深度学习导论

Here you will get an introduction to deep learning.

在这里，您将获得深度学习的介绍。

Deep learning is also known as hierarchical learning. It is used for interpretation of information processing and communication patterns in biological neural system. It also defines relation between different stimuli and associated neural responses in brain. It is a part of machine learning methods with non-task specific algorithms based on learning data representation.

深度学习也称为分层学习。 它用于解释生物神经系统中的信息处理和通信模式。 它还定义了不同刺激与大脑中相关神经React之间的关系。 它是具有基于学习数据表示的非特定任务算法的机器学习方法的一部分。

Deep learning can be applied in many fields such as computer vision, speech recognition, image processing, bioinformatics, social network filtering and drug design with  the help of its architectures such as deep neural networks and recurrent neural network.

借助深度神经网络和递归神经网络等架构，深度学习可以应用于许多领域，例如计算机视觉，语音识别，图像处理，生物信息学，社交网络过滤和药物设计。

It generates result comparable or in some cases superior to human experts. It uses outpouring of multiple layers of nonlinear processing units  for transformation and feature extraction. In this, each successive layer takes output from previous layer as input.

它产生的结果可与人类专家媲美，或在某些情况下优于人类专家。 它使用多层非线性处理单元的浇注进行变换和特征提取。 在此，每个连续的层都将前一层的输出作为输入。

Deep learning levels form hierarchy of concepts and multiple level of representations corresponding to different levels of abstraction. It also uses few form of gradient descent algorithm with back propagation. Multiple layers used in deep learning include hidden layer of neural network and set of propositional formulas.

深度学习级别形成概念的层次结构，并对应于不同的抽象级别形成多个表示形式。 它还使用了带有反向传播的几种形式的梯度下降算法。 深度学习中使用的多层包括神经网络的隐藏层和命题公式集。

Deep learning can be in supervised or unsupervised manner. Supervised learning and unsupervised are completely opposite of each other. In supervised learning task of inferring from labeled data and in unsupervised  learning task of inferring from unlabeled data. Supervised learning includes classification and unsupervised learning includes pattern analysis.

深度学习可以是有监督的或无监督的。 有监督的学习与无监督是完全相反的。 从标签数据推断的监督学习任务和从未标签数据推断的监督学习任务中。 监督学习包括分类，无监督学习包括模式分析。

深度学习的主要架构 (Major Architectures of Deep Learning)

Let’s take a review at four major deep learning architectures.

让我们回顾一下四种主要的深度学习架构。

• Unsupervised Pre-trained Networks (UPNs)
  无监督的预训练网络(UPN)
• Convolutional Neural Networks (CNNs)
  卷积神经网络(CNN)
• Recurrent Neural Networks
  递归神经网络
• Recursive Neural Networks
  递归神经网络

However the two most important architectures are: CNNs (Convolutional Neural Networks) for image modeling and Long Short-Term Memory (LSTM) Networks (Recurrent Networks) for sequence modeling.

但是，两个最重要的体系结构是：用于图像建模的CNN(卷积神经网络)和用于序列建模的长短期记忆(LSTM)网络(递归网络)。

无监督的预训练网络(UPN) (Unsupervised Pre-trained Networks (UPNs))

In this group, there are three specific architectures:

在这一组中，存在三种特定的体系结构：

• Autoencoders
  自动编码器
• Deep Belief Networks (DBNs)
  深度信仰网络(DBN)
• Generative Adversarial Networks (GANs)
  生成对抗网络(GAN)

Autoencoders

自动编码器

Auto-encoder is used to restore input. Therefore it must have an output layer which capable of restoring input. This implies that selection of activation function must be carefully done. Also the normalization of range of input values must be such that the shape of output remains same as input.

自动编码器用于恢复输入。 因此，它必须具有能够恢复输入的输出层。 这意味着必须仔细选择激活功能。 同样，输入值范围的规格化必须确保输出的形状与输入相同。

Deep Belief Networks (DBNs)

深度信仰网络(DBN)

Deep Belief Network (DBN) is a class of deep neural network which is composed of hidden units that involves connections between layers not between units in each layer.

深度信仰网络(DBN)是一类深度神经网络，由隐藏的单元组成，这些单元涉及各层之间的连接，而不是各层之间的连接。

Deep belief network can be seen as a composition of unsupervised networks such as restricted Boltzmann machines where hidden layer of each sub network serves as visible layer for the next layer. Restricted Boltzmann machines is generative energy based model with input layer visible and hidden layer connection with it.

深度信任网络可以看作是无监督网络的组成，例如受限的Boltzmann机器，其中每个子网络的隐藏层充当下一层的可见层。 受限的Boltzmann机器是基于生成能量的模型，具有输入层可见层和隐藏层连接。

Deep belief network can be seen in many real life applications and services like drug discovery, electroencephalography, etc.

深度信任网络可以在许多现实生活中的应用和服务中看到，例如药物发现，脑电图等。

Generative Adversarial Networks (GANs)

生成对抗网络(GAN)

Generative Adversarial Networks (GANs) used in unsupervised machine learning. It is a class of artificial intelligence algorithms. It implemented by two neural network system debating with each other in a zero-sum game frame work.

在无监督机器学习中使用的生成对抗网络(GAN)。 这是一类人工智能算法 。 它由两个在零和游戏框架中相互辩论的神经网络系统实现。

Zero-sum game is mathematical solution of a situation in which few participants gains and few losses. Each gain and loss of utility is equally balanced so that when they are sum up the result will be zero. Total gains of participants is added and total losses are subtracted and there some makes result to zero.

零和博弈是对参与者获利少而损失少的情况的数学解决方案。 效用的每种收益和损失均相等，因此将它们相加时结果将为零。 参与者的总收益相加，总损失相减，结果为零。

卷积神经网络(CNN) (Convolutional Neural Networks (CNNs))

Convolutional neural network is a class of deep learning with feed forward artificial neural network that is  applied to analyze visual image.

卷积神经网络是一类具有前馈人工神经网络的深度学习方法，用于分析视觉图像。

In convolutional neural network, the multilayer perceptron varies to attempt minimal processing. This multilayer perceptron is called space invariant artificial neural network. The connectivity pattern between neurons is similar to  organization of animal biological process

在卷积神经网络中，多层感知器会发生变化，以尝试进行最少的处理。 这种多层感知器称为空间不变人工神经网络。 神经元之间的连通性模式类似于动物生物学过程的组织

The aim of convolutional neural network is to learn higher order features in data with the help of convolutions. They are used in object recognition, also used to identify faces, street signs and others aspects used to visualize data. Convolutional neural networks are also used in analyzing word as discrete textual units by overlapping text analysis with optical character recognition. Image recognition by convolutional  neural network is only reason why world is attracted towards power pf deep learning.

卷积神经网络的目的是借助卷积来学习数据中的高阶特征。 它们用于对象识别，还用于识别人脸，路牌和其他用于可视化数据的方面。 卷积神经网络还用于通过重叠的文本分析和光学字符识别来分析作为离散文本单元的单词。 卷积神经网络的图像识别只是世界被深度学习的力量所吸引的唯一原因。

Convolutional neural networks are used in many applications like image and video recognition, natural language processing and recommender system.

卷积神经网络被用于许多应用中，例如图像和视频识别，自然语言处理和推荐系统。

递归神经网络 (Recurrent Neural Networks)

Recurrent Neural Networks  is used for parallel and sequential computation it is used to compute each and every thing similar to traditional computer. Recurrent neural network works similar to human brain, it is a large feedback network of connected neurons that can translate a input stream into a sequence of motor outputs. A recurrent neural network (RNN) use their internal memory to process sequencing of inputs. In recurrent neural network, connections between units form a directed cycle. Recurrent neural network model each vector from sequence of input stream vectors one at time. This allows  the network to retain its state during modeling of each input vector across the window of input vectors.

递归神经网络用于并行和顺序计算，它用于计算与传统计算机类似的每件事。 递归神经网络的工作原理类似于人脑，它是一个连接神经元的大型反馈网络，可以将输入流转换为一系列运动输出。 递归神经网络(RNN)使用其内部存储器来处理输入的排序。 在递归神经网络中，单元之间的连接形成有向循环。 递归神经网络一次从输入流向量序列中对每个向量建模。 这允许网络在跨输入向量窗口的每个输入向量建模期间保留其状态。

Recurrent neural network is like network of neuron nodes where each node is directly connected to other node. Each node has real valued activation that varies with time. Each connection in RNNs has real value weight that can be modified. Neuron nodes are either input nodes which receives data from outside the network, output nodes which yields results or hidden nodes which are used to modify data enrooting from input to output.

递归神经网络就像神经元节点的网络，其中每个节点直接连接到另一个节点。 每个节点具有随时间变化的真正有价值的激活。 RNN中的每个连接都具有可以修改的实际值权重。 神经元节点要么是从网络外部接收数据的输入节点，要么是产生结果的输出节点，要么是用于修改从输入到输出的数据扎根的隐藏节点。

Applications of Recurrent Neural Networks include:

递归神经网络的应用包括：

• Robot control
  机械手控制
• Time series predictions
  时间序列预测
• Rhythm learning
  节奏学习
• Music composition
  音乐创作
• Grammar learning
  语法学习
• Handwriting recognition
  手写识别
• Human action recognition
  人体动作识别

递归神经网络 (Recursive Neural Networks)

A Recursive Neural Network architecture is similar to deep neural network. It consist of a shared-weight matrix and a binary tree structure that allows the recursive network to learn varying sequences of words or parts of an image. It is created by applying similar set of weight recursively over the structure so that it can produce a structured prediction over varied size of input structure. It give scalar prediction by traversing the structure in topological order. Recursive neural network can be used as a scene parser. Recursive Neural Networks also deal with variable length input similar to recurrent neural network.

递归神经网络架构类似于深度神经网络。 它由一个权重矩阵和一个二叉树结构组成，该结构允许递归网络学习单词或图像部分的变化序列。 通过在结构上递归应用相似的权重集来创建它，以便可以在输入结构的各种大小上产生结构化的预测。 它通过以拓扑顺序遍历结构来进行标量预测。 递归神经网络可以用作场景解析器。 递归神经网络还处理可变长度输入，类似于递归神经网络。

Recursive Neural Networks use backpropagation through structure (BPTS), it is variation of backpropagation. Recursive neural network operate on any hierarchical structure that combine child representation into parent representation. Recursive neural networks are used in learning sequence and in natural language processing. It is also used for phrase and sentence representations based on word embedding

递归神经网络使用结构反向传播 (BPTS)，这是反向传播的变体。 递归神经网络可在任何将子代表示合并为父代表示的层次结构中运行。 递归神经网络用于学习序列和自然语言处理。 它也用于基于单词嵌入的短语和句子表示

深度学习的应用 (Applications of Deep Learning)

• Automatic speech recognition
  自动语音识别
• Image recognition
  影像识别
• Visual Art Processing
  视觉艺术处理
• Natural language processing
  自然语言处理
• Drug discovery and toxicology
  药物发现与毒理学
• Customer relationship management
  客户关系管理
• Recommendation systems
  推荐系统
• Bioinformatics
  生物信息学
• Mobile Advertising
  流动广告

About Author:

关于作者：

Shubham Sharma, currently working as Analytics Engineer in Data Science Domain. Has around 2+ years of experience in Data Science. Skilled in Python, Pandas, Anaconda, Tensorflow, Keras, Scikit learn, Numpy, Scipy, Microsoft Excel, SQL, Cassandra and Statistical Data Analysis, Hadoop, Hive, Pig, Spark, Pyspark. Connect with him at [email protected]

Shubham Sharma，目前在数据科学领域担任分析工程师。 在数据科学领域拥有大约2年以上的经验。 精通Python，Pandas，Anaconda，Tensorflow，Keras，Scikit学习，Numpy，Scipy，Microsoft Excel，SQL，Cassandra和统计数据分析，Hadoop，Hive，Pig，Spark，Pyspark。 通过[电子邮件保护]与他联系

Comment below if you have any doubts related to above introduction to deep learning.

如果您对以上深度学习入门有任何疑问，请在下面评论。

翻译自: https://www.thecrazyprogrammer.com/2017/12/introduction-to-deep-learning.html