costFunctionJ.m

function J = costFunctionJ(X, Y, Theta)

% X is desgin matrix contanining all of the traning data
% Y is the real price

m = size (X, 1); % how many rows does X have, m means the size of traning set
Predictions = X*Theta; % here you will get a m x 1 matrix, actually this is a vector, whose length is the same as Y's, so it's ok to use Predictions substract Y
sqrErrors = (Predictions-Y).^2;

J = 1/(2*m)*sum(sqrErrors);