View Uploaded Answer Sheets Qtext:- A. Assume that in the AdaBoost algorithm, we are initially given a dataset of 6 points with classification (x, y = class): (1, +), (2, +), (3,-), (4, -1), (7, +). The classifier is a decision tree stump choosing a constant c such that all points with x > c are labeled one class and all points with x c are labeled the other class. Assume that the first classifier (i.e, at the end of the first iteration) misclassifies only the points at x = 1 and x = 2. A. What are possible values of c for the first classifier? B. Find the importance of the first classifier. C. Find the values of instance weights at the end of the first iteration. B. Linear regression was performed on a dataset and it was found that the best least square fit was obtained by the line y = 2x + 3. The dataset on which regression was performed was corrupted in storage and it is known that the points are (x, y): (-2,a), (0,1), (2, 3). Can we recover unique values of a, so that the line y = 2x + 3 continues to be the best least square fit? If yes, find those unique values of a,. Otherwise, give a mathematical justification for your answer. C. Suppose a logistic regression classifier (x,y)=1/(1+exp(-w0-7.5*x-7.5*y)) is used to classify the following dataset. What is the range of values w0 can take for 100% classification accuracy? Show the steps clearly. [1.5+1+2.5+4+3=12 Marks] X 0 0 1 1 y 0 1 0 1 class 0 0 0 1