Coursera Machine Learning Study notes (vii)

-Gradient descent for linear regression

Here we apply the gradient descent algorithm to the linear regression model, we first review the gradient descent algorithm and the linear regression model:

We then expand the slope of the gradient descent algorithm to the partial derivative:

In most cases, the linear regression model cost function is shaped like a convex body, so the local minimum value is equivalent to the global minimum:

The following is the entire convergence and parameter determination process:



Coursera Machine Learning Study notes (vii)