**cost function** - measures the accuracy of our hypothesis function h_{θ}(x)

￼

This function is also called the **squared error cost function** or **mean squared error**.

We want h_{θ}(x) - y to be small.

We minimize the cost function J(θ_{0}θ_{1}) over θ_{0}θ_{1}. J(θ_{0}θ_{1}) is a parabolic function.
Minimizing it means finding the value of θ_{1}.