In this assignment, we will learn how to fit a polynomial to data points (x,t) using 1) Maximum Likelihood (ML) estimation --- find w that maximises p(t|x,w) 2) Maximum Posterior (MAP) estimation --- find w that maximises p(w|x,t) 3) Bayesian approach --- models the predictive distribution p(t|x,w) (does not find optimal w) The Matlab files in this assignment are generate_data.m generates data from the sin(2*pi) function and adds random noise. evaluate_polynomial.m evaluates polynomial w at points in vector x fit_polynomial_ML.m fits a polynomial to data x,t via Maximum Likelihood (ML) estimation fit_polynomial_MAP.m fits a polynomial to data x,t via Maximum Posterior (MAP) estimation fit_polynomial_bayesian.m computes the optimal predictive distribution p(t|x,w) fit_multivariate_gaussian.m fits a multivariate gaussian to data You have to fill in the missing pieces of code in evaluate_polynomial.m fit_polynomial_ML.m fit_polynomial_MAP.m To generate all results required for this assignment, run the provided script get_all_results.