网易云课堂 Machine Learning 编程作业 1：liner regression

网易云课堂 Machine Learning 编程作业 1：liner regression

一.单变量线性回归

1. warmUpExercise.m：Output the 5 by 5 identity matrix

A = eye(5);

2.plotData.m：plot the data

figure; 
plot(x, y, 'rx', 'MarkerSize', 10); 
ylabel('Profit in $10,000s'); 
xlabel('Population of City in 10,000s'); 

3.computeCost.m

$$J(\theta )=\frac{1}{2m}\sum _{i=1}^m{\left(h_{\theta }\left(x^{(i)}\right)-y^{(i)}\right)}^2$$

J = sum((X * theta - y).^2) / (2*m); 

4 .gradientDescent.m:梯度下降法，对参数进行迭代

$${\theta }_j:={\theta }_j-\alpha \frac{1}{m}\sum _{i=1}^m\left(h_{\theta }\left(x^{(i)}\right)-y^{(i)}\right)x_j^{(i)},(j=0,1)$$

theta(1) = theta(1) - alpha / m * sum(X * theta_s - y);       
theta(2) = theta(2) - alpha / m * sum((X * theta_s - y) .* X(:,2));  
theta_s=theta; 

二 .多变量线性回归

1. featureNormalize.m:数据归一化

$$z=\frac{x-\mu }{\sigma }$$

 mu = mean(X);       %  mean value 
 sigma = std(X);     %  standard deviation
 X_norm  = (X - repmat(mu,size(X,1),1)) ./  repmat(sigma,size(X,1),1);

2.computeCostMulti.m：计算代价

J = sum((X * theta - y).^2) / (2*m); 

3.gradientDescentMulti.m：计算梯度

$$\begin{array}{rl}\frac{\partial }{\partial {\theta }_j}J(\theta )& =\frac{1}{2m}\left[2\left(h_{\theta }\left(x^{(1)}\right)-y^{(1)}\right)x_j^{(1)}+2\left(h_{\theta }\left(x^{(2)}\right)-y^{(2)}\right)x_j^{(2)}+\dots \right]\\ & =\frac{1}{m}\sum _{i=1}^m\left(h_{\theta }\left(x^{(i)}\right)-y^{(i)}\right)x_j^{(i)}\end{array}$$

$${\theta }_j:={\theta }_j-\alpha \frac{1}{m}\sum _{i=1}^m\left(h_{\theta }\left(x^{(i)}\right)-y^{(i)}\right)x_j^{(i)},(j=0,1)$$

不适用循环，直接使用矩阵乘法

$$\theta =\theta -\alpha \frac{1}{m}{X}^T(X\theta -Y)$$

theta = theta - alpha / m * X' * (X * theta - y); 

4.根据迭代n次后得到的θ \thetaθ，计算1650平方英尺、3个卧室的房子价钱

price = [1 (([1650 3]-mu) ./ sigma)] * theta ;

三.使用正规方程进行求解

$$\theta ={\left(X^{T}X\right)}^{-1}{X}^{T}Y$$

theta = pinv( X' * X ) * X' * y;

第一次使用markdown编辑，还有很多需要改进和学习的地方