Machine learning

Q5: AdaBoost at work (12 points) Consider building an ensemble of decision stumps Gm with the AdaBoost algorithm, M $(x) = sign (am Gm(e) =1 The below figure displays a few labeled points in two dimensions as well as the first stump we have chosen. A decision stump predicts binary +1 values, and depends only on one coordinate value (the split point). The little arrow in the figure is the normal to the stump decision boundary indicating the positive side where the stump predicts +1. All the points start with uniform weights. (a) 2 points List all the points whose weight will increase as a result of incorporating the first stump. 2 X 2 -1 +1 1 B +1 X 1 (b) 4 points Give a possible stump that we could select at the next boosting iteration. Give its orientation (horizontal line/ vertical line), and describe what points are on either side of it. (For example, "Horizontal line; points above: A, D; points below: B, C, E, F") Q5: AdaBoost at work (12 points) Consider building an ensemble of decision stumps Gm with the AdaBoost algorithm, M $(x) = sign (am Gm(e) =1 The below figure displays a few labeled points in two dimensions as well as the first stump we have chosen. A decision stump predicts binary +1 values, and depends only on one coordinate value (the split point). The little arrow in the figure is the normal to the stump decision boundary indicating the positive side where the stump predicts +1. All the points start with uniform weights. (a) 2 points List all the points whose weight will increase as a result of incorporating the first stump. 2 X 2 -1 +1 1 B +1 X 1 (b) 4 points Give a possible stump that we could select at the next boosting iteration. Give its orientation (horizontal line/ vertical line), and describe what points are on either side of it. (For example, "Horizontal line; points above: A, D; points below: B, C, E, F")