Problem 1 (16 Points): Probability Review Consider a classifier which randomly assigns labels to data points; specifically, for each label , it assigns that label with probability proportional to the number of times that label appears in the training dataset. Let the size of training set be N, total number of classes be K and ne be number of data points belonging to class c (zinc = N). Then the probability of labelling a data point with class c is ne/N. Consider a training set with N = 100, C = 2, n1 = n2 = 50 and a testing set with N = 100, C = 2, n1 = 30, n2 = 70. 1. 4 Points. What is the expected accuracy of the classifier on the training set? 2. 4 Points. What is the expected accuracy of the classifier on the testing set? Now consider a training set with N = 100, C = 3, n1 = 50, n2 = 20, n3 = 30 and a testing set with N = 100, C = 3, n1 = 20, n2 = 20, n3 = 60. 1. 4 Points. What is the expected accuracy of the classifier on the training set? 2. 4 Points. What is the expected accuracy of the classifier on the testing set