Question: 4. (a) Consider a linear regression problem y =W1.+ Wo, with a training set having m examples (2.1), (02, y2), ..., (um, Ym). Suppose that

4. (a) Consider a linear regression problem y =W1.+ Wo, with a training set having m examples (2.1), (02, y2), ..., (um, Ym). Suppose that we wish to minimize the mean fifth degree error (loss function) given by: Loss = - (yi - W1.0; wo) i. Derive the equation to calculate the gradient with respect to the parameters W1 and wo. (6 marks) ii. Write the pseudo-code of the gradient descent algorithm for this problem. (6 marks) 4. (a) Consider a linear regression problem y =W1.+ Wo, with a training set having m examples (2.1), (02, y2), ..., (um, Ym). Suppose that we wish to minimize the mean fifth degree error (loss function) given by: Loss = - (yi - W1.0; wo) i. Derive the equation to calculate the gradient with respect to the parameters W1 and wo. (6 marks) ii. Write the pseudo-code of the gradient descent algorithm for this problem. (6 marks)
Step by Step Solution
There are 3 Steps involved in it
Get step-by-step solutions from verified subject matter experts
