Cost Function (Squared error function)
Cost Functions helps us figure out how to fit the best possible straight line in our data.
Recall that m is the number of training examples (number of rows)
Parameters
In linear regression we have a training set like the one plotted above, what we want to do is to come up with values for the parameters (theta 0 and theta 1) so that the straight line we get out of it, corresponds to a straight line that somehow fits the data well.
NOTE:
y = mx + c # equation of a line
theta 0 = c
theta 1 = m
y = h(theta0, theta 1)
Minimising Theta 0, Theta 1