Bias, Variance and Regularization (a) (5 points) The figures below show the decision boundary of three different classifiers. In which of the. figures below does the classifier have a larger bias and in which figure does the classifier has a larger variance? Draw out an approximate graph where you demonstrate how the training and test error for each classifier will change over time during the course of training the model, and explain how do you expect each classifier to perform (accuracy) on the test set. Note: You don't need to calculate the errors, but you should show how the training and test errors compare for different classifiers. (b) (5 points) One strategy to reduce variance and improve generalization is regularization. In figure below, the blue lines are the logistic regression without regularization and the black lines are logistic regression with L1 or L2 regularization. In which figure L1 regularization is used and why