Machine Learning - Gradient Descent

function [theta, J_history] = gradientDescent(X, y, theta, alpha, num_iters)
	% Linear Regression
	%  Parameters:
	%		- 	X: Training Set of d(m*n)
	%		-	y: Target Set of d(m*1) 
	%		-	theta: para, d(n*1)
	%		-	alpha: learning ratio
	%		-	num_iters: numer of iterations
	
	m = length(y); 
	J_history = zeros(num_iters, 1);
	fitures = size(X, 2);
	
	for iter = 1:num_iters
	    theta=theta-alpha/m*(X'*(X*theta-y))
	    J_history(iter) = computeCost(X, y, theta);
	end
end

------------------------------------------------------------------------------

function J = computeCost(X, y, theta)
% Compute cost for linear regression
	m = length(y); 
	J = 0;
	delta_y=X*theta-y;
	J=sum((X*theta-y).^2)/2/m
	return;
end