多层感知机详解(如果增加多层感知机的隐藏层层数)

Principlesoftrainingmulti-layerneuralnetworkusingbackpropagation  Theprojectdescribesteachingprocessofmulti-layerneuralnetworkemploying backpropagation algorithm.Toillustrateth…

大家好,又见面了,我是你们的朋友全栈君。

Principles of training multi-layer neural network using backpropagation


 

The project describes teaching process of multi-layer neural network employing backpropagation algorithm. To illustrate this process the three layer neural network with two inputs and one output,which is shown in the picture below, is used: 
 

多层感知机详解(如果增加多层感知机的隐藏层层数)

Each neuron is composed of two units. First unit adds products of weights coefficients and input signals. The second unit realise nonlinear function, called neuron activation function. Signal e is adder output signal, and y = f(e) is output signal of nonlinear element. Signal y is also output signal of neuron. 
 

多层感知机详解(如果增加多层感知机的隐藏层层数)

To teach the neural network we need training data set. The training data set consists of input signals (x1 and x2 ) assigned with corresponding target (desired output) z. The network training is an iterative process. In each iteration weights coefficients of nodes are modified using new data from training data set. Modification is calculated using algorithm described below: Each teaching step starts with forcing both input signals from training set. After this stage we can determine output signals values for each neuron in each network layer. Pictures below illustrate how signal is propagating through the network, Symbols w(xm)n represent weights of connections between network input xm and neuron n in input layer. Symbols yn represents output signal of neuron n
 

多层感知机详解(如果增加多层感知机的隐藏层层数)

 

多层感知机详解(如果增加多层感知机的隐藏层层数)

 

多层感知机详解(如果增加多层感知机的隐藏层层数)

Propagation of signals through the hidden layer. Symbols wmn represent weights of connections between output of neuron m and input of neuron n in the next layer. 
 

多层感知机详解(如果增加多层感知机的隐藏层层数)

 

多层感知机详解(如果增加多层感知机的隐藏层层数)

Propagation of signals through the output layer. 
 

多层感知机详解(如果增加多层感知机的隐藏层层数)

In the next algorithm step the output signal of the network y is compared with the desired output value (the target), which is found in training data set. The difference is called error signal d of output layer neuron. 
 

多层感知机详解(如果增加多层感知机的隐藏层层数)

It is impossible to compute error signal for internal neurons directly, because output values of these neurons are unknown. For many years the effective method for training multiplayer networks has been unknown. Only in the middle eighties the backpropagation algorithm has been worked out. The idea is to propagate error signal d (computed in single teaching step) back to all neurons, which output signals were input for discussed neuron. 
 

多层感知机详解(如果增加多层感知机的隐藏层层数)

 

多层感知机详解(如果增加多层感知机的隐藏层层数)

The weights’ coefficients wmn used to propagate errors back are equal to this used during computing output value. Only the direction of data flow is changed (signals are propagated from output to inputs one after the other). This technique is used for all network layers. If propagated errors came from few neurons they are added. The illustration is below: 
 

多层感知机详解(如果增加多层感知机的隐藏层层数)

 

多层感知机详解(如果增加多层感知机的隐藏层层数)

 

多层感知机详解(如果增加多层感知机的隐藏层层数)

When the error signal for each neuron is computed, the weights coefficients of each neuron input node may be modified. In formulas belowdf(e)/de represents derivative of neuron activation function (which weights are modified). 
 

多层感知机详解(如果增加多层感知机的隐藏层层数)

 

多层感知机详解(如果增加多层感知机的隐藏层层数)

 

多层感知机详解(如果增加多层感知机的隐藏层层数)

 

多层感知机详解(如果增加多层感知机的隐藏层层数)

 

多层感知机详解(如果增加多层感知机的隐藏层层数)

 

多层感知机详解(如果增加多层感知机的隐藏层层数)

Coefficient h affects network teaching speed. There are a few techniques to select this parameter. The first method is to start teaching process with large value of the parameter. While weights coefficients are being established the parameter is being decreased gradually. The second, more complicated, method starts teaching with small parameter value. During the teaching process the parameter is being increased when the teaching is advanced and then decreased again in the final stage. Starting teaching process with low parameter value enables to determine weights coefficients signs. 

版权声明:本文内容由互联网用户自发贡献,该文观点仅代表作者本人。本站仅提供信息存储空间服务,不拥有所有权,不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容, 请发送邮件至 举报,一经查实,本站将立刻删除。

发布者:全栈程序员-用户IM,转载请注明出处:https://javaforall.cn/128063.html原文链接:https://javaforall.cn

【正版授权,激活自己账号】: Jetbrains全家桶Ide使用,1年售后保障,每天仅需1毛

【官方授权 正版激活】: 官方授权 正版激活 支持Jetbrains家族下所有IDE 使用个人JB账号...

(0)


相关推荐

  • mysql表锁与行锁_考核机制表

    mysql表锁与行锁_考核机制表MySQL表锁和行锁机制行锁变表锁,是福还是坑?如果你不清楚MySQL加锁的原理,你会被它整的很惨!不知坑在何方?没事,我来给你们标记几个坑。遇到了可别乱踩。通过本章内容,带你学习MySQL的行锁,表锁,两种锁的优缺点,行锁变表锁的原因,以及开发中需要注意的事项。还在等啥?经验等你来拿!MySQL的存储引擎是从MyISAM到InnoDB,锁从表锁到行锁。后者的出现从某种程度上是弥补前者的…

  • vue引入外部js文件并使用_为什么vue不使用ajax

    vue引入外部js文件并使用_为什么vue不使用ajax在一个组件内部需要引入一个js文件,如果放在index.html,每个组件都会有这个js,所以需要在组件内单独引入。下载静态文件下来后,放入文件夹:组件代码:<template><div><button@click=”compressImage”>点击调用方法</button></div></template><script>importImageCompressorfrom’@/

  • android之Random.nextInt(k)陷阱「建议收藏」

    android之Random.nextInt(k)陷阱「建议收藏」API:Returnsapseudo-randomuniformlydistributedintinthehalf-openrange[0,k). 意思就是说,nextInt的取值是0到k-1,不包括k。

  • kubernetes安装及集群搭建

    kubernetes安装及集群搭建

  • 两个服务通过http传输excel文件

    两个服务通过http传输excel文件两个服务通过http传输excel文件

  • 分析了10万条B站UP主数据后,我知道了成为百万粉丝UP主的一些秘密「建议收藏」

    分析了10万条B站UP主数据后,我知道了成为百万粉丝UP主的一些秘密「建议收藏」前几天一位好朋友入了B站,问我如何才能成为一名百万粉丝的up主。这不,于是我做了这篇的一些分析,知道了成为百万粉丝up主的一些小秘密。还做了一个昵称生成器,给其昵称起名提供建议。这是她的b站视频截图:关于昵称起名我的想法是这样,是我们把B站这些百万粉丝大佬的昵称分析一下成分构成,根据相关性随机起个名,是不是就有百万粉丝up主昵称的那味了?上面截图是她改名前的昵称,是否会改名,改名后叫什么咱们拭目以待。咱们现在就开始爬取整整:B站up主信息爬取直接通过b站首页去爬是很不方便的,这里我找到了两个第

发表回复

您的电子邮箱地址不会被公开。

关注全栈程序员社区公众号