Circle one answer per problem or write down your answer in the space provided. $1.$ T or F Increasing the number of features will always increase the accuracy of the classification. $2.$ T or F Prediction error is caused by both bias and variance of the model $($ignore the residual$).3.$ T or F Binary decision trees with depth one will always give a linear decision boundary.For binary tree is True, but for more branches tree, it gives more parallel straight lines. $4.$ T or F Logistic regression in combination with decision rule is a supervised classification algorithm. $5.$ T or F When a decision tree is grown to full depth, it is more likely to fit the noise in the data.