Exercise: PCA in 2D
Step 0: Load data
The starter code contains code to load 45 2D data points. When plotted using the scatter function, the results should look like the following:
Step 1: Implement PCA
In this step, you will implement PCA to obtain xrot, the matrix in which the data is "rotated" to the basis comprising made up of the principal components
Step 1a: Finding the PCA basis
Find and , and draw two lines in your figure to show the resulting basis on top of the given data points.
Step 1b: Check xRot
Compute xRot, and use the scatter function to check that xRot looks as it should, which should be something like the following:
Step 2: Dimension reduce and replot
In the next step, set k, the number of components to retain, to be 1
Step 3: PCA Whitening
Step 4: ZCA Whitening
Code
close all %%================================================================
%% Step : Load data
% We have provided the code to load data from pcaData.txt into x.
% x is a * matrix, where the kth column x(:,k) corresponds to
% the kth data point.Here we provide the code to load natural image data into x.
% You do not need to change the code below. x = load('pcaData.txt','-ascii'); % 载入数据
figure();
scatter(x(, :), x(, :)); % 用圆圈绘制出数据分布
title('Raw data'); %%================================================================
%% Step 1a: Implement PCA to obtain U
% Implement PCA to obtain the rotation matrix U, which is the eigenbasis
% sigma. % -------------------- YOUR CODE HERE --------------------
u = zeros(size(x, )); % You need to compute this
[n m]=size(x);
% x=x-repmat(mean(x,),,m); %预处理,均值为零 —— 2维,每一维减去该维上的均值
sigma=(1.0/m)*x*x'; % 协方差矩阵
[u s v]=svd(sigma); % --------------------------------------------------------
hold on
plot([ u(,)], [ u(,)]); % 画第一条线
plot([ u(,)], [ u(,)]); % 画第二条线
scatter(x(, :), x(, :));
hold off %%================================================================
%% Step 1b: Compute xRot, the projection on to the eigenbasis
% Now, compute xRot by projecting the data on to the basis defined
% by U. Visualize the points by performing a scatter plot. % -------------------- YOUR CODE HERE --------------------
xRot = zeros(size(x)); % You need to compute this
xRot=u'*x; % -------------------------------------------------------- % Visualise the covariance matrix. You should see a line across the
% diagonal against a blue background.
figure();
scatter(xRot(, :), xRot(, :));
title('xRot'); %%================================================================
%% Step : Reduce the number of dimensions from to .
% Compute xRot again (this time projecting to dimension).
% Then, compute xHat by projecting the xRot back onto the original axes
% to see the effect of dimension reduction % -------------------- YOUR CODE HERE --------------------
k = ; % Use k = and project the data onto the first eigenbasis
xHat = zeros(size(x)); % You need to compute this
xHat = u*([u(:,),zeros(n,)]'*x); % 降维
% 使特征点落在特征向量所指的方向上而不是原坐标系上 % --------------------------------------------------------
figure();
scatter(xHat(, :), xHat(, :));
title('xHat'); %%================================================================
%% Step : PCA Whitening
% Complute xPCAWhite and plot the results. epsilon = 1e-;
% -------------------- YOUR CODE HERE --------------------
xPCAWhite = zeros(size(x)); % You need to compute this
xPCAWhite = diag(./sqrt(diag(s)+epsilon))*u'*x; % 每个特征除以对应的特征向量,以使每个特征有一致的方差
% --------------------------------------------------------
figure();
scatter(xPCAWhite(, :), xPCAWhite(, :));
title('xPCAWhite'); %%================================================================
%% Step : ZCA Whitening
% Complute xZCAWhite and plot the results. % -------------------- YOUR CODE HERE --------------------
xZCAWhite = zeros(size(x)); % You need to compute this
xZCAWhite = u*diag(./sqrt(diag(s)+epsilon))*u'*x; % --------------------------------------------------------
figure();
scatter(xZCAWhite(, :), xZCAWhite(, :));
title('xZCAWhite'); %% Congratulations! When you have reached this point, you are done!
% You can now move onto the next PCA exercise. :)
Exercise: PCA in 2D的更多相关文章
- 【DeepLearning】Exercise:PCA in 2D
Exercise:PCA in 2D 习题的链接:Exercise:PCA in 2D pca_2d.m close all %%=================================== ...
- 【DeepLearning】Exercise:PCA and Whitening
Exercise:PCA and Whitening 习题链接:Exercise:PCA and Whitening pca_gen.m %%============================= ...
- Deep Learning 4_深度学习UFLDL教程:PCA in 2D_Exercise(斯坦福大学深度学习教程)
前言 本节练习的主要内容:PCA,PCA Whitening以及ZCA Whitening在2D数据上的使用,2D的数据集是45个数据点,每个数据点是2维的.要注意区别比较二维数据与二维图像的不同,特 ...
- UFLDL教程笔记及练习答案二(预处理:主成分分析和白化)
首先将本节主要内容记录下来.然后给出课后习题的答案. 笔记: :首先我想推导用SVD求解PCA的合理性. PCA原理:如果样本数据X∈Rm×n.当中m是样本数量,n是样本的维数.PCA降维的目的就是为 ...
- Deep Learning 教程(斯坦福深度学习研究团队)
http://www.zhizihua.com/blog/post/602.html 说明:本教程将阐述无监督特征学习和深度学习的主要观点.通过学习,你也将实现多个功能学习/深度学习算法,能看到它们为 ...
- [Scikit-learn] 4.3 Preprocessing data
数据分析的重难点,就这么来了,欢迎欢迎,热烈欢迎. 4. Dataset transformations 4.3. Preprocessing data 4.3.1. Standardization, ...
- UFLDL教程之(三)PCA and Whitening exercise
Exercise:PCA and Whitening 第0步:数据准备 UFLDL下载的文件中,包含数据集IMAGES_RAW,它是一个512*512*10的矩阵,也就是10幅512*512的图像 ( ...
- PCA and kmeans MATLAB实现
MATLAB基础知识 l Imread: 读取图片信息: l axis:轴缩放:axis([xmin xmax ymin ymax zmin zmax cmin cmax]) 设置 x.y 和 ...
- Deep Learning 5_深度学习UFLDL教程:PCA and Whitening_Exercise(斯坦福大学深度学习教程)
前言 本文是基于Exercise:PCA and Whitening的练习. 理论知识见:UFLDL教程. 实验内容:从10张512*512自然图像中随机选取10000个12*12的图像块(patch ...
随机推荐
- PostgreSQL Replication之第四章 设置异步复制(5)
4.5 使流复制更健壮 当连接到master时,slave要做的第一件事情是赶上master.但是,这会一直工作吗?我们已经看到,我们可以使用由基于流和基于文件组成的混合设置.这给了我们一些额外的安全 ...
- 【Git 四】一款不错的 Git 客户端
平常做开发使用 git bash 进行代码提交,一直没有使用过 git 相关的客户端. 直到有次同一分支下两个日志进行代码比较时,bash 返回的结果可视化理解起来比较差. 如果更改的部分比较多,问题 ...
- Tomcat IO阻塞异常
tomcat的maxThreads.acceptCount(最大线程数.最大排队数) tomcat 的Connector配置如下 <Connector port="8080" ...
- [NOI2016]优秀的拆分(SA数组)
[NOI2016]优秀的拆分 题目描述 如果一个字符串可以被拆分为 \(AABB\) 的形式,其中 A和 B是任意非空字符串,则我们称该字符串的这种拆分是优秀的. 例如,对于字符串 \(aabaaba ...
- myeclipse2013 jsp编辑初始化
首先,大家可能有过这种经历.双击打开jsp编辑.它默认会打开视图,这样就使人恼火了,卡死了.所以我们能够自己设jsp的默认打开方式:打开Window-->preferences得: 搜索edit ...
- bzoj 2120 数颜色 题解
转载请注明:http://blog.csdn.net/jiangshibiao/article/details/23990489 [原题] 2120: 数颜色 Time Limit: 6 Sec M ...
- linux命令su与su-的差别
su命令和su -命令最大的本质差别就是: su仅仅是切换了root身份.但Shell环境仍然是普通用户的Shell. 而su -连用户和Shell环境一起切换成root身份了. 仅仅有切换了Shel ...
- Java中AtomicInteger的使用!!!
今天在看Volley的源码的时候,看到里面使用了AtomicInteger这个类,曾经没用过,今天看了一下API学习了一下: 首先介绍一下这个类的用处,这个类主要是用来替换java中的自增和自减操作, ...
- 【LeetCode-面试算法经典-Java实现】【063-Unique Paths II(唯一路径问题II)】
[063-Unique Paths II(唯一路径问题II)] [LeetCode-面试算法经典-Java实现][全部题目文件夹索引] 原题 Follow up for "Unique Pa ...
- Linq中where查询
Linq的Where操作包括3种形式:简单形式.关系条件形式.First()形式. 1.简单形式: 例:使用where查询在北京的客户 var q = from c in db.Customers ...