance of the system is measured on a different set of examples called a test set. This serves to test the generalization ability of the machine — its ability to produce sensible answers on new inputs that it has never seen during training.

在实践中，大多数从业者使用的程序称为随机梯度下降(SGD)。这包括显示一些示例的输入向量，计算输出和误差，计算这些示例的平均梯度，并相应地调整权重。对训练集中的许多小样本集重复这个过程，直到目标函数的平均值停止下降。之所以称之为随机，是因为每个小样本集都给出了对所有样本平均梯度的噪声估计。与更为复杂的优化技术相比，这个简单的过程通常会以惊人的速度找到一组好的权重。在训练之后，系统的性能将在另一组称为测试集的例子上进行测试。这用于测试机器的泛化能力——它在训练中从未见过的新输入上产生合理答案的能力。

Many of the current practical applications of machine learning use linear classifiers on top of hand-engineered features. A two-class linear classifier computes a weighted sum of the feature vector components. If the weighted sum is above a threshold, the input is classified as belonging to a particular category.
目前许多机器学习的实际应用都在手工设计的特性之上使用线性分类器。一个二分类线性分类器计算特征向量分量的加权和。如果加权和高于阈值，则将输入分类为属于某个特定类别。

Since the 1960s we have known that linear classifiers can only carve their input space into very simple regions, namely half-spaces separated by a hyperplane. But problems such as image and speech recognition require the input–output function to be insensitive to irrelevant variations of the input, such as variations in position, orientation or illumination of an object, or variations in the pitch or accent of speech, while being very sensitive to particular minute variations (for example, the difference between a white wolf and a breed of wolf-like white dog called a Samoyed). At the pixel level, images of two Samoyeds in different poses and in different environments may be very different from each other, whereas two images of a Samoyed and a wolf in the same position and on similar backgrounds may be very similar to each other. A linear classifier, or any other ‘shallow’ classifier operating on raw pixels could not possibly distinguish the latter two, while putting the former two in the same category. This is why shallow classifiers require a good feature extractor that solves the selectivity–invariance dilemma — one that produces representations that are selective to the aspects of the image that are important for discrimination, but that are invariant to irrelevant aspects such as the pose of the animal. To make classifiers more powerful, one can use generic non-linear features, as with kernel methods, but generic features such as those arising with the Gaussian kernel do not allow the learner to generalize well far from the training examples. The conventional option is to hand design good feature extractors, which requires a considerable amount of engineering skill and domain expertise. But this can all be avoided if good features can be learned automatically using a general-purpose learning procedure. This is the key advantage of deep learning.

自20世纪60年代以来，我们就知道线性分类器只能将其输入空间分割成非常简单的区域，即由超平面分隔的半空间。但图像和语音识别等问题,需要对输入输出功能对无关的输入的变化不敏感,如一个目标的位置,方向或照明的变化,或音调的变化或口音的变化,对特定的微小变化非常敏感(例如,白狼和一种叫萨摩耶的类似狼的白色狗之间的区别)。在像素级上，两幅处于不同姿势和不同环境中的萨摩耶图像可能差别很大，而两幅位于相同位置且背景相似的萨摩耶和狼的图像可能非常相似。线性分类器或其他任何在其上运行的“浅”分类器无法区分后两幅图片，而将前两幅图像归为同一类别。这就是为什么浅分类器需要一个好的特征提取器来解决选择性不变性难题的原因。提取器可以产生对图像中对于辨别重要的方面具有选择性但对不相关方面（例如动物的姿态）不变的表示形式。为了使分类器更强大，可以使用一般的非线性特征，如核方法，但是一般的特征，比如那些由高斯核产生的特征，使学习者无法从训练示例中很好地概括。传统的选择是人工设计好的特征提取器，这需要大量的工程技术和领域专业知识。但是，如果可以使用通用学习过程自动学习好的功能，这一切都可避免。这是深度学习的关键优势。

A deep-learning architecture is a multilayer stack of simple modules, all (or most) of which are subject to learning, and many of which compute non-linear input–output mappings. Each module in the stack transforms its input to increase both the selectivity and the invariance of the representation. With multiple non-linear layers, say a depth of 5 to 20, a system can implement extremely intricate functions of its inputs that are simultaneously sensitive to minute details — distinguishing Samoyeds from white wolves — and insensitive to large irrelevant variations such as the background, pose, lighting and surrounding objects.
深度学习架构是简单模块的多层堆栈，其中所有(或大部分)模块都需要学习，其中许多模块计算非线性的输入-输出映射。堆栈中的每个模块都转换其输入，以增加表示的选择性和不变性。系统具有多个非线性层深度，例如深度5到20，系统可以实现非常复杂的函数的输入，而这些功能同时对微小的细节很敏感——区分萨摩耶和白色的狼,对背景、姿势、光线和周围物体等无关大变化不敏感。

Backpropagation to train multilayer architectures

反向传播训练多层架构

From the earliest days of pattern recognition, the aim of researchers has been to replace hand-engineered features with trainable multilayer networks, but despite its simplicity, the solution was not widely understood until the mid 1980s. As it turns out, multilayer architectures can be trained by simple stochastic gradient descent. As long as the modules are relatively smooth functions of their inputs and of their internal weights, one can compute gradients using the backpropagation procedure. The idea that this could be done, and that it worked, was discovered independently by several different groups during the 1970s and 1980s.
从早期的模式识别开始，研究人员的目标是用可训练的多层网络取代手工设计的特征，但是尽管它很简单，直到20世纪80年代中期，这个解决办法才被广泛理解。事实证明，多层网络结构可以通过简单的随机梯度下降来进行训练。只要模块是其输入和内部权值的相对平滑的函数，就可以使用反向传播程序计算梯度。20世纪70年代和80年代，几个不同的研究小组独立地发现了这一想法，并认为它可行。

The backpropagation procedure to compute the gradient of an objective function with respect to the weights of a multilayer stack of modules is nothing more than a practical application of the chain rule for derivatives. The key insight is that the derivative (or gradient) of the objective with respect to the input of a module can be computed by working backwards from the gradient with respect to the output of that module (or the input of the subsequent module) (Fig. 1). The backpropagation equation can be applied repeatedly to propagate gradients through all modules, starting from the output at the top (where the network produces its prediction) all the way to the bottom (where the external input is fed). Once these gradients have been computed, it is straightforward to compute the gradients with respect to the weights of each module.
计算目标函数关于多层模堆权重的梯度的反向传播过程只不过是导数链式法则的实际应用。关键的观点是，目标相对于模块输入的导数(或梯度)可以通过计算相对于该模块输出(或后续模块输入)的梯度来计算(图1)。反向传播方程可以被反复应用，在所有模块中传播梯度，从顶部的输出(网络产生预测的地方)一直到底部(外部输入的地方)。一旦计算出了这些梯度，就可以直接计算出相对于每个模块权重的梯度。

Many applications of deep learning use feedforward neural network architectures (Fig. 1), which learn to map a fixed-size input (for example, an image) to a fixed-size output (for example, a probability for each of several categories). To go from one layer to the next, a set of units compute a weighted sum of their inputs from the previous layer and pass the result through a non-linear function. At present, the most popular non-linear function is the rectified linear unit (ReLU), which is simply the half-wave rectifier f(z) = max(z, 0). In past decades, neural nets used smoother non-linearities, such as tanh(z) or 1/(1 + exp(−z)), but the ReLU typically learns much faster in networks with many layers, allowing training of a deep supervised network without unsupervised pre-training. Units that are not in the input or output layer are conventionally called hidden units. The hidden layers can be seen as distorting the input in a non-linear way so that categories become linearly separable by the last layer (Fig. 1).
深度学习的许多应用使用前馈神经网络架构（图1），该架构学习将固定大小的输入（例如，图像）映射到固定大小的输出（例如，几个类别中的每一个的概率）。为了从一层到下一层，用一组单元计算它们从上一层输入的加权和，并将结果传递给一个非线性函数。目前最流行的非线性函数是整流线性单元（ReLU），即半波整流器f（z）=max（z，0）。在过去的几十年里，神经网络使用更平滑的非线性，例如tanh（z）或1/（1+exp（−z）），但ReLU通常在多层网络中学习得更快，允许在无监督预训练的情况下训练深度监督网络。不在输入或输出层的单元通常称为隐藏单元。隐藏层可以被视为以非线性方式扭曲输入，使得类别可以由最后一层线性分离（图1）。

In the late 1990s, neural nets and backpropagation were largely forsaken by the machine-learning community and ignored by the computer-vision and speech-recognition communities. It was widely thought that learning useful, multistage, feature extractors with little prior knowledge was infeasible. In particular, it was commonly thought that simple gradient descent would get trapped in poor local minima — weight configurations for which no small change would reduce the average error.
在20世纪90年代末，神经网络和反向传播在很大程度上被机器学习社区所抛弃，被计算机视觉和语音识别社区所忽视。人们普遍认为，在缺乏先验知识的情况下学习有用的、多阶段的特征提取器是不可行的。特别是，人们普遍认为简单的梯度下降会陷入糟糕的局部最小权值配置中，对于这种配置，任何微小的变化都不能减少平均误差。

In practice, poor local minima are rarely a problem with large networks. Regardless of the initial conditions, the system nearly always reaches solutions of very similar quality. Recent theoretical and empirical results strongly suggest that local minima are not a serious issue in general. Instead, the landscape is packed with a combinatorially large number of saddle points where the gradient is zero, and the surface curves up in most dimensions and curves down in the remainder. The analysis seems to show that saddle points with only a few downward curving directions are present in very large numbers, but almost all of them have very similar values of the objective function. Hence, it does not much matter which of these saddle points the algorithm gets stuck at.
在实践中，较差的局部极小值在大型网络中很少出现问题。不管初始条件如何，系统几乎总能得到质量非常相似的解。最近的理论和实证结果强烈表明，局部极小值一般不是一个严重的问题。取而代之的是，景观中充满了大量的鞍点，这些鞍点梯度为零，并且曲面在大多数维度上都向上弯曲，而在其余维度上则向下弯曲。 分析似乎表明，只有少数向下弯曲方向的鞍点数量非常多，但几乎所有鞍点的目标函数值都非常相似。因此，算法在这些鞍点中的哪一个卡住并不重要。

Interest in deep feedforward networks was revived around 2006 (refs 31–34) by a group of researchers brought together by the Canadian Institute for Advanced Research (CIFAR). The researchers introduced unsupervised learning procedures that could create layers of feature detectors without requiring labelled data. The objective in learning each layer of feature detectors was to be able to reconstruct or model the activities of feature detectors (or raw inputs) in the layer below. By ‘pre-training’ several layers of progressively more complex feature detectors using this reconstruction objective, the weights of a deep network could be initialized to sensible values. A final layer of output units could then be added to the top of the network and the whole deep system could be fine-tuned using standard backpropagation. This worked remarkably well for recognizing handwritten digits or for detecting pedestrians, especially when the amount of labelled data was very limited.
2006年前后，由加拿大高级研究所（CIFAR）召集的一组研究人员重新唤起了人们对深度前馈网络的兴趣（参考文献31-34）。研究人员引入了无监督的学习程序，这种程序可以在不需要标记数据的情况下创建特征检测器层。学习每一层特征检测器的目的是能够重建或模拟下一层特征检测器（或原始输入）的活动。通过使用该重构目标对多个逐步复杂的特征检测器进行“预训练”，可以将深度网络的权值初始化为合理值。最后一层输出单元可以被添加到网络的顶部，整个深系统可以使用标准反向传播进行微调。这对于识别手写数字或检测行人非常有效，尤其是在标签数据量非常有限的情况下。

The first major application of this pre-training approach was in speech recognition, and it was made possible by the advent of fast graphics processing units (GPUs) that were convenient to program and allowed researchers to train networks 10 or 20 times faster. In 2009, the approach was used to map short temporal windows of coefficients extracted from a sound wave to a set of probabilities for the various fragments of speech that might be represented by the frame in the centre of the window. It achieved record-breaking results on a standard speech recognition benchmark that used a small vocabulary and was quickly developed to give record-breaking results on a large vocabulary task. By 2012, versions of the deep net from 2009 were being developed by many of the major speech groups6 and were already being deployed in Android phones. For smaller data sets, unsupervised pre-training helps to prevent overfitting, leading to significantly better generalization when the number of labelled examples is small, or in a transfer setting where we have lots of examples for some ‘source’ tasks but very few for some ‘target’ tasks. Once deep learning had been rehabilitated, it turned out that the pre-training stage was only needed for small data sets.
这种预训练方法的第一个主要应用是在语音识别中，并且由于快速图形处理单元（GPU）的出现而成为可能，它便于编程，并使研究人员训练网络的速度提高了10到20倍。2009年，该方法被用于将从声波中提取的系数的短时间窗口映射为各种语音片段的概率集，这些语音片段可能由窗口中心的帧表示。它在使用小词汇的标准语音识别基准测试中取得了破纪录的结果38，并且很快被开发出来，在一个大词汇量任务中给出了破纪录的结果39。到2012年，许多主要的语音组织6都在开发2009年的deepnet版本，并且已经部署在Android手机上。对于较小的数据集，无监督的预培训有助于防止过度拟合40，当标记的示例数量较少时，或者在转移设置中，我们有很多示例用于某些“源”任务，但很少有用于某些“目标”任务，因此可以显著提高泛化能力。一旦深度学习得到恢复，原来只需要对小数据集进行预培训。

There was, however, one particular type of deep, feedforward network that was much easier to train and generalized much better than networks with full connectivity between adjacent layers. This was the convolutional neural network (ConvNet). It achieved many practical successes during the period when neural networks were out of favour and it has recently been widely adopted by the computervision community.
然而，有一种特殊的深度前馈网络，它比在相邻层之间完全连接的网络更容易训练和推广。这就是卷积神经网络(ConvNet)41,42。在神经网络失宠的时期，它取得了许多实际的成功，最近被计算机视觉界广泛采用。

Convolutional neural networks

卷积神经网络

ConvNets are designed to process data that come in the form of multiple arrays, for example a colour image composed of three 2D arrays containing pixel intensities in the three colour channels. Many data modalities are in the form of multiple arrays: 1D for signals and sequences, including language; 2D for images or audio spectrograms; and 3D for video or volumetric images. There are four key ideas behind ConvNets that take advantage of the properties of natural signals: local connections, shared weights, pooling and the use of many layers.
ConvNets被设计用来处理多阵列形式的数据，例如由三个二维阵列组成的彩色图像，三个彩色通道中包含像素强度。许多数据形式是多阵列的:信号和序列的一维，包括语言;用于图像或音频谱图的2D;和3D视频或体积图像。在利用自然信号特性的ConvNets背后有四个关键思想:本地连接、共享权重、共用和多层使用。

The architecture of a typical ConvNet (Fig. 2) is structured as a series of stages. The first few stages are composed of two types of layers: convolutional layers and pooling layers. Units in a convolutional layer are organized in feature maps, within which each unit is connected to local patches in the feature maps of the previous layer through a set of weights called a filter bank. The result of this local weighted sum is then passed through a non-linearity such as a ReLU. All units in a feature map share the same filter bank. Different feature maps in a layer use different filter banks. The reason for this architecture is twofold. First, in array data such as images, local groups of values are often highly correlated, forming distinctive local motifs that are easily detected. Second, the local statistics of images and other signals are invariant to location. In other words, if a motif can appear in one part of the image, it could appear anywhere, hence the idea of units at different locations sharing the same weights and detecting the same pattern in different parts of the array. Mathematically, the filtering operation performed by a feature map is a discrete convolution, hence the name.
典型的ConvNet（图2）的体系结构是由一系列阶段构成的。前几个阶段由两种类型的层组成：卷积层和池层。卷积层中的单元被组织在特征映射中，其中每个单元通过一组称为滤波器组的权重连接到上一层的特征映射中的局部面片。然后，该局部加权和的结果通过一个非线性，如ReLU。要素图中的所有单元共享同一个过滤器组。一个图层中的不同特征映射使用不同的滤波器组。这种架构有两个原因。首先，在图像等阵列数据中，值的局部组通常高度相关，形成易于检测的独特的局部模体。第二，图像和其他信号的局部统计信息对位置不变性。换言之，如果一个模体可以出现在图像的一个部分，那么它就可以出现在任何地方，因此在不同位置的单元共享相同的权重，并在阵列的不同部分检测相同的模式。从数学上讲，特征映射执行的过滤操作是一个离散卷积，因此得名。

Although the role of the convolutional layer is to detect local conjunctions of features from the previous layer, the role of the pooling layer is to merge semantically similar features into one. Because the relative positions of the features forming a motif can vary somewhat, reliably detecting the motif can be done by coarse-graining the position of each feature. A typical pooling unit computes the maximum of a local patch of units in one feature map (or in a few feature maps). Neighbouring pooling units take input from patches that are shifted by more than one row or column, thereby reducing the dimension of the representation and creating an invariance to small shifts and distortions. Two or three stages of convolution, non-linearity and pooling are stacked, followed by more convolutional and fully-connected layers. Backpropagating gradients through a ConvNet is as simple as through a regular deep network, allowing all the weights in all the filter banks to be trained.
虽然卷积层的作用是检测前一层特征的局部连接，但池化层的作用是将语义上相似的特征合并为一个。由于构成基序的特征的相对位置会有所变化，因此可以通过对每个特征的位置进行粗粒化来可靠地检测基序。典型的池单元计算一个特征图(或几个特征图)中局部单元的最大值。相邻的池单元从移位了不止一行或一列的块中获取输入，从而减少了表示的维度，并对小的移位和扭曲创建了不变性。卷积、非线性和池化的两个或三个阶段被堆叠起来，然后是更卷积的和完全连接的层。通过ConvNet反向传播梯度和通过常规深度网络一样简单，允许对所有滤波器组中的所有权重进行训练。

Deep neural networks exploit the property that many natural signals are compositional hierarchies, in which higher-level features are obtained by composing lower-level ones. In images, local combinations of edges form motifs, motifs assemble into parts, and parts form objects. Similar hierarchies exist in speech and text from sounds to phones, phonemes, syllables, words and sentences. The pooling allows representations to vary very little when elements in the previous layer vary in position and appearance.
深度神经网络利用了许多自然信号是组合层次结构的特性，即通过组合较低层次的特征来获得较高层次的特征。在图像中，局部的边缘组合形成图案，图案组合成零件，零件形成物体。在语音和文本中，从声音到音素、音素、音节、单词和句子都存在着类似的层级。当前一层中的元素在位置和外观上发生变化时，池允许表示变化很小。

The convolutional and pooling layers in ConvNets are directly inspired by the classic notions of simple cells and complex cells in visual neuroscience43, and the overall architecture is reminiscent of the LGN–V1–V2–V4–IT hierarchy in the visual cortex ventral pathway44. When ConvNet models and monkeys are shown the same picture, the activations of high-level units in the ConvNet explains half of the variance of random sets of 160 neurons in the monkey’s inferotemporal cortex45. ConvNets have their roots in the neocognitron46, the architecture of which was somewhat similar, but did not have an end-to-end supervised-learning algorithm such as backpropagation. A primitive 1D ConvNet called a time-delay neural net was used for the recognition of phonemes and simple words47,48.
卷积网络中的卷积和池化层直接受到视觉神经科学中简单细胞和复杂细胞的经典概念的启发，整个架构让人联想到视觉皮层腹侧通路中的LGN-V1-V2-V4-IT层次结构。当ConvNet模型和猴子显示相同的图片时，ConvNet中高层单元的激活解释了猴子下颞叶皮层中160个神经元随机集合的一半方差。 ConvNets的根源是新认知器，其架构有些相似，但没有反向传播那样的端到端监督学习算法。称为时延神经网络的原始一维ConvNet用于识别音素和简单单词。

There have been numerous applications of convolutional networks going back to the early 1990s, starting with time-delay neural networks for speech recognition and document reading. The document reading system used a ConvNet trained jointly with a probabilistic model that implemented language constraints. By the late 1990s this system was reading over 10% of all the cheques in the United States. A number of ConvNet-based optical character recognition and handwriting recognition systems were later deployed by Microsoft. ConvNets were also experimented with in the early 1990s for object detection in natural images, including faces and hands, and for face recognition.
从语音识别和文件读取的延时神经网络开始，卷积网络早在20世纪90年代初就有了大量的应用。文档读取系统使用了一个与实现语言约束的概率模型联合训练的卷积网。到20世纪90年代末，这个系统读取了美国超过10%的支票。许多基于ConvNet t的光学字符识别和手写识别系统后来被Microsoft部署。在20世纪90年代早期，卷积神经网络也被实验用于在自然图像中检测物体，包括人脸和手，以及人脸识别

Image understanding with deep convolutional networks

用深度卷积网络理解图像

Since the early 2000s, ConvNets have been applied with great success to the detection, segmentation and recognition of objects and regions in images. These were all tasks in which labelled data was relatively abundant, such as traffic sign recognition, the segmentation of biological images particularly for connectomics, and the detection of faces, text, pedestrians and human bodies in natural images .A major recent practical success of ConvNets is face recognition .
自21世纪初以来，卷积神经网络在图像中的目标和区域的检测、分割和识别方面的实际应用中取得了巨大的成功。这些都是标记数据相对丰富的任务，如交通标志识别，生物图像的分割尤其是连接体，以及在自然图像中对人脸、文本、行人和人体的检测。最近ConvNets的一个主要的实际成功是人脸识别

Importantly, images can be labelled at the pixel level, which will have applications in technology, including autonomous mobile robots and self-driving cars. Companies such as Mobileye and NVIDIA are using such ConvNet-based methods in their upcoming vision systems for cars. Other applications gaining importance involve natural language understanding and speech recognition.
重要的是，图像可以在像素级进行标记，这将在技术上有应用，包括自主移动机器人和自动驾驶汽车。移动眼(Mobileye)和英伟达(NVIDIA)等公司正在他们即将推出的汽车视觉系统中使用这种基于convnet的方法。其他越来越重要的应用包括自然语言理解和语音识别。

Despite these successes, ConvNets were largely forsaken by the mainstream computer-vision and machine-learning communities until the ImageNet competition in 2012. When deep convolutional networks were applied to a data set of about a million images from the web that contained 1,000 different classes, they achieved spectacular results, almost halving the error rates of the best competing approaches. This success came from the efficient use of GPUs, ReLUs, a new regularization technique called dropout, and techniques to generate more training examples by deforming the existing ones. This success has brought about a revolution in computer vision; ConvNets are now the dominant approach for almost all recognition and detection tasks and approach human performance on some tasks. A recent stunning demonstration combines ConvNets and recurrent net modules for the generation of image captions (Fig. 3).
尽管取得了这些成功，但在2012年ImageNet竞赛之前，ConvNets基本上被主流的计算机视觉和机器学习社区所抛弃。当深度卷积网络应用于包含1000个不同类别的网络上的约100万张图像的数据集时，它们取得了惊人的结果，几乎将最佳竞争方法的错误率降低了一半。这一成功来自GPUs的有效使用，ReLUs，一种叫做dropout的新的正则化技术，以及通过变形现有的训练例子来生成更多训练例子的技术。这一成功带来了计算机视觉的革命;卷积神经网络现在是几乎所有识别和检测任务的主导方法，和研究人类在某些任务上的表现。最近的一个惊人的演示结合了ConvNets和递归网络模块来生成图像字幕(图3)。

Recent ConvNet architectures have 10 to 20 layers of ReLUs, hundreds of millions of weights, and billions of connections between units. Whereas training such large networks could have taken weeks only two years ago, progress in hardware, software and algorithm parallelization have reduced training times to a few hours.
最近的ConvNet架构有10到20层ReLUs，数亿个权重并且单元之间有数十亿个连接。在两年前，训练如此庞大的网络可能需要花费数周时间，而在硬件、软件和算法并行化方面的进步已将训练时间缩短到几个小时。

The performance of ConvNet-based vision systems has caused most major technology companies, including Google, Facebook, Microsoft, IBM, Y ahoo!, Twitter and Adobe, as well as a quickly growing number of start-ups to initiate research and development projects and to deploy ConvNet-based image understanding products and services.
基于ConvNet的视觉系统的性能已经引起了大多数主要技术公司的关注，包括谷歌、Facebook、微软、IBM、Y ahoo!、Twitter 和 Adobe，以及越来越多的新兴公司开始启动研究和开发项目，并部署基于ConvNet的图像理解产品和服务。

ConvNets are easily amenable to efficient hardware implementations in chips or field-programmable gate arrays. A number of companies such as NVIDIA, Mobileye, Intel, Qualcomm and Samsung are developing ConvNet chips to enable real-time vision applications in smartphones, cameras, robots and self-driving cars.
ConvNets很容易适应芯片或现场可编程门阵列中有效的硬件实现。例如，英伟达(NVIDIA)、移动眼(Mobileye)、英特尔(Intel)、高通(Qualcomm)和三星(Samsung)等多家公司都在开发ConvNet芯片，以便在智能手机、摄像头、机器人和自动驾驶汽车上实现实时视觉应用。

Distributed representations and language processing

分布式表示和语言处理

Deep-learning theory shows that deep nets have two different exponential advantages over classic learning algorithms that do not use distributed representations21. Both of these advantages arise from the power of composition and depend on the underlying data-generating distribution having an appropriate componential structure40. First, learning distributed representations enable generalization to new combinations of the values of learned features beyond those seen during training (for example, 2n combinations are possible with n binary features)68,69. Second, composing layers of representation in a deep net brings the potential for another exponential advantage70 (exponential in the depth).
深度学习理论表明，与不使用分布式表示的经典学习算法相比，深度网具有两种不同的指数优势。这两个优点都来自于组合的强大功能，并且依赖于底层数据生成分布具有适当的组件结构。首先，学习分布式表示使学习到的特征值能够泛化到新的组合，而不是在训练中看到的(例如，n个二进制特征可能有2n个组合)。其次，在深层网络中组合表示层会带来另一个指数优势(深度指数)

The hidden layers of a multilayer neural network learn to represent the network’s inputs in a way that makes it easy to predict the target outputs. This is nicely demonstrated by training a multilayer neural network to predict the next word in a sequence from a local context of earlier words. Each word in the context is presented to the network as a one-of-N vector, that is, one component has a value of 1 and the rest are 0. In the first layer, each word creates a different pattern of activations, or word vectors (Fig. 4). In a language model, the other layers of the network learn to convert the input word vectors into an output word vector for the predicted next word, which can be used to predict the probability for any word in the vocabulary to appear as the next word. The network learns word vectors that contain many active components each of which can be interpreted as a separate feature of the word, as was first demonstrated in the context of learning distributed representations for symbols. These semantic features were not explicitly present in the input. They were discovered by the learning procedure as a good way of factorizing the structured relationships between the input and output symbols into multiple ‘micro-rules’. Learning word vectors turned out to also work very well when the word sequences come from a large corpus of real text and the individual micro-rules are unreliable .When trained to predict the next word in a news story, for example, the learned word vectors for Tuesday and Wednesday are very similar, as are the word vectors for Sweden and Norway. Such representations are called distributed representations because their elements (the features) are not mutually exclusive and their many configurations correspond to the variations seen in the observed data. These word vectors are composed of learned features that were not determined ahead of time by experts, but automatically discovered by the neural network. Vector representations of words learned from text are now very widely used in natural language applications.

多层神经网络的隐含层学会以某种方式表示网络的输入，这种方法使得预测目标输出变得容易。通过训练一个多层神经网络来从前面单词的局部上下文中预测序列中的下一个单词，可以很好地演示这一点。上下文中的每个单词都以one-of- n向量的形式呈现给网络，也就是说，其中一个分量的值为1，其余为0。在第一层中，每个单词创建了不同的激活模式，或单词向量(图4)。在语言模型中，网络的其他层学会将输入的单词向量转换为预测下一个单词的输出单词向量，该向量可用于预测词汇表中任何单词出现为下一个单词的概率。网络学习包含许多活动组件的词向量，其中每一个都可以被解释为单词的一个单独的特征，就像第一次在学习符号的分布式表示的上下文中演示的那样。这些语义特征并没有明确地出现在输入中。它们是在学习过程中被发现的，是将输入和输出符号之间的结构关系分解成多个“微观规则”的好方法。当单词序列来自大量的真实文本语料库并且单个的微观规则不可靠时，学习单词向量也可以很好地工作。例如，当训练预测一篇新闻报道中的下一个单词时，星期二和星期三学到的单词向量非常相似，瑞典和挪威学到的单词向量也非常相似。这样的表示被称为分布式表示，因为它们的元素(特征)不是互斥的，它们的许多配置对应于观察到的数据中的变化。这些词向量是由学习过的特征组成的，这些特征不是由专家提前确定的，而是由神经网络自动发现的。从文本中学习的单词的矢量表示现在在自然语言应用中得到了广泛的应用。

The issue of representation lies at the heart of the debate between the logic-inspired and the neural-network-inspired paradigms for cognition. In the logic-inspired paradigm, an instance of a symbol is something for which the only property is that it is either identical or non-identical to other symbol instances. It has no internal structure that is relevant to its use; and to reason with symbols, they must be bound to the variables in judiciously chosen rules of inference. By contrast, neural networks just use big activity vectors, big weight matrices and scalar non-linearities to perform the type of fast ‘intuitive’ inference that underpins effortless commonsense reasoning.
表征的问题是关于认知的逻辑启发范式和神经网络启发范式之间争论的核心。在逻辑启发的范式中，一个符号实例的唯一属性是它与其他符号实例相同或不相同。没有与其使用有关的内部结构;为了用符号进行推理，它们必须与审慎选择的推理规则中的变量绑定在一起。相比之下，神经网络只是使用大的活动向量、大的权重矩阵和标量非线性来执行快速的“直觉”推理，从而支持无需费力的常识推理。

Before the introduction of neural language models, the standard approach to statistical modelling of language did not exploit distributed representations: it was based on counting frequencies of occurrences of short symbol sequences of length up to N (called N-grams). The number of possible N-grams is on the order of VN, where V is the vocabulary size, so taking into account a context of more than a handful of words would require very large training corpora. N-grams treat each word as an atomic unit, so they cannot generalize across semantically related sequences of words,whereas neural language models can because they associate each word with a vector of real valued features, and semantically related words end up close to each other in that vector space (Fig. 4).
在引入神经语言模型之前，语言统计建模的标准方法没有利用分布表示:它基于对长度为N的短符号序列(称为N克)出现的频率进行计数。可能的N-grams的数量是VN的数量级，其中V是词汇表的大小，因此，考虑一个超过几个单词的上下文将需要非常大的训练库。N-grams将每个单词视为一个原子单位，因此它们无法在语义上相关的单词序列中进行泛化，而神经语言模型则可以将它们与实际值特征的向量相关联，而语义相关的单词最终彼此靠近 在该向量空间中（图4）。

Recurrent neural networks

循环神经网络

When backpropagation was first introduced, its most exciting use was for training recurrent neural networks (RNNs). For tasks that involve sequential inputs, such as speech and language, it is often better to use RNNs (Fig. 5). RNNs process an input sequence one element at a time, maintaining in their hidden units a ‘state vector’ that implicitly contains information about the history of all the past elements of the sequence. When we consider the outputs of the hidden units at different discrete time steps as if they were the outputs of different neurons in a deep multilayer network (Fig. 5, right), it becomes clear how we can apply backpropagation to train RNNs.
当反向传播首次被引入时，它最令人兴奋的用途是用于训练循环神经网络(RNNs)。对于涉及顺序输入的任务，如语音和语言，通常使用RNNs更好(图5)。RNNs一次处理一个输入序列的元素，在它们的隐藏单元中维护一个“状态向量”，它隐式地包含了序列中所有过去元素的历史信息。当我们把隐藏单元在不同离散时间步长的输出看作是深层多层网络中不同神经元的输出时(图5，右)，如何应用反向传播来训练RNNs就变得很清楚了。

RNNs are very powerful dynamic systems, but training them has proved to be problematic because the backpropagated gradients either grow or shrink at each time step, so over many time steps they typically explode or vanish.
RNNs是非常强大的动态系统，但是训练它们被证明是有问题的，因为反向传播的梯度不是在每一个时间步长时变大就是变小，所以在很多时间步长时，它们通常会爆炸或消失

Thanks to advances in their architecture and ways of training them, RNNs have been found to be very good at predicting the next character in the text or the next word in a sequence, but they can also be used for more complex tasks. For example, after reading an English sentence one word at a time, an English ‘encoder’ network can be trained so that the final state vector of its hidden units is a good representation of the thought expressed by the sentence. This thought vector can then be used as the initial hidden state of (or as extra input to) a jointly trained French ‘decoder’ network, which outputs a probability distribution for the first word of the French translation. If a particular first word is chosen from this distribution and provided as input to the decoder network it will then output a probability distribution for the second word of the translation and so on until a full stop is chosen. Overall, this process generates sequences of French words according to a probability distribution that depends on the English sentence. This rather naive way of performing machine translation has quickly become competitive with the state-of-the-art, and this raises serious doubts about whether understanding a sentence requires anything like the internal symbolic expressions that are manipulated by using inference rules. It is more compatible with the view that everyday reasoning involves many simultaneous analogies that each contribute plausibility to a conclusion.
体系结构和训练方式的进步，研究发现，RNNs非常擅长预测文本中的下一个字符或序列中的下一个单词，但它们也可以用于更复杂的任务。例如，在一次一个单词地阅读一个英语句子后，可以训练一个英语“编码器”网络，使其隐藏单位的最终状态向量很好地表达了句子所表达的思想。然后，这个思想向量可以用作一个联合训练的法语“解码器”网络的初始隐藏状态(或额外的输入)，该网络输出法语翻译的第一个单词的概率分布。如果从这个分布中选择了一个特定的第一个单词并作为输入提供给解码器网络，那么它将输出翻译的第二个单词的概率分布，以此类推，直到选择了句号停止。总体而言，此过程根据取决于英语句子的概率分布生成法语单词序列。这种相当幼稚的机器翻译方式已经快速与最先进的技术相媲美，这引发了严重的疑问:理解一个句子是否需要类似于使用推理规则操作的内部符号表达式的东西。它更符合这样的观点，即日常推理涉及许多同时进行的类比，每个类比都有助于得出结论的合理性。

Instead of translating the meaning of a French sentence into an English sentence, one can learn to ‘translate’ the meaning of an image into an English sentence (Fig. 3). The encoder here is a deep ConvNet that converts the pixels into an activity vector in its last hidden layer. The decoder is an RNN similar to the ones used for machine translation and neural language modelling. There has been a surge of interest in such systems recently (see examples mentioned in ref. 86).
人们可以学会把一幅图像的意思“翻译”成一个英语句子，而不是把一个法语句子的意思翻译成一个英语句子(图3)。这里的编码器是一个深度ConvNet，它在最后一个隐藏层中将像素转换为活动向量。解码器是一个类似于机器翻译和神经语言建模的RNN。最近，人们对这种系统的兴趣大增。

RNNs, once unfolded in time (Fig. 5), can be seen as very deep feedforward networks in which all the layers share the same weights. Although their main purpose is to learn long-term dependencies, theoretical and empirical evidence shows that it is difficult to learn to store information for very long.
一旦及时展开（图5），RNNs就可以被看作是深度前馈网络，其中所有层的权值都相同。虽然它们的主要目的是学习长期依赖，但理论和经验证据表明，学习长时间存储信息是困难的

To correct for that, one idea is to augment the network with an explicit memory. The first proposal of this kind is the long short-term memory (LSTM) networks that use special hidden units, the natural behaviour of which is to remember inputs for a long time79. A special unit called the memory cell acts like an accumulator or a gated leaky neuron: it has a connection to itself at the next time step that has a weight of one, so it copies its own real-valued state and accumulates the external signal, but this self-connection is multiplicatively gated by another unit that learns to decide when to clear the content of the memory.
为了解决这个问题，，一个想法是使用显式内存来扩大网络。这种类型的第一个提议是长短期记忆(LSTM)网络，它使用特殊的隐藏单元，其自然行为是长时间记忆输入。一个特殊的单位称为存储单元就像蓄电池或封闭的漏水的神经元:它与下一个时间步的自身有一个连接它的权值为1，所以它拷贝自己的实值状态和积累外部信号,但是这种自我联系被另一个学会何时清除记忆内容的单元成倍地控制着。

LSTM networks have subsequently proved to be more effective than conventional RNNs, especially when they have several layers for each time step87, enabling an entire speech recognition system that goes all the way from acoustics to the sequence of characters in the transcription. LSTM networks or related forms of gated units are also currently used for the encoder and decoder networks that perform so well at machine translation
后来，LSTM网络被证明比传统的RNNs更有效，特别是当它们在每个时间步都有好几层时，使得整个语音识别系统能够从声学一直到转录中的字符序列。LSTM网络或相关形式的门控单元目前也用于在机器翻译方面表现良好的编码器和解码器网络

Over the past year, several authors have made different proposals to augment RNNs with a memory module. Proposals include the Neural Turing Machine in which the network is augmented by a ‘tape-like’ memory that the RNN can choose to read from or write to88, and memory networks, in which a regular network is augmented by a kind of associative memory. Memory networks have yielded excellent performance on standard question-answering benchmarks. The memory is used to remember the story about which the network is later asked to answer questions.
在过去的一年里，几个作者提出了不同的建议来增加RNNs的内存模块。建议包括神经图灵机，在该机器中，网络被一个RNN可以选择读取或写入的“类似磁带”的内存扩充，以及存储网络，在这种网络中，常规的网络被一种联想记忆所增强。内存网络在标准的问题回答基准测试中取得了优异的性能。存储器是用来记住网络后来被要求回答问题的故事。

Beyond simple memorization, neural Turing machines and memory networks are being used for tasks that would normally require reasoning and symbol manipulation. Neural Turing machines can be taught ‘algorithms’. Among other things, they can learn to output a sorted list of symbols when their input consists of an unsorted sequence in which each symbol is accompanied by a real value that indicates its priority in the list. Memory networks can be trained to keep track of the state of the world in a setting similar to a text adventure game and after reading a story, they can answer questions that require complex inference90. In one test example, the network is shown a 15-sentence version of the The Lord of the Rings and correctly answers questions such as “where is Frodo now?”.
除了简单的记忆，神经图灵机和存储网络也被用于通常需要推理和符号操作的任务。神经图灵机可以被称为“算法”。除此之外，当它们的输入由未排序的序列组成时，它们可以学习输出一个已排序的符号列表，其中每个符号都伴随着一个表示其在列表中的优先级的真实值。在类似于文本冒险游戏的设置中，存储网络可以被训练来跟踪世界的状态，在读完故事后，他们可以回答需要复杂推理的问题。在一个测试例子中，网络被展示了一个15句的指环王版本，并正确地回答了诸如“佛罗多现在在哪里?”的问题。

The future of deep learning

深度学习的未来

Unsupervised learning had a catalytic effect in reviving interest in deep learning, but has since been overshadowed by the successes of purely supervised learning. Although we have not focused on it in this Review, we expect unsupervised learning to become far more important in the longer term. Human and animal learning is largely unsupervised: we discover the structure of the world by observing it, not by being told the name of every object.
无监督学习在恢复人们对深度学习的兴趣方面起到了催化作用，但在纯监督学习的成功面前黯然失色。虽然我们在这篇综述中没有关注它，但我们期望无监督学习在长期内变得更加重要。人类和动物的学习在很大程度上是不受监督的:我们通过观察来发现世界的结构，而不是通过被告知每一个物体的名称来发现它。

Human vision is an active process that sequentially samples the optic array in an intelligent, task-specific way using a small, high-resolution fovea with a large, low-resolution surround. We expect much of the future progress in vision to come from systems that are trained end-toend and combine ConvNets with RNNs that use reinforcement learning to decide where to look. Systems combining deep learning and reinforcement learning are in their infancy, but they already outperform passive vision systems99 at classification tasks and produce impressive results in learning to play many different video games100.
人类的视觉是一个主动的过程，它以一种智能的、特定任务的方式对光学阵列进行连续采样，使用一个小的、高分辨率的中央凹和一个大的、低分辨率的环绕。我们期望未来视觉领域的大部分进步将来自于这样的系统:通过端到端训练，将ConvNets与RNN结合起来，利用强化学习来决定看向哪里。结合了深度学习和强化学习的系统还处于起步阶段，但它们在分类任务方面已经超过了被动视觉系统，并且在学习玩许多不同的视频游戏方面产生了令人印象深刻的结果

Natural language understanding is another area in which deep learning is poised to make a large impact over the next few years. We expect systems that use RNNs to understand sentences or whole documents will become much better when they learn strategies for selectively attending to one part at a time76,86.
自然语言理解是深度学习在未来几年有望产生重大影响的另一个领域。我们期望使用RNNs来理解句子或整个文档的系统，在学习了每次有选择地关注一个部分的策略后，会变得更好。

Ultimately, major progress in artificial intelligence will come about through systems that combine representation learning with complex reasoning. Although deep learning and simple reasoning have been used for speech and handwriting recognition for a long time, new paradigms are needed to replace rule-based manipulation of symbolic expressions by operations on large vectors.
最终，人工智能的重大进步将通过将表示学习与复杂推理相结合的系统实现。虽然深度学习和简单推理已经在语音和笔迹识别中使用了很长时间，但仍需要新的范例来通过对大向量进行运算来代替基于规则的符号表达操纵。