⼈⼯神经⽹络导论_神经⽹络导论
⼈⼯神经⽹络导论
Here you will get an introduction to neural networks in the field of data science.
在这⾥，您将对数据科学领域的神经⽹络进⾏介绍。
Neural networks are similar to biological neural network. Biological neural network is collection of biological neurons in human brain similarly Neural network is collection of nodes called Artificial neurons.
神经⽹络类似于⽣物神经⽹络。 ⽣物神经⽹络类似地是⼈脑中⽣物神经元的集合。神经⽹络是称为⼈⼯神经元的节点的集合。
Neural networks are based on non-task specific programming concepts like in image recognition they learn to resemble images by analyzing sample images labeled with name as “car” or “no car” and by using such sample example they identify car in other images. They need not to acquire any knowledge regarding car like it has engine, four wheels, shape and so on. They generate their own relevant characteristics from the process of their learning material.
神经⽹络基于⾮任务特定的编程概念，例如在图像识别中，它们通过分析标记为“ car”或“ no car”的样本图像来学习类似于图像的⽅式，并通过使⽤此类样本⽰例将其识别为其他图像中的汽车。 他们不需要获
得有关汽车的任何知识，例如它的发动机，四个车轮，形状等。 他们从学习材料的过程中产⽣⾃⼰的相关特征。
Neural Network is a feature of artificial intelligence that efforts to copy the way human brain works. Neural network perform its operation by connecting the processing elements rather than doing all computations that manipulate zeros and ones in digital model
神经⽹络是⼈⼯智能的⼀项功能，旨在复制⼈脑的⼯作⽅式。 神经⽹络通过连接处理元件来执⾏其操作，⽽不是执⾏在数字模型中操纵零和⼀的所有计算
Neural network is used to represent relationships between complex input/output and also it is capable to capture data the same way human brain works. This idea for the development of neural network technology arises from the desire to
perform all task intelligently similar to human brain and develop an artificial system to perform all this task.
神经⽹络⽤于表⽰复杂输⼊/输出之间的关系，并且能够以与⼈脑相同的⽅式捕获数据。 神经⽹络技术发展的这种想法源于对智能地执⾏类似于⼈脑的所有任务并开发⼀种⼈⼯系统来执⾏所有任务的需求。
Neural network gains knowledge through learning. Synaptic inter-neuron connection strengths are used to store a neural network’s knowledge.
神经⽹络通过学习获得知识。 突触权重，即神经元间的连接强度，⽤于存储神经⽹络的知识。
神经⽹络的基本组织 (Basic Organization of Neural Network)
In Neural network, each connection called synapse between nodes or artificial neurons is used to transmit signal from one another and the receiving neuron called postsynaptic can process the signal and information and thereafter signal neurons connected to it.
在神经⽹络中，节点或⼈⼯神经元之间的每个称为突触的连接都⽤于相互传输信号，⽽称为突触后的接收神经元可以处理信号和信息，然后再与之连接的信号神经元。
Generally, neurons are arranged in layers. Different layers may perform different transformation with their inputs. Signals travelling from the first layer to the last layer, possibly have to traverse the layers multiple times.
通常，神经元分层排列。 不同的层可能会对它们的输⼊执⾏不同的转换。 从输⼊即第⼀层传播到输出即最后⼀层的信号可能必须多次遍历这些层。
In neural networks the sending signal (synapse) is real number and output is calculated by non-linear function. Output of each neuron is calculated by non-linear function of the sum of its inputs. Synapses and artificial neurons have weights that are adjustable as learning proceeds. The weight of neurons increases or decreases the signal strength that it has to send over synapse .
在神经⽹络中，发送信号(突触)是实数，并且输出是通过⾮线性函数计算的。 每个神经元的输出是通过其输⼊总和的⾮线性函数来计算的。突触和⼈⼯神经元的权重可以随着学习的进⾏⽽调整。 神经元的重量增加或减少了它必须通过突触传递的信号强度。
Neural network solve the problem the same way human brain do. Neural network have been used in computer speech recognition, video games, machine translation and medical diagnosis.
神经⽹络以与⼈类⼤脑相同的⽅式解决问题。 神经⽹络已⽤于计算机语⾳识别，视频游戏，机器翻译和医学诊断中。
神经⽹络的类型 (Types of Neural Network)
1.前馈神经⽹络 (1. Feedforward Neural Network)
Feedforward neural network is simplest of all neural network. It has no cycles or loops in its network that is it moves information in one direction only. The data in feedforward network moves from input to output nodes passing through hidden layer if there is any hidden layer in between the input and output
node.
前馈神经⽹络是所有神经⽹络中最简单的。 它的⽹络中没有循环或循环，仅在⼀个⽅向上移动信息。 如果输⼊和输出节点之间存在任何隐藏层，则前馈⽹络中的数据将从输⼊节点移动到通过隐藏层的节点。
2.径向基函数神经⽹络 (2. Radial Basis Function Neural Network)
Radial basis function neural network is highly spontaneous neural network. It is the first choice in multidimensional space during interpolation. In radial basis function neural network, each neuron saves an example from training set as a “prototype”. Radial basis function has advantage that it doesn’t suffer from local minima offered by linearity involved in functioning of it.
径向基函数神经⽹络是⾼度⾃发的神经⽹络。 它是插值过程中多维空间的⾸选。 在径向基函数神经⽹络中，每个神经元将训练集中的⼀个⽰例保存为“原型”。 径向基函数的优点是不会受到函数线性涉及的局部最⼩值的影响。
3. Kohonen⾃组织神经⽹络 (3. Kohonen Self-Organizing Neural Network)
Kohonen self-organizing neural network is used to visualize high dimensional data as low dimensional
views. It is invented by Teuvo Kohonen. Kohonen self-organizing  neural network is used to describe hidden structures in it by performing
functions on unlabeled data. competitive learning is applied by self-organizing neural network to a set of input data not error correction learning applied by other neural network.
Kohonen⾃组织神经⽹络⽤于将⾼维数据可视化为低维视图。 它是由Teuvo Kohonen发明的。 Kohonen⾃组织神经⽹络⽤于通过对未标记数据执⾏功能来描述其中的隐藏结构。 竞争性学习是通过⾃组织神经⽹络应⽤于⼀组输⼊数据，⽽不是其他神经⽹络进⾏的纠错学习。
4.递归神经⽹络 ( 4. Recurrent Neural Network)
Recurrent Neural Network 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 o
ne 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。
5.模块化神经⽹络 (5. Modular Neural Network)
Modular neural network consist of series of independent neural networks that are operated by intermediary. Each independent neural network act as a module and works with separate input that network hopes to perform by accomplishing subtask. The intermediary accepts the output of each module and helps them to process the final output for modular neural network. Also the independent neural the modules do not interact with each other.
模块化神经⽹络由⼀系列由中介操作的独⽴神经⽹络组成。 每个独⽴的神经⽹络都充当模块，并与⽹络希望通过完成⼦任务来执⾏的单独输⼊⼀起⼯作。 中介接受每个模块的输出，并帮助他们处理模块化神
经⽹络的最终输出。 同样，独⽴的神经⽹络，即模块之间不相互影响。
6.物理神经⽹络 (6. Physical Neural Network)
The physical neural network aims to focus on physical hardware along with the software while simulating the neural network.
A resistance material that is electrically adjustable is used for emulating the function of neural synapse. When the physical hardware emulates the neurons, the software emulates the neural network.
物理神经⽹络旨在在仿真神经⽹络时将重点放在物理硬件以及软件上。 电可调节的电阻材料⽤于模拟神经突触的功能。 当物理硬件模拟神经元时，软件将模拟神经⽹络。
神经⽹络的应⽤ (Applications of Neural Networks)
Speech Recognition
语⾳识别
Character Recognition
字符识别
Signature Verification Application
签名验证申请
Human Face Recognition
⼈脸识别
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
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。通过与他联系tensorflow入门教程
Comment below if you found any information incorrect or have doubts related to above tutorial for introduction to neural networks.
如果发现任何信息不正确或对上述神经⽹络⼊门教程有疑问，请在下⾯评论。
⼈⼯神经⽹络导论

版权声明：本站内容均来自互联网，仅供演示用，请勿用于商业和其他非法用途。如果侵犯了您的权益请与我们联系QQ:729038198，我们将在24小时内删除。