当前位置:网站首页>Neural Network Study Notes 4 - Autoencoder (including sparse, stacked) (updated)
Neural Network Study Notes 4 - Autoencoder (including sparse, stacked) (updated)
2022-07-30 10:40:00 【Oreos are delicious】
目录
配套讲解视频
It is recommended to read the blog post in conjunction with the video
10Minutes to learn automatic encoder from principle to programming implementation_哔哩哔哩_bilibili
10Minutes to learn automatic encoder from principle to programming implementation
1.Programs and Datasets
链接:https://pan.baidu.com/s/1aSNq94BJuKsiKO5gNGF29Q
提取码:6666
--来自百度网盘超级会员V5的分享
2.自动编码器
2.1自编码器原理
Learning efficient encodings in a set of data by means of unsupervised learning


The target of the autoencoder:Re-extract features,降低维度,Minimize refactoring errors
目标函数:Make the refactoring error as 0

Simple two-layer autoencoder example

2.2代码实现
1.数据导入
D=xlsread('C:\Users\86188\Desktop\B站ppt\ae\RaisinDataset.xlsx');
data=D(:,1:7)';
label=D(:,8)';2.数据集处理
k=rand(1,900);
[m,n]=sort(k);
input_train=data(:,n(1:750));
input_test=data(:,n(751:900));
output_train=label(:,n(1:750));
output_test=label(:,n(751:900));
x = input_train;
t=ind2vec(output_train);
t=full(t)3.设置网络结构
ae1=trainAutoencoder(x,5);
features=encode(ae1,x);
softmax=trainSoftmaxLayer(features,t);
nets=stack(ae1,softmax);4.显示结果,测试网络
view(nets)
output_test
y=nets(input_test) 
5.计算准确率
for i=1:150
output_fore(i)=find(y(:,i)==max(y(:,i)));
end
right1=0;
for i=1:150
if output_fore(i) == output_test(i)
right1=right1+1;
end
end
right=right1/1503.堆叠式自编码器
对于很多数据来说,仅使用两层神经网络的自编码器还不足以获取一种好的数据表示,为了获取更好的数据表示,我们可以使用更深层的神经网络,深层神经网络作为自编码器提取的数据表示一般会更加抽象,It can better capture the semantic information of the data.
在实践中经常使用逐层堆叠的方式来训练一个深层的自编码器.称为堆叠自编码器(StackedAuto-EncoderSAE)Stacked autoencoders can generally be trained layer by layer(Layer-WiseTraining)来学习网络参数
4.稀疏自编码器
4.1稀疏编码
Advantages of sparse coding
(1).计算量
稀疏性带来的最大好处就是可以极大地降低计算量.
(2)可解释性
因为稀疏编码只有少数的非零元素,相当于将一个输入样本表示为少数几个相关的特征.这样我们可以更好地描述其特征,并易于理解.
(3)特征选择
稀疏性带来的另外一个好处是可以实现特征的自动选择,只选择和输入样本相关的最少特征,This allows for a better representation of the input samples,降低噪声并减轻过拟合.
4.2.稀疏自编码器
By feeding the hidden layer units in the autoencoderz加上稀疏性限制,自编码器可以学习到数据中一些有用的结构.
目标函数

WRepresents a parameter in the autoencoder
和稀疏编码一样,The advantage of sparse autoencoders is high interpretability,并同时进行了隐式的特征选择.
结构图

边栏推荐
- 【HMS core】【Analytics Kit】【FAQ】如何解决华为分析付费分析中付款金额显示为0的问题?
- 大根堆的创建(视频讲解)
- Neural Ordinary Differential Equations
- Multithreading--the usage of threads and thread pools
- Meikle Studio-Look at Hongmeng Device Development Practical Notes 7-Network Application Development
- Security Thought Project Summary
- 再有人问你分布式事务,把这篇扔给他
- flyway的快速入门教程
- 死锁的理解
- OC-手动引用计数内存管理
猜你喜欢

Re20:读论文 What About the Precedent: An Information-Theoretic Analysis of Common Law

JVM内存布局、类加载机制及垃圾回收机制详解

【C和指针第七章】可变参数列表

Pytorch中 nn.Transformer的使用详解与Transformer的黑盒讲解

Meikle Studio-Look at Hongmeng Device Development Practical Notes 7-Network Application Development

Materialist Dialectics - Conditionalism

If someone asks you about distributed transactions again, throw this to him
![MySQL installation tutorial [installation version]](/img/e9/9c7b0e3aac22206d126de428c1a4bd.png)
MySQL installation tutorial [installation version]

(***Key points***) Flink common memory problems and tuning guide (1)

Detailed explanation of JVM memory layout, class loading mechanism and garbage collection mechanism
随机推荐
Basic operations of sequence table in C language
jmeter接口压力测试-(二)
105. Construct binary tree from preorder and inorder traversal sequence (video explanation!!)
唯物辩证法-条件论
Multi-threading scheme to ensure that a single thread opens a transaction and takes effect
OC-ARC(Automatic Reference Counting)自动引用计数
软考 系统架构设计师 简明教程 | 案例分析 | 需求分析
GNOME 新功能:安全启动被禁用时警告用户
【C和指针第七章】可变参数列表
你真的懂Redis的5种基本数据结构吗?
ospf2 two-point two-way republish (question 2)
Flask之路由(app.route)详解
电压跟随器不要随便加
The thread pool method opens the thread -- the difference between submit() and execute()
Four ways the Metaverse is changing the way humans work
Paper reading: SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers
WARN: Establishing SSL connection without server's identity verification is not recommended when connecting to mysql
Basemap and Seaborn
Beijing suddenly announced big news in the Metaverse
kubernetes的一些命令