Why do we need to define another function grad() , if we already had the function gradientDescent()?
And also what is the use of np.zeros in fn gard()?
will the algorithm work if we dont use grad() but only gradientDescent()?
Why do we need to define another function grad() , if we already had the function gradientDescent()?
And also what is the use of np.zeros in fn gard()?
will the algorithm work if we dont use grad() but only gradientDescent()?