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
- OC-ARC (Automatic Reference Counting) automatic reference counting
- New in GNOME: Warn users when Secure Boot is disabled
- 606. Create a string from a binary tree (video explanation!!!)
- 4. yolov5-6.0 ERROR: AttributeError: 'Upsample' object has no attribute 'recompute_scale_factor' solution
- 分页 paging
- 大根堆的创建(视频讲解)
- 这种叫什么手法
- Re16:读论文 ILDC for CJPE: Indian Legal Documents Corpus for Court Judgment Prediction and Explanation
- Understanding of deadlock
- 自适应控制——仿真实验一 用李雅普诺夫稳定性理论设计自适应规律
猜你喜欢

Re19:读论文 Paragraph-level Rationale Extraction through Regularization: A case study on European Court

通过构建一个顺序表——教你计算时间复杂度和空间复杂度(含递归)
![[Deep Learning] (Problem Record) <What do I get by calculating the gradient of a variable> - Linear Regression - Small Batch Stochastic Gradient Descent](/img/28/834aac16859fd26ab69de30f5fed55.png)
[Deep Learning] (Problem Record)
- Linear Regression - Small Batch Stochastic Gradient Descent 
图像去噪——Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Images

Meikle Studio - see the actual combat notes of Hongmeng equipment development five - drive subsystem development

Flask之路由(app.route)详解

梅科尔工作室-看鸿蒙设备开发实战笔记四——内核开发

Flask's routing (app.route) detailed

Study Notes 11--Direct Construction of Local Trajectories

WARN: Establishing SSL connection without server's identity verification is not recommended when connecting to mysql
随机推荐
OC- about alloc and dealloc (haven't started writing yet)
flowable workflow all business concepts
神经网络学习笔记4——自动编码器(含稀疏,堆叠)(更新中)
Shell system learning function
MySQL installation tutorial [installation version]
判断一颗树是否为完全二叉树——视频讲解!!!
Determine whether a tree is a complete binary tree - video explanation!!!
【HMS core】【FAQ】HMS Toolkit Typical Questions Collection 1
In 2022, the top will be accepted cca shut the list
多线程保证单个线程开启事务并生效的方案
关于verilog的时延研究
Container Technology - A Simple Understanding of Kubernetes Objects
Re15:读论文 LEVEN: A Large-Scale Chinese Legal Event Detection Dataset
在机器人行业的专业人士眼里,机器人行业目前的情况如何?
Baidu promotion assistant encounters duplicate keywords, verification errors, how to delete redundant ones with one click
阿里云OSS对象存储
what is this method called
系统设计精选 | 基于FPGA的CAN总线控制器的设计(附代码)
Re16: Read the paper ILDC for CJPE: Indian Legal Documents Corpus for Court Judgment Prediction and Explanation
第2章 常用安全工具