(a) Describe the difference between the regression and classification setups?

(b) Consider the following set of data points D = {(1,0), (3, 1), (4, 1), (4, 0), (2, 0), (1, 0), (1, 0), (7, 1), (10, 1), (2, 1)}. where, for each observation, (x_n, y_n) D(n = 1,..., 10), x_n is the object attribute and y_n the object label.. Compute the predicted label of a test object with attribute x = 3 using KNN for K = 1,4,9.

(c) Briefly explain why a classification KNN algorithm can be considered an approximation of the Bayes classifier (max 2 or 3 lines).

(d Consider the bias/variance decomposition of the expected error. Which of the following values of K, K=1, K=2, K=100, K=9, defines the model with the highest variance? Justify your answer by briefly explaining how the value of K relates to the model flexibility (max 1 or 2 lines).