wk1 Linear Regression

最近正在學習MOOC上的經典課程：Machine learning (by Andrew Ng)， 具體課程連結：MACHINE LEARNING
根據進度將作業的關鍵程式碼部分貼上，僅供交流與討論。

• computeCost

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

• gradientDescent

theta = theta - (1/m)*alpha*(X.'*(X*theta-y));
J_history(iter) = computeCost(X, y, theta);

• featureNormalize

mu=mean(X,1);
sigma = std(X);
X_norm = (X - ones(size(X, 1), 1) * mu) ./ (ones(size(X, 1), 1) * sigma);

• computeCostMulti

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

• gradeDescentMulti

theta = theta - (1/m)*alpha*(X.'*(X*theta-y));
J_history(iter) = computeCostMulti(X, y, theta);

• normalEqn

theta=(inv(X.'*X))*X.'*y;

——轉載請註明出處